OpenUCT :: Browsing by Author "Douglas, Tania"

Browsing by Author "Douglas, Tania"

Now showing 1 - 20 of 20

Open Access
A deep learning algorithm for contour detection in synthetic 2D biplanar X-ray images of the scapula: towards improved 3D reconstruction of the scapula
(University of Cape Town, 2020) Namayega, Catherine; Mutsvangwa, Tinashe; Malila, Bessie; Douglas, Tania
Three-dimensional (3D) reconstruction from X-ray images using statistical shape models (SSM) provides a cost-effective way of increasing the diagnostic utility of two-dimensional (2D) X-ray images, especially in low-resource settings. The landmark-constrained model fitting approach is one way to obtain patient-specific models from a statistical model. This approach requires an accurate selection of corresponding features, usually landmarks, from the bi-planar X-ray images. However, X-ray images are 2D representations of 3D anatomy with super-positioned structures, which confounds this approach. The literature shows that detection and use of contours to locate corresponding landmarks within biplanar X-ray images can address this limitation. The aim of this research project was to train and validate a deep learning algorithm for detection the contour of a scapula in synthetic 2D bi-planar Xray images. Synthetic bi-planar X-ray images were obtained from scapula mesh samples with annotated landmarks generated from a validated SSM obtained from the Division of Biomedical Engineering, University of Cape Town. This was followed by the training of two convolutional neural network models as the first objective of the project; the first model was trained to predict the lateral (LAT) scapula image given the anterior-posterior (AP) image. The second model was trained to predict the AP image given the LAT image. The trained models had an average Dice coefficient value of 0.926 and 0.964 for the predicted LAT and AP images, respectively. However, the trained models did not generalise to the segmented real X-ray images of the scapula. The second objective was to perform landmark-constrained model fitting using the corresponding landmarks embedded in the predicted images. To achieve this objective, the 2D landmark locations were transformed into 3D coordinates using the direct linear transformation. The 3D point localization yielded average errors of (0.35, 0.64, 0.72) mm in the X, Y and Z directions, respectively, and a combined coordinate error of 1.16 mm. The reconstructed landmarks were used to reconstruct meshes that had average surface-to-surface distances of 3.22 mm and 1.72 mm for 3 and 6 landmarks, respectively. The third objective was to reconstruct the scapula mesh using matching points on the scapula contour in the bi-planar images. The average surface-to-surface distances of the reconstructed meshes with 8 matching contour points and 6 corresponding landmarks of the same meshes were 1.40 and 1.91 mm, respectively. In summary, the deep learning models were able to learn the mapping between the bi-planar images of the scapula. Increasing the number of corresponding landmarks from the bi-planar images resulted into better 3D reconstructions. However, obtaining these corresponding landmarks was non-trivial, necessitating the use of matching points selected from the scapulae contours. The results from the latter approach signal a need to explore contour matching methods to obtain more corresponding points in order to improve the scapula 3D reconstruction using landmark-constrained model fitting.
Open Access
Analysis of orthopaedic device development in South Africa: Mapping the landscape and understanding the drivers of knowledge development and knowledge diffusion through networks
(2021) Salie, Faatiema; Douglas, Tania; de Jager, Kylie
An orthopaedic medical device refers to a part, implant, prosthetic or orthotic which is used to address damage to the body's musculoskeletal system, primarily by providing stability and mobility. Orthopaedic medical devices play a role in injury-related disorders, which have been highlighted as a key element of the quadruple burden of disease in South Africa. In this thesis, orthopaedic devices are conceptualised as a technological field and a technological innovation system (TIS) framework is applied to understand orthopaedic device development in South Africa. Knowledge development and knowledge diffusion are fundamental components of any innovation system. The thesis hypothesises that the functions “knowledge development” and “knowledge diffusion through networks” of the orthopaedic devices TIS are influenced by contextual factors. The objectives of the study are: to identify the actors who generate knowledge for orthopaedic device development and to characterise the relationships between them; to identify focus areas of orthopaedic device development; to provide insight into the drivers and barriers to knowledge development and diffusion in the TIS; and to identify the contextual factors that influence knowledge dynamics in the TIS. These objectives are investigated using social network analysis based on bibliometric data (scientific publications and patents), keyword networks, a review of institutions, and a set of case studies where the primary data source are interviews with actors. Actors producing knowledge were from the university, healthcare, industry and science council sectors, although science councils played a small role. International actors were shown to bring new ideas into the TIS. The networks were fragmented, illustrating that knowledge diffusion through the networks was limited. This was especially the case in the patent networks as many actors patent in isolation. The keyword networks highlighted unrealised collaboration potential between actors based on their common research interests. The case studies revealed features of cross-sector interaction for orthopaedic device development not evident from network analysis based on bibliometric data. Drivers of knowledge development and knowledge diffusion were: inter-sectoral collaboration; the availability of resources; the affordability of available devices; and the positive externalities of allied TISs. The main barrier to knowledge development and diffusion was in the form of barriers to intersectoral collaboration. These include unmatched expectations from partners in collaboration, different views on intellectual property ownership, and burdensome university administrative processes. The orthopaedic devices TIS was structurally coupled to the embedded TIS and sectoral contexts, and externally linked and structurally coupled to its political context. Knowledge development and diffusion was found to be positively enhanced by innovation in the additive manufacturing TIS, with shared structural elements and resources. Knowledge development and diffusion was influenced by sectoral dynamics of the university, healthcare and industry sectors. This thesis makes the following contributions. First, it applies the TIS framework to a new focus area, namely medical device development, in a developing country context. Second, it makes two unique methodological contributions: it presents an index to capture the extent of sectoral collaboration in a network; and it develops a method for determining the collaboration potential of actors in a network based on cognitive distance.
Open Access
Articulated Statistical Shape Modelling of the Shoulder Joint
(2020) Alemneh, Tewodros; Mutsvangwa, Tinashe; Douglas, Tania
The shoulder joint is the most mobile and unstable joint in the human body. This makes it vulnerable to soft tissue pathologies and dislocation. Insight into the kinematics of the joint may enable improved diagnosis and treatment of different shoulder pathologies. Shoulder joint kinematics can be influenced by the articular geometry of the joint. The aim of this project was to develop an analysis framework for shoulder joint kinematics via the use of articulated statistical shape models (ASSMs). Articulated statistical shape models extend conventional statistical shape models by combining the shape variability of anatomical objects collected from different subjects (statistical shape models), with the physical variation of pose between the same objects (articulation). The developed pipeline involved manual annotation of anatomical landmarks selected on 3D surface meshes of scapulae and humeri and establishing dense surface correspondence across these data through a registration process. The registration was performed using a Gaussian process morphable model fitting approach. In order to register two objects separately, while keeping their shape and kinematics relationship intact, one of the objects (scapula) was fixed leaving the other (humerus) to be mobile. All the pairs of registered humeri and scapulae were brought back to their native imaged position using the inverse of the associated registration transformation. The glenohumeral rotational center and local anatomic coordinate system of the humeri and scapulae were determined using the definitions suggested by the International Society of Biomechanics. Three motions (flexion, abduction, and internal rotation) were generated using Euler angle sequences. The ASSM of the model was built using principal component analysis and validated. The validation results show that the model adequately estimated the shape and pose encoded in the training data. Developing ASSM of the shoulder joint helps to define the statistical shape and pose parameters of the gleno humeral articulating surfaces. An ASSM of the shoulder joint has potential applications in the analysis and investigation of population-wide joint posture variation and kinematics. Such analyses may include determining and quantifying abnormal articulation of the joint based on the range of motion; understanding of detailed glenohumeral joint function and internal joint measurement; and diagnosis of shoulder pathologies. Future work will involve developing a protocol for encoding the shoulder ASSM with real, rather than handcrafted, pose variation.
Open Access
Assessing eHealth knowledge diffusion within the public health sector in Kenya using social network analysis
(2020) Gitau, Ryan Nyotu; Douglas, Tania
High disease morbidity coupled with limited healthcare personnel places the health sector in Kenya under strain, leaving parts of the population with limited access to health services. Electronic health (eHealth), the utilisation of information and communication technologies in healthcare, is an innovation with the potential to improve access to health services. Several examples exist of eHealth projects being undertaken in Kenya. However, eHealth solutions have been poorly adopted in the public healthcare sector, which has partly been blamed on lack of knowledge amongst healthcare providers and patients. The aim of this study was to examine how knowledge is exchanged between the stakeholders currently active within the eHealth implementation space in the Kenyan public sector. The results of the study would aid in identifying communication breakdowns and ways of increasing information flow with regard to eHealth, and ultimately would aid strategies to help improve the uptake of eHealth within the public sector. A mixed methods study was undertaken that combined quantitative social network analysis and qualitative analysis of semi-structured interviews conducted with stakeholders involved in implementation of eHealth projects in Kenya. Publications on implementation of eHealth projects in Kenya from 2001 to 2018 were used to obtain data on relevant organisations. Social network analysis was used to identify prominent actors. Individuals working within such organisations were invited to participate in semi-structured interviews. Further social network analysis was applied to data gathered through the interviews. Foreign universities and foreign not-for-profit organisations were the most commonly identified organisations in the networks generated. The tacit nature of knowledge within networks, low research capacity and output, information guarding, geographical distance between collaborating organisations, and low cohesion were some of the factors found to inhibit knowledge diffusion within the eHealth implementation space in Kenya. The search for capacity and funding were found to contribute to network structure. eHealth knowledge management strategies should be given attention, for enhanced exchange of knowledge within the public health sector in Kenya.
Open Access
Designing the concept for a mobile health solution to educate female scholars residing in a low-to-middle income socio economic setting in Cape Town about HPV and its vaccine
(2022) Oliver, Kedebone; Fortuin, Jill; Douglas, Tania
Introduction Cervical cancer is the second most common cancer in South African women and fourth most common in women worldwide. Human papillomavirus (HPV) infection is the causative agent of 90% of cervical cancers. It can be prevented, especially in younger, non-sexually active individuals through a 2- or 3-dose vaccination. The vaccines are given free of charge to female grade 4 learners (9-15 year-olds) in South African public schools since 2014. The vaccination programme was promoted through educational pamphlets, posters, publications on the government websites, social media, and broadcasts on national radio and television prior to the start of the campaign. However, the available vaccines do not protect against all types of HPVs, and thus consistent education would be useful to advise young girls about safe lifestyle choices. Young people use mobile devices extensively, and therefore these devices may be an effective way to reach them directly, and to engage with them consistently. The project aimed to design the concept for a mobile health (mHealth) solution to aid in educating young female scholars residing in a low-to- middle-income setting in Cape Town about HPV and its vaccine. Methodology A user-centred approach known as the Information systems research (ISR) design framework was used to design the concept for a mHealth solution. It involved three main steps that were applied in a cyclic manner: namely the cycles of relevance, design and rigour. The relevance cycle involved assessment of the needs and knowledge of the target population (grade 4-7 female scholars of the Ikamva Labantwana Bethu tutoring programme in Crossroads) through a quantitative survey with 43 participants, which was followed by two focus group discussion with 8 participants each. The focus group discussion formed part of the design cycle, where a mock mHealth tool (based on the survey results) was presented to the groups to engage them about their attitudes, preferences, and perceptions towards the proposed solution. The rigour cycle involved combining the survey and focus group discussion data with knowledge from literature, for the conceptual design of the mHealth tool. Results A total of 43 learners completed the survey, and all participants indicated that they were vaccinated for HPV at school; however, none of them were able to answer the HPV knowledge questions. There was a high level of access to mobile technologies, as all the participants reported that they had access to cell phones and laptops (own or borrowed). The learners showed a strong preference for learning about sexual health and HPV from schoolteachers and tutors, with 25 out the 41 participants selecting this option, and 52% preferring an interactive learning style. During the focus group discussions, emphasis was placed on the mHealth application having entertainment features, while still being informative. Conclusions There was sufficient access to mobile technologies and WIFI access, which made an mHealth solution feasible. The fact that the participants had all been vaccinated, but they still didn't know what HPV was, showed that an mHealth tool could be useful. The learners prefer to learn interactively, and from their teachers and tutors, which is an element that can be introduced to the mHealth platform through a chatting function and educational video.
Open Access
Developing a mHealth-based portable ultrasound platform for breast cancer screening
(2021) Musasizi, Racheal; Fortuin, Jill; Douglas, Tania
Background Breast cancer is amongst the 10 most common cancers globally. The disease burden is increasing rapidly in Sub-Saharan African countries, where women living in rural and or remote areas are particularly prone to be diagnosed with late-stage breast cancer. This is due to the limited availability of advanced screening and diagnostic options. Ultrasound is a feasible screening tool for breast cancer, due to its portability, affordability and accuracy. The integration of mHealth with portable ultrasound enables the provision of screening services in rural and remote areas, through electronic consultation by a non-specialist with a specialist for interpretation and reporting of the ultrasound results. This project developed an application for a mHealth-based portable ultrasound platform that could be used by a non-specialist to provide breast cancer screening services with remote specialist support. Methods A systematic review of the literature was conducted for the period of 2004 to 2019 to gather evidence on the use of mHealth-based portable ultrasound platforms for improved access to ultrasound services like breast cancer screening. The evidence from the literature was used to design and develop a prototype of an application for a mHealth-based portable ultrasound platform suitable for breast cancer screening. The prototype application was integrated with a mobile-based portable ultrasound from Philips Lumify. Images generated by scanning a phantom breast using the portable ultrasound were uploaded onto the application and downloaded from the application to demonstrate the concept. Results The systematic review showed only two clinical conditions (obstetrics and cardiovascular disease) which used a mHealth-based portable ultrasound platform. The outcomes from the studies showed improved access to the respective ultrasound services in terms of patient management, early detection, improved quality of care and increased patient attendance, which resulted in access to other services. The integration of the prototype application with a mobile-based portable ultrasound resulted into a mHealthbased portable ultrasound platform prototype intended for breast cancer screening. The ability to upload images onto the platform and download images from the platform satisfied the design requirements for the platform. Conclusion A mHealth-based portable ultrasound prototype was developed, which has potential for improving access to breast cancer screening services. Further research including testing of the application with health professionals and patients is recommended to strengthen the feasibility of the concept.
Open Access
Development of a statistical shape and appearance model of the skull from a South African population
(2018) Lugadilu, Brian; Mutsvangwa, Tinashe; Douglas, Tania
Statistical shape models (SSMs) and statistical appearance models (SAMs) have been applied in medical analysis such as in surgical planning, finite element analysis, model-based segmentation, and in the fields of anthropometry and forensics. Similar applications can make use of SSMs and SAMs of the skull. A combination of the SSM and SAM of the skull can also be used in model-based segmentation. This document presents the development of a SSM and a SAM of the human skull from a South African population, using the Scalismo software package. The SSM development pipeline was composed of three steps: 1) Image data segmentation and processing; 2) Development of a free-form deformation (FFD) model for establishing correspondence across the training dataset; and 3) Development and validation of a SSM from the corresponding dataset. The SSM was validated using the leave one-out cross-validation method. The first eight principal components of the SSM represented 92.13% of the variation in the model. The generality of the model in terms of the Hausdorff distance between a new shape generated by the SSM and instances of the SSM had a steady state value of 1.48mm. The specificity of the model (in terms of Hausdorff distance) had a steady state value of 2.04mm. The SAM development pipeline involved four steps: 1) Volumetric mesh generation of the reference mesh to be used in establishing volumetric correspondence; 2) Sampling of intensity values from original computed tomography (CT) images using the in-correspondence volumetric meshes; and 3) Development of a SAM from the in-correspondence intensity values. A complete validation of the SAM was not possible due to limitations of the Scalismo software. As a result, only the shapes of the incomplete skulls were reconstructed and thereby validated. The amount of missing detail, as represented by absent landmarks, affected the registration results. Complete validation of the SAM is recommended as future work, via the use of a combined shape and intensity model (SSIM).
Open Access
Does the DHET research output subsidy model penalise high-citation publication? A case study
(2016) Harley, Yolande X; Huysamen, Esmari; Hlungwani, Carlette; Douglas, Tania
Abstract South African universities are awarded annual subsidy from the Department of Higher Education and Training (DHET) based on their research publication output. Journal article subsidy is based on the number of research publications in DHET-approved journals as well as the proportional contribution of authors from the university. Co-authorship with other institutions reduces the subsidy received by a university, which may be a disincentive to collaboration. Inter-institutional collaboration may affect the scientific impact of resulting publications, as indicated by the number of citations received. We analysed 812 journal articles published in 2011 by authors from the University of Cape Town’s Faculty of Health Sciences to determine if there was a significant relationship between subsidy units received and (1) citation count and (2) field-weighted citation impact. We found that subsidy units had a significant inverse relationship with both citation count (r= -0.247; CI = -0.311 – -0.182; p less than 0.0001) and field-weighted citation impact (r= -0.192; CI= -0.258 – -0.125; p less than 0.0001). These findings suggest that the annual subsidy awarded to universities for research output may inadvertently penalise high-citation publication. Revision of the funding model to address this possibility would better align DHET funding allocation with the strategic plans of the South African Department of Science and Technology, the National Research Foundation and the South African Medical Research Council, and may better support publication of greater impact research.
Open Access
Geometric morphometrics for 3D dense surface correspondence: population comparisons of shoulder bone morphology
(2018) Fouefack, Jean-Rassaire; Mutsvangwa, Tinashe; Douglas, Tania; Inyang, Adijat Omowumi
Background: Comparisons in morphological shape/form across population groups could provide population differences that might assist in making decisions on diagnosis and prognosis by the clinician. Geometric morphometrics (GM) is one of the fields that help to provide such population comparisons. In medical imaging and related disciplines, GM is commonly done using annotated landmarks or distances measured from 3D surfaces (consisting of triangular meshes). However, these landmarks may not be sufficient to describe the complete shape. This project aimed to develop GM for analysis that consider all vertices in the triangular mesh as landmarks. The developed methods were applied to South African and Swiss shoulder bones (scapula and humerus) to analyse morphological differences. Methods: The developed pipeline required first establishing correspondence across the datasets through a registration process. Gaussian process fitting was chosen to perform the registration since it is considered state-of-the-art. Secondly, a novel method for automatic identification of vertices or areas encoding the most shape/form variation was developed. Thirdly, a principal component analysis (PCA) that addressed the high dimensionality and lower sample size (HDLSS) phenomenon was adopted and applied to the dense correspondence data. This approach allowed for the stabilisation of the distribution of the data in low-dimensional form/shape space. Lastly, appropriate statistical tests were developed for population comparisons of the shoulder bones when dealing with HDLSS data in both form and shape space. Results: When the mesh-based GM analysis approach was applied to the training datasets (South African and Swiss shoulder bones), it was found that the anterior glenoid which is often the site of the shoulder dislocation is the most varied area of the glenoid. This has implications for diagnosis and provides knowledge for prosthesis design. The distribution of the data in the modified PCA space was shown to converge to a stable distribution when more vertices/landmarks are used for the analysis. South African and Swiss datasets were shown to be more distinguishable in a low-dimensional space when considering form rather than shape. It was found that left and right South African scapula bones are significantly different in terms of shape. Discussion: In general, it was observed that the two populations means can be significantly different in shape but not in form. An improved understanding of these observed shape and form differences has utility for shoulder arthroplasty prosthesis design and may also be useful for orthopaedic surgeons during surgical preoperative planning.
Open Access
Hand X-ray absorptiometry for measurement of bone mineral density on a slot-scanning X-ray imaging system
(2014) Dendere, Ronald; Douglas, Tania; Whiley, S
Bone mineral density (BMD) is an indicator of bone strength. While femoral and spinal BMDs are traditionally used in the management of osteoporosis, BMD at peripheral sites such as the hand has been shown to be useful in evaluating fracture risk for axial sites. These peripheral locations have been suggested as alternatives to the traditional sites for BMD measurement. Dual-energy X-ray absorptiometry (DXA) is the gold standard for measuring BMD due to low radiation dose, high accuracy and proven ability to evaluate fracture risk. Computed digital absorptiometry (CDA) has also been shown to be very effective at measuring the bone mass in hand bones using an aluminium step wedge as a calibration reference. In this project, the aim was to develop algorithm s for accurate measurement of BMD in hand bones on a slot - scanning digital radiography system. The project assess e d the feasibility of measuring bone mineral mass in hand bones using CDA on the current system. Images for CDA - based measurement were acquired using the default settings on the system for a medium sized patient. A method for automatic processing of the hand images to detect the aluminium step wedge, included in the scan for calibration, was developed and the calibration accuracy of the step wedge was evaluated. The CDA method was used for computation of bone mass with units of equivalent aluminium thickness (mmA1). The precision of the method was determined by taking three measurements in each of 1 6 volunteering subjects and computing the root - mean - square coefficient of variation (CV) of the measurements. The utility of the method was assessed by taking measurements of excised bones and assessing the correlation between the measured bone mass and ash weight obtained by incinerating the bones. The project also assessed the feasibility of implementing a DXA technique using two detectors in a slot-scanning digital radiography system to acquire dual-energy X-ray images for measuring areal and volumetric BMD of the middle phalanx of the middle finger. The dual-energy images were captured in two consecutive scans. The first scan captured the low- energy image using the detector in its normal set-up. The second scan captured the high- energy image with the detector modified to include an additional scintillator to simulate the presence of a second detector that would capture the low-energy image in a two-detector system. Scan parameters for acquisition of the dual-energy images were chosen to optimise spectral separation, entrance dose and image quality. Simulations were carried out to evaluate the spectral separation of the low- and high-energy spectra.
Open Access
Image analysis for a mobile phone-based assessment of latent tuberculosis infection
(University of Cape Town, 2020) Maclean, Sarah; Mutsvangwa, Tinashe; Malila, Bessie; Douglas, Tania
The current, most widely used method to screen for latent tuberculosis infection is the Mantoux tuberculin skin test, where tuberculin is injected into a patient's arm and may result in a cutaneous induration forming at the site of injection. A diameter measurement of the resultant induration, recorded using a ruler and ball point pen, is currently used to indicate the presence of latent tuberculosis infection. Limitations associated with the tuberculin skin test procedure are the crudeness of the induration measurement method, the follow-up clinical visit required from patients to have their induration measured, and the need for trained clinicians who can perform the induration measurement. These limitations motivated research into a mobile phone-based screening system which can be used to obtain a more accurate measurement of the induration without the need for a second visit to the clinic by patients. The prototype screening tool consists of a user interface for capturing induration images and a backend processing system that produces a threedimensional reconstruction of the induration for measurement. Recommendations from previous studies on the prototype screening tool, which involved evaluation of the mobile application using mock induration images, included improving the accuracy of measuring the induration and evaluating the tool on real induration images. The aim of this study was to evaluate the existing backend system and explore an alternative assessment approach for assessing the induration. This was achieved through the following objectives: (1) applying the current backend system to real induration images, (2) examining the need for three-dimensional reconstruction for delineation of the induration for measurement and (3) exploring an alternative method for the assessment of induration images using deep learning. Results for the first objective showed the three-dimensional reconstruction to be unsuccessful on real images. This was due to the homogeneity between the indurations and the surrounding skin, rendering the algorithm ineffective in delineating the indurations to obtain the diameter measurement required for diagnosis. The second objective involved determining whether the image orientation or induration height affected the diagnostic measurement. It was found that real indurations are much flatter and more subtle compared to the mock indurations used in the previous studies. This motivated an alternative image assessment approach using deep learning. However, deep learning approaches require large databases of annotated images to prevent overfitting on training data. The last objective therefore involved the design and implementation of a generative adversarial network for generation of synthetic images from a limited number of real images, which allowed the generation of an unlimited number of realistic-looking synthetic images from 150 real induration images.
Open Access
Impact of the Functional Resonance Analysis Method (FRAM) in safety management at healthcare organisations
(2021) Wessels, Maatje; Fortuin, Jill; Douglas, Tania
Patient safety events are likely to be one of the ten leading causes of death and disability in the world (World Health Organization, 2020). To manage safety, healthcare organisations have traditionally focused on identifying failures, performing analysis of events, and developing strategies to reduce the failures. Several thought leaders have argued that the traditional method is not adequate to manage safety in a complex environment. Their argument is that safety management should not solely focus on what went wrong, it should also include efforts which enable things to go right more often. If healthcare organisations want to broaden their approach towards managing safety, suitable methods must be investigated. The Functional Resonance Analysis Method (FRAM) was developed by Hollnagel in 2004 and has been applied in high-risk industries such as railway, aviation, maritime and healthcare. FRAM investigates the interaction of the different functions within a complex, underspecified system, and improves the understanding of normal work and its variability (Hollnagel, 2012). This systematic review will assess the application of FRAM in healthcare settings to develop a rich understanding of the application of FRAM in healthcare as a complementary method to safety management. Firstly, understanding how FRAM was implemented within healthcare organisations and secondly understanding how healthcare organisations have perceived the value-add of FRAM in terms of safety management. The results are expected to provide healthcare organisations with guidance on applying the FRAM and demonstrate the value it potentially adds to safety management. In the studies reviewed, FRAM was applied in a wide variety of settings and in different contexts. Thematic value-added aspects were identified and discussed. Shortcomings and prerequisites for the application of FRAM was also highlighted. This dissertation wishes to motivate healthcare organisations to investigate and apply alternative methods such as FRAM to enhance their ability to manage safety in a complex environment.
Open Access
Network analysis of Diagnostic Medical Device Development for Infectious Diseases Prevalent in South Africa
(2018) Nyathi, Nonku; Douglas, Tania; De Jager, Kylie
Infectious diseases are a major health concern in South Africa and many other developing countries. The local development of medical devices for infectious diseases in such settings, utilizing the local knowledge base, has the potential to improve the accuracy of and access to diagnoses and to lead to the devices being more context-appropriate and affordable. The aim of this project was to examine the landscape of diagnostic medical device development targeting infectious diseases prevalent in South Africa for the period 2000-2016, particularly with regard to collaboration between institutions in different sectors and the contributions of different collaborators. Such knowledge would be beneficial to future technological and policy developments aimed at improving access to diagnostic services and treatment in the South African context. Collaboration across four sectors was considered: university, hospital, industry and science councils and facilities. A bibliometric analysis was performed, and publications documenting medical device development for diagnosis of infectious diseases were extracted. Co-authorship of the journal and conference articles was used as a proxy for collaboration across organisations. Affiliation data extracted from the publications were used to generate a collaboration network. Netdraw, a network visualisation tool, was used to visualize the network, and network metrics such as degree centrality, betweenness centrality and closeness centrality, as well as group density measures, were produced using UCINET software. The collaboration network and the network metrics were used to determine which organisations have collaborated and which collaborators have played the most active and influential roles in diagnostic device development. The university sector was found to make the largest contribution to the development of diagnostic medical devices in South Africa, and also played a key role in transmitting information throughout the network due to its high frequency of connections to other organisations. The most prevalent type of inter-sectoral collaboration was between universities and science councils and facilities, while universities were found to collaborate most amongst themselves with regard to intrasectoral collaboration. Foreign organisations played a prominent role in diagnostic device development between 2012 and 2016. Tuberculosis was the most prevalent infectious disease in diagnostic device development research, and computer-aided detection was a common feature of research on diagnostic device development.
Open Access
Reconstruction of three-dimensional facial geometric features related to fetal alcohol syndrome using adult surrogates
(2020) Atuhaire, Felix; Mutsvangwa, Tinashe; Douglas, Tania
Fetal alcohol syndrome (FAS) is a condition caused by prenatal alcohol exposure. The diagnosis of FAS is based on the presence of central nervous system impairments, evidence of growth abnormalities and abnormal facial features. Direct anthropometry has traditionally been used to obtain facial data to assess the FAS facial features. Research efforts have focused on indirect anthropometry such as 3D surface imaging systems to collect facial data for facial analysis. However, 3D surface imaging systems are costly. As an alternative, approaches for 3D reconstruction from a single 2D image of the face using a 3D morphable model (3DMM) were explored in this research study. The research project was accomplished in several steps. 3D facial data were obtained from the publicly available BU-3DFE database, developed by the State University of New York. The 3D face scans in the training set were landmarked by different observers. The reliability and precision in selecting 3D landmarks were evaluated. The intraclass correlation coefficients for intra- and inter-observer reliability were greater than 0.95. The average intra-observer error was 0.26 mm and the average inter-observer error was 0.89 mm. A rigid registration was performed on the 3D face scans in the training set. Following rigid registration, a dense point-to-point correspondence across a set of aligned face scans was computed using the Gaussian process model fitting approach. A 3DMM of the face was constructed from the fully registered 3D face scans. The constructed 3DMM of the face was evaluated based on generalization, specificity, and compactness. The quantitative evaluations show that the constructed 3DMM achieves reliable results. 3D face reconstructions from single 2D images were estimated based on the 3DMM. The MetropolisHastings algorithm was used to fit the 3DMM features to 2D image features to generate the 3D face reconstruction. Finally, the geometric accuracy of the reconstructed 3D faces was evaluated based on ground-truth 3D face scans. The average root mean square error for the surface-to-surface comparisons between the reconstructed faces and the ground-truth face scans was 2.99 mm. In conclusion, a framework to estimate 3D face reconstructions from single 2D facial images was developed and the reconstruction errors were evaluated. The geometric accuracy of the 3D face reconstructions was comparable to that found in the literature. However, future work should consider minimizing reconstruction errors to acceptable clinical standards in order for the framework to be useful for 3D-from-2D reconstruction in general, and also for developing FAS applications. Finally, future work should consider estimating a 3D face using multi-view 2D images to increase the information available for 3D-from-2D reconstruction.
Open Access
Security for networked smart healthcare systems: A systematic review
(2022) Ndarhwa, Nyamwezi Perfect; Malila, Bessie; Douglas, Tania
Background and Objectives Smart healthcare systems use technologies such as wearable devices, Internet of Medical Things and mobile internet technologies to dynamically access health information, connect patients to health professionals and health institutions, and to actively manage and respond intelligently to the medical ecosystem's needs. However, smart healthcare systems are affected by many challenges in their implementation and maintenance. Key among these are ensuring the security and privacy of patient health information. To address this challenge, several mitigation measures have been proposed and some have been implemented. Techniques that have been used include data encryption and biometric access. In addition, blockchain is an emerging security technology that is expected to address the security issues due to its distributed and decentralized architecture which is similar to that of smart healthcare systems. This study reviewed articles that identified security requirements and risks, proposed potential solutions, and explained the effectiveness of these solutions in addressing security problems in smart healthcare systems. Methods This review adhered to the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines and was framed using the Problem, Intervention, Comparator, and Outcome (PICO) approach to investigate and analyse the concepts of interest. However, the comparator is not applicable because this review focuses on the security measures available and in this case no comparable solutions were considered since the concept of smart healthcare systems is an emerging one and there are therefore, no existing security solutions that have been used before. The search strategy involved the identification of studies from several databases including the Cumulative Index of Nursing and Allied Health Literature (CINAL), Scopus, PubMed, Web of Science, Medline, Excerpta Medical database (EMBASE), Ebscohost and the Cochrane Library for articles that focused on the security for smart healthcare systems. The selection process involved removing duplicate studies, and excluding studies after reading the titles, abstracts, and full texts. Studies whose records could not be retrieved using a predefined selection criterion for inclusion and exclusion were excluded. The remaining articles were then screened for eligibility. A data extraction form was used to capture details of the screened studies after reading the full text. Of the searched databases, only three yielded results when the search strategy was applied, i.e., Scopus, Web of science and Medline, giving a total of 1742 articles. 436 duplicate studies were removed. Of the remaining articles, 801 were excluded after reading the title, after which 342 after were excluded after reading the abstract, leaving 163, of which 4 studies could not be retrieved. 159 articles were therefore screened for eligibility after reading the full text. Of these, 14 studies were included for detailed review using the formulated research questions and the PICO framework. Each of the 14 included articles presented a description of a smart healthcare system and identified the security requirements, risks and solutions to mitigate the risks. Each article also summarized the effectiveness of the proposed security solution. Results The key security requirements reported were data confidentiality, integrity and availability of data within the system, with authorisation and authentication used to support these key security requirements. The identified security risks include loss of data confidentiality due to eavesdropping in wireless communication mediums, authentication vulnerabilities in user devices and storage servers, data fabrication and message modification attacks during transmission as well as while the data is at rest in databases and other storage devices. The proposed mitigation measures included the use of biometric accessing devices; data encryption for protecting the confidentiality and integrity of data; blockchain technology to address confidentiality, integrity, and availability of data; network slicing techniques to provide isolation of patient health data in 5G mobile systems; and multi-factor authentication when accessing IoT devices, servers, and other components of the smart healthcare systems. The effectiveness of the proposed solutions was demonstrated through their ability to provide a high level of data security in smart healthcare systems. For example, proposed encryption algorithms demonstrated better energy efficiency, and improved operational speed; reduced computational overhead, better scalability, efficiency in data processing, and better ease of deployment. Conclusion This systematic review has shown that the use of blockchain technology, biometrics (fingerprints), data encryption techniques, multifactor authentication and network slicing in the case of 5G smart healthcare systems has the potential to alleviate possible security risks in smart healthcare systems. The benefits of these solutions include a high level of security and privacy for Electronic Health Records (EHRs) systems; improved speed of data transaction without the need for a decentralized third party, enabled by the use of blockchain. However, the proposed solutions do not address data protection in cases where an intruder has already accessed the system. This may be potential avenues for further research and inquiry.
Open Access
Three-Dimensional Body Volume Measurement From Two-Dimensional Images: Towards A Smartphone Application
(2020) Majola, Khwezi; Mutsvangwa, Tinashe; Douglas, Tania; Lambert, Vicki
Obesity poses a public health threat worldwide and is associated with a higher mortality, increased likelihood of diabetes, and an increased risk of cancer. When treating obesity, regular monitoring of metrics such as body mass index (BMI) and waist circumference has been found to result in improved health outcomes for patients. Three-dimensional (3D) scanners provide a useful tool to provide body measurements based on 3D images in obesity management. However, such scanners are often inaccessible due to cost. A smartphone image-based method able to produce 3D images may provide a more accessible measuring tool. As a step towards developing such a smartphone application, this project developed a method for 3D reconstruction of body images from two-dimensional (2D) images, using a full body 3D Gaussian process morphable model (GPMM). Separate GPMMs were trained to learn the shape of female and male human bodies. Gaussian process regression of the three-dimensional (3D) GPMM models onto two-dimensional (2D) images is performed. Corresponding landmarks on the 3D shapes and in the 2D images are employed in reconstruction. Measurements of body volume, waist circumference and height are then performed to extract information that is useful in obesity management. Different model configurations (shape model with arms; modified shape model with arms; shape model without arms; marginalised shape model without arms; shape model with different landmarks) were used to ascertain the most promising approach for the reconstruction. Each reconstructed body was tested for accuracy using the surface-tosurface distance per vertex, modified Hausdorff distance, and assessment of the measurements. Tests were performed using data from the same dataset used to build the model and generalised data from a different dataset. In all test cases, the best performing approach used shape models without arms when considering surface distances. However, the surface-to-surface distances errors were larger than those seen in literature. For body measurements, the best performing models varied with different models performing best for different measurements. For the measurements, the errors were larger than the allowable errors and larger than those found in literature. Landmark positions were evaluated separately and found to be imprecise. There are a few sources that contribute towards the reconstruction errors. Possible sources of error include an inability to interpret pose and landmark position errors. The major recommendations for future work are to use a model that incorporates both shape and pose and to use automatic landmarking methods. Regarding a pathway to a smartphone app, camera parameter information should be considered to improve processing of the images and smartphone orientation information should be considered to correct for distortions due to a tilted phone.
Open Access
Towards a framework for multi class statistical modelling of shape, intensity and kinematics in medical images
(2021) Fouefack, Jean-Rassaire; Mutsvangwa, Tinashe; Burdin, Valérie; Douglas, Tania; Borotikar, Bhushan
Statistical modelling has become a ubiquitous tool for analysing of morphological variation of bone structures in medical images. For radiological images, the shape, relative pose between the bone structures and the intensity distribution are key features often modelled separately. A wide range of research has reported methods that incorporate these features as priors for machine learning purposes. Statistical shape, appearance (intensity profile in images) and pose models are popular priors to explain variability across a sample population of rigid structures. However, a principled and robust way to combine shape, pose and intensity features has been elusive for four main reasons: 1) heterogeneity of the data (data with linear and non-linear natural variation across features); 2) sub-optimal representation of three-dimensional Euclidean motion; 3) artificial discretization of the models; and 4) lack of an efficient transfer learning process to project observations into the latent space. This work proposes a novel statistical modelling framework for multiple bone structures. The framework provides a latent space embedding shape, pose and intensity in a continuous domain allowing for new approaches to skeletal joint analysis from medical images. First, a robust registration method for multi-volumetric shapes is described. Both sampling and parametric based registration algorithms are proposed, which allow the establishment of dense correspondence across volumetric shapes (such as tetrahedral meshes) while preserving the spatial relationship between them. Next, the framework for developing statistical shape-kinematics models from in-correspondence multi-volumetric shapes embedding image intensity distribution, is presented. The framework incorporates principal geodesic analysis and a non-linear metric for modelling the spatial orientation of the structures. More importantly, as all the features are in a joint statistical space and in a continuous domain; this permits on-demand marginalisation to a region or feature of interest without training separate models. Thereafter, an automated prediction of the structures in images is facilitated by a model-fitting method leveraging the models as priors in a Markov chain Monte Carlo approach. The framework is validated using controlled experimental data and the results demonstrate superior performance in comparison with state-of-the-art methods. Finally, the application of the framework for analysing computed tomography images is presented. The analyses include estimation of shape, kinematic and intensity profiles of bone structures in the shoulder and hip joints. For both these datasets, the framework is demonstrated for segmentation, registration and reconstruction, including the recovery of patient-specific intensity profile. The presented framework realises a new paradigm in modelling multi-object shape structures, allowing for probabilistic modelling of not only shape, but also relative pose and intensity as well as the correlations that exist between them. Future work will aim to optimise the framework for clinical use in medical image analysis.
Open Access
Towards a framework for multi class statistical modelling of shape, intensity, and kinematics in medical images
(2021) Fouefack, Jean-Rassaire; Burdin, Valérie; Mutsvangwa, Tinashe; Borotikar, Bhushan; Douglas, Tania
Statistical modelling has become a ubiquitous tool for analysing of morphological variation of bone structures in medical images. For radiological images, the shape, relative pose between the bone structures and the intensity distribution are key features often modelled separately. A wide range of research has reported methods that incorporate these features as priors for machine learning purposes. Statistical shape, appearance (intensity profile in images) and pose models are popular priors to explain variability across a sample population of rigid structures. However, a principled and robust way to combine shape, pose and intensity features has been elusive for four main reasons: 1) heterogeneity of the data (data with linear and non-linear natural variation across features); 2) sub-optimal representation of three-dimensional Euclidean motion; 3) artificial discretization of the models; and 4) lack of an efficient transfer learning process to project observations into the latent space. This work proposes a novel statistical modelling framework for multiple bone structures. The framework provides a latent space embedding shape, pose and intensity in a continuous domain allowing for new approaches to skeletal joint analysis from medical images. First, a robust registration method for multi-volumetric shapes is described. Both sampling and parametric based registration algorithms are proposed, which allow the establishment of dense correspondence across volumetric shapes (such as tetrahedral meshes) while preserving the spatial relationship between them. Next, the framework for developing statistical shape-kinematics models from in-correspondence multi-volumetric shapes embedding image intensity distribution, is presented. The framework incorporates principal geodesic analysis and a non-linear metric for modelling the spatial orientation of the structures. More importantly, as all the features are in a joint statistical space and in a continuous domain; this permits on-demand marginalisation to a region or feature of interest without training separate models. Thereafter, an automated prediction of the structures in images is facilitated by a model-fitting method leveraging the models as priors in a Markov chain Monte Carlo approach. The framework is validated using controlled experimental data and the results demonstrate superior performance in comparison with state-of-the-art methods. Finally, the application of the framework for analysing computed tomography images is presented. The analyses include estimation of shape, kinematic and intensity profiles of bone structures in the shoulder and hip joints. For both these datasets, the framework is demonstrated for segmentation, registration and reconstruction, including the recovery of patient-specific intensity profile. The presented framework realises a new paradigm in modelling multi-object shape structures, allowing for probabilistic modelling of not only shape, but also relative pose and intensity as well as the correlations that exist between them. Future work will aim to optimise the framework for clinical use in medical image analysis.
Open Access
Ventilation in minibus taxis as a means of airborne infection control
(2018) Matose, Munyaradzi T; Poluta, Mladen; Douglas, Tania
Airborne infection control (AIC) measures are used extensively in healthcare settings to curtail the spread of airborne infectious diseases; these measures include administrative, architectural, engineering (e.g. ventilation) and personal protective interventions, serving either to reduce the concentration of airborne infectious particles or to protect individuals from direct exposure to airborne infection. Few such measures are applied in public congregate spaces outside of health facilities, such as those associated with public transport. Limited literature is available on existing AIC measures in the context of public transport modalities. This study explores the role of ventilation as an AIC measure in minibus taxis in Cape Town, South Africa, to determine its potential role in reducing airborne infectious disease transmission. The minibus taxi model chosen for the study was the Toyota Quantum Ses’fikile, which is commonly used in the Cape Town metropole. The Ses’fikile taxi has 6 windows, 2 at the front, 2 in line with the main passenger door and 2 towards the rear of the taxi. Ultrasonic anemometers were placed at key positions throughout the taxi-interior to measure and log airflow patterns, under different widow-open/close configurations and at different taxi speeds. To determine ventilation rates, the configurations were tested in an occupied taxi, with occupants comprising the driver, a researcher, and 14 volunteer participants. This study analysed TB transmission risk using the Issarow equation, a dose-response model. Airflows created by different window configurations produced patterns in airflow direction and velocity. A linear regression model fit to the ventilation data revealed that increasing taxi speed increased ventilation. Ventilation rates were found to depend on interior airflow as a result of the window configuration, as well as on the number of open windows, although the ventilation rate was not highest with the highest number of open windows. The best ventilation rates were found with four open windows, which included the front windows on both sides of the vehicle, and either the middle windows on both sides or the rear windows on both sides. The ventilation rates produced by these configurations at all tested taxi speeds (40 km/h, 80 km/h and 100 km/h) ranged from 108 to 316 L/s and exceeded the World Health Organization recommendation for new healthcare facilities, airborne precaution rooms, and general wards and outpatient departments. TB transmission probabilities in a taxi were dependent on ventilation, occupancy, number of infectors and duration of exposure. The risk of transmission was shown to increase substantially when ventilation rates fell below 50 L/s. In conclusion, minibus taxis were found to provide an effective range of ventilation rates that reduce the risk of TB transmission at varying speeds, however when natural ventilation is not used and with typical high occupancies, the risk posed to all occupants is high. Alternative AIC interventions may have to be considered.
Open Access
Visualisation and manipulation of 3D patient-specific bone geometry using augmented reality
(2020) Coertze, Johannes A; Mutsvangwa, Tinashe; Douglas, Tania; Bracio, Boris R
Computer-mediated reality technologies have the potential to improve the imageguided surgery (IGS) workflow; specifically, pre-surgical planning, intra-operative guidance, post-surgical assessment, and rehabilitation. Augmented reality (AR), a form of computer-mediated reality, uses an electronic display or projection module to add a hologram in the user's field of view (FOV). For intra-operative guidance, AR could aid in reducing the cognitive overload experienced by clinicians due to integrating multi-modal imaging data from several sources while performing the intervention on the patient. Three AR HMD systems have been developed to explore the capabilities of the Microsoft HoloLens as an AR HMD to be used in developing an AR HMD medical system. The three AR HMD systems required different software and hardware system architectures, however, each of the AR HMD system's software applications has been developed in Unity combined with the Mixed Reality Toolkit (MRTK). Each of the AR HMD systems implemented different registration techniques to localize the virtual object in the real-world coordinate system. The registration techniques were user calibration alignment to identified anatomical landmarks, fiducial marker tracking, and markerless tracking. For user calibration with anatomical landmarks, the MRTK was manipulated to allow alignment of the virtual object. For fiducial registration, the Vuforia Software Development Kit (SDK) was added to assess the alignment and spatial anchoring of the virtual object as specified. Finally, the Leap Motion Controller (LMC) and Leap's Orion SDK was used for exploring markerless tracking. The AR HMD systems developed enabled performance assessments, and alignment errors were identified during trials of the three systems. Most notably the location drift of the 3D virtual object in the spatial space due to the clinician moving around the registered location. This project entailed preliminary development towards the AR HMD medical system to create an in-vivo view of 3D patient-specific bone geometries as a hologram in the clinician's FOV.