Glioma Multimodal MRI Analysis System for Tumor Layered Diagnosis via Multi-task Semi-supervised Learning
Cancer Research Institute, Central South University（中南大学肿瘤研究所）；School of Physics & Electronic Science, Changsha University of Science & Technology（长沙理工大学物理与电子科学学院）；IFLYTEK Research（iFlytek研究院）；School of Life Sciences, Central South University（中南大学生命科学学院）；Department of Radiology, Xiangya Hospital, Central South University（中南大学湘雅医院放射科）；School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Department of Neurosurgery, Xiangya Hospital, Central South University（中南大学湘雅医院神经外科）
Gliomas are the most common primary tumors of the central nervous system. Multimodal MRI is widely used for the preliminary screening of gliomas and plays a crucial role in auxiliary diagnosis, therapeutic efficacy, and prognostic evaluation. Currently, the computer-aided diagnostic studies of gliomas using MRI have focused on independent analysis events such as tumor segmentation, grading, and radiogenomic classification, without studying inter-dependencies among these events. In this study, we propose a Glioma Multimodal MRI Analysis System (GMMAS) that utilizes a deep learning network for processing multiple events simultaneously, leveraging their inter-dependencies through an uncertainty-based multi-task learning architecture and synchronously outputting tumor region segmentation, glioma histological subtype, IDH mutation genotype, and 1p/19q chromosome disorder status. Compared with the reported single-task analysis models, GMMAS improves the precision across tumor layered diagnostic tasks. Additionally, we have employed a two-stage semi-supervised learning method, enhancing model performance by fully exploiting both labeled and unlabeled MRI samples. Further, by utilizing an adaptation module based on knowledge self-distillation and contrastive learning for cross-modal feature extraction, GMMAS exhibited robustness in situations of modality absence and revealed the differing significance of each MRI modal. Finally, based on the analysis outputs of the GMMAS, we created a visual and user-friendly platform for doctors and patients, introducing GMMAS-GPT to generate personalized prognosis evaluations and suggestions.
University of California San Francisco（加州大学旧金山分校）；University of Pennsylvania（宾夕法尼亚大学）
Here we present the University of California San Francisco Preoperative Diffuse Glioma MRI (UCSF-PDGM) dataset. The UCSF-PDGM dataset includes 500 subjects with histopathologically-proven diffuse gliomas who were imaged with a standardized 3 Tesla preoperative brain tumor MRI protocol featuring predominantly 3D imaging, as well as advanced diffusion and perfusion imaging techniques. The dataset also includes isocitrate dehydrogenase (IDH) mutation status for all cases and O6-methylguanine-DNA methyltransferase (MGMT) promotor methylation status for World Health Organization (WHO) grade III and…
Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Prediction
Oslo University Hospital（奥斯陆大学医院）；Universitat Politècnica de València（瓦伦西亚理工大学）；Instituto Universitario de Tecnologías de la Información y Comunicaciones（信息技术与通信大学学院）
Faculty of Physics and Mathematics, Benemérita Universidad Autónoma de Puebla（普埃布拉自治大学物理与数学学院）
Gliomas are brain tumors composed of different highly heterogeneous histological subregions. Image analysis techniques to identify relevant tumor substructures have high potential for improving patient diagnosis, treatment and prognosis. However, due to the high heterogeneity of gliomas, the segmentation task is currently a major challenge in the field of medical image analysis. In the present work, the database of the Brain Tumor Segmentation (BraTS) Challenge 2018, composed of multimodal MRI scans of gliomas, was studied. A segmentation methodology based on the design and application of conv…
Zhengzhou University（郑州大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Peng Cheng Laboratory（鹏城实验室）；Guangdong Provincial People’s Hospital（广东省人民医院）；Guangdong Academy of Medical Sciences（广东省医学科学院）
Multi-contrast magnetic resonance imaging (MRI)-based automatic auxiliary glioma diagnosis plays an important role in the clinic. Contrast-enhanced MRI sequences (e.g., contrast-enhanced T1-weighted imaging) were utilized in most of the existing relevant studies, in which remarkable diagnosis results have been reported. Nevertheless, acquiring contrast-enhanced MRI data is sometimes not feasible due to the patients physiological limitations. Furthermore, it is more time-consuming and costly to collect contrast-enhanced MRI data in the clinic. In this paper, we propose an adaptive PromptNet to …
Department of Computer Science, University of Rochester（罗切斯特大学计算机科学系）；Department of Electrical Engineering, University of Rochester（罗切斯特大学电气工程系）；Department of Biomedical Engineering, University of Rochester（罗切斯特大学生物医学工程系）；Department of Imaging Sciences, University of Rochester（罗切斯特大学影像科学系）；Faculty of Medicine and Institute of Clinical Radiology, Ludwig Maximilian University（路德维希-马克西米利安大学医学院及临床放射学研究所）
Glioma is one of the most common and aggressive types of primary brain tumors. The accurate segmentation of subcortical brain structures is crucial to the study of gliomas in that it helps the monitoring of the progression of gliomas and aids the evaluation of treatment outcomes. However, the large amount of required human labor makes it difficult to obtain the manually segmented Magnetic Resonance Imaging (MRI) data, limiting the use of precise quantitative measurements in the clinical practice. In this work, we try to address this problem by developing a 3D Convolutional Neural Network~(3D C…
Structural magnetic resonance imaging (MRI) has been widely utilized for analysis and diagnosis of brain diseases. Automatic segmentation of brain tumors is a challenging task for computer-aided diagnosis due to low-tissue contrast in the tumor subregions. To overcome this, we devise a novel pixel-wise segmentation framework through a convolutional 3D to 2D MR patch conversion model to predict class labels of the central pixel in the input sliding patches. Precisely, we first extract 3D patches from each modality to calibrate slices through the squeeze and excitation (SE) block. Then, the outp…
Adult Glioma Segmentation in Sub-Saharan Africa using Transfer Learning on Stratified Finetuning Data
Sheikh Zayed Institute for Pediatric Surgical Innovation（谢赫·扎耶德儿科外科创新研究所）；Children’s National Hospital（儿童国家医院）；Biomedical Image Technologies（生物医学影像技术中心）；Universidad Politécnica de Madrid（马德里理工大学）；CIBER-BBN（西班牙生物医学网络研究中心）；ISCIII（卡洛斯三世卫生研究所）；School of Medicine and Health Sciences, George Washington University（乔治·华盛顿大学医学与健康科学学院）
Washington University in St. Louis（圣路易斯华盛顿大学）；Mallinckrodt Institute of Radiology（马林克罗特放射研究所）；Washington University School of Medicine（华盛顿大学医学院）；Institute for Informatics（信息学研究所）
Isocitrate dehydrogenase (IDH) mutation and 1p/19q codeletion status are important prognostic markers for glioma. Currently, they are determined using invasive procedures. Our goal was to develop artificial intelligence-based methods to non-invasively determine these molecular alterations from MRI. For this purpose, pre-operative MRI scans of 2648 patients with gliomas (grade II-IV) were collected from Washington University School of Medicine (WUSM; n = 835) and publicly available datasets viz. Brain Tumor Segmentation (BraTS; n = 378), LGG 1p/19q (n = 159), Ivy Glioblastoma Atlas Project (Ivy…
Training Beyond Convergence: Grokking nnU-Net for Glioma Segmentation in Sub-Saharan MRI
Multimedia University（多媒体大学）；University of British Columbia（不列颠哥伦比亚大学）；McGill University（麦吉尔大学）；Montreal Neurological Institute（蒙特利尔神经学研究所）；Federal University of Technology Minna（明纳联邦理工大学）；Medical Artificial Intelligence Laboratory（医学人工智能实验室）；Friedrich-Alexander-Universität（弗里德里希-亚历山大大学）
Duke Kunshan University（昆山杜克大学）；Duke University（杜克大学）
We developed a deep ensemble learning model with a radiomics spatial encoding execution for improved glioma segmentation accuracy using multi-parametric MRI (mp-MRI). This model was developed using 369 glioma patients with a 4-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. In each modality volume, a 3D sliding kernel was implemented across the brain to capture image heterogeneity: fifty-six radiomic features were extracted within the kernel, resulting in a 4th order tensor. Each radiomic feature can then be encoded as a 3D image volume, namely a radiomic feature map…
Reutlingen University（罗伊特林根大学）；Menoufia University（梅努菲亚大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Reliable and accurate registration of patient-specific brain magnetic resonance imaging (MRI) scans containing pathologies is challenging due to tissue appearance changes. This paper describes our contribution to the Registration of the longitudinal brain MRI task of the Brain Tumor Sequence Registration Challenge 2022 (BraTS-Reg 2022). We developed an enhanced unsupervised learning-based method that extends the iRegNet. In particular, incorporating an unsupervised learning-based paradigm as well as several minor modifications to the network pipeline, allows the enhanced iRegNet method to achi…
Targeted Neural Architectures in Multi-Objective Frameworks for Complete Glioma Characterization from Multimodal MRI
School of Computer Science and Engineering, Vellore Institute of Technology（韦洛尔理工学院计算机科学与工程学院）；College of Engineering, Guindy, Anna University（安娜大学金迪工程学院）；Institute of Neurosurgery, Madras Medical College（马德拉斯医学院神经外科研究所）
Vingroup Big Data Institute (VinBigdata)（越南 VinBigdata 大数据研究院）；Hanoi University of Science and Technology (HUST)（河内科技大学）；University of Engineering and Technology (UET), VNU（越南国立大学工程技术大学）
Brain tumor segmentation plays an essential role in medical image analysis. In recent studies, deep convolution neural networks (DCNNs) are extremely powerful to tackle tumor segmentation tasks. We propose in this paper a novel training method that enhances the segmentation results by adding an additional classification branch to the network. The whole network was trained end-to-end on the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2020 training dataset. On the BraTS's validation set, it achieved an average Dice score of 78.43%, 89.99%, and 84.22% respectively for the enhancing tumo…
Enhancement Without Contrast: Stability-Aware Multicenter Machine Learning for Glioma MRI Imaging
Tehran University of Medical Science（德黑兰医科大学）；Guilan University of Medical Sciences（吉兰医科大学）；University of Tehran（德黑兰大学）；Motamed Cancer Institute, ACECR（莫塔梅德癌症研究所，学术中心教育文化研究委员会）；University of British Columbia（不列颠哥伦比亚大学）；Technological Virtual Collaboration Company (TECVICO CORP.)（技术虚拟协作公司）；BC Cancer Research Institute（不列颠哥伦比亚省癌症研究所）
Massachusetts General Hospital（麻省总医院）；Harvard University（哈佛大学）；General Electric Healthcare（通用电气医疗集团）；Indian Institute of Science（印度科学学院）
Gliomas are one of the most frequent brain tumors and are classified into high grade and low grade gliomas. The segmentation of various regions such as tumor core, enhancing tumor etc. plays an important role in determining severity and prognosis. Here, we have developed a multi-threshold model based on attention U-Net for identification of various regions of the tumor in magnetic resonance imaging (MRI). We propose a multi-path segmentation and built three separate models for the different regions of interest. The proposed model achieved mean Dice Coefficient of 0.59, 0.72, and 0.61 for enhan…
Revolutionizing Glioma Segmentation & Grading Using 3D MRI - Guided Hybrid Deep Learning Models
Department of Computer Science and Engineering, School of Computer Science and Engineering（计算机科学与工程系，计算机科学与工程学院）；Vellore Institute of Technology, Chennai, India（维洛雷技术学院，钦奈，印度）；School of Advanced Science, Vellore Institute of Technology, Chennai, India（先进科学学院，维洛雷技术学院，钦奈，印度）；Centre for Human Movement Analytics, Vellore Institute of Technology, Chennai, India（人类运动分析中心，维洛雷技术学院，钦奈，印度）
The most common primary brain tumors are gliomas, evolving from the cerebral supportive cells. For clinical follow-up, the evaluation of the preoperative tumor volume is essential. Volumetric assessment of tumor volume with manual segmentation of its outlines is a time-consuming process that can be overcome with the help of computerized segmentation methods. In this contribution, two methods for World Health Organization (WHO) grade IV glioma segmentation in the human brain are compared using magnetic resonance imaging (MRI) patient data from the clinical routine. One method uses balloon infla…
Indian Statistical Institute（印度统计研究所）；DAV Institute of Engineering and Technology（DAV工程技术学院）
Inspired by the success of Convolutional Neural Networks (CNN), we develop a novel Computer Aided Detection (CADe) system using CNN for Glioblastoma Multiforme (GBM) detection and segmentation from multi channel MRI data. A two-stage approach first identifies the presence of GBM. This is followed by a GBM localization in each "abnormal" MR slice. As part of the CADe system, two CNN architectures viz. Classification CNN (C-CNN) and Detection CNN (D-CNN) are employed. The CADe system considers MRI data consisting of four sequences ($T_1$, $T_{1c},$ $T_2$, and $T_{2FLAIR}$) as input, and automati…
University College Dublin（都柏林大学学院）；Université Paris-Est Créteil Val de Marne - Université Paris 12（巴黎东-马恩拉瓦莱大学（巴黎第十二大学））；ADAPT SFI Research Centre（ADAPT SFI研究中心）
Magnetic Resonance Imaging (MRI) is the most commonly used non-intrusive technique for medical image acquisition. Brain tumor segmentation is the process of algorithmically identifying tumors in brain MRI scans. While many approaches have been proposed in the literature for brain tumor segmentation, this paper proposes a lightweight implementation of U-Net. Apart from providing real-time segmentation of MRI scans, the proposed architecture does not need large amount of data to train the proposed lightweight U-Net. Moreover, no additional data augmentation step is required. The lightweight U-Ne…
Quantifying U-Net Uncertainty in Multi-Parametric MRI-based Glioma Segmentation by Spherical Image Projection
Duke University（杜克大学）；Duke Kunshan University（昆山杜克大学）；The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）；The University of Texas MD Anderson Graduate School of Biomedical Science（德克萨斯大学MD安德森生物医学研究生院）
University of Calcutta（加尔各答大学）；West Bengal University of Technology（西孟加拉技术大学）
Tumor segmentation from magnetic resonance imaging (MRI) data is an important but time consuming manual task performed by medical experts. Automating this process is a challenging task because of the high diversity in the appearance of tumor tissues among different patients and in many cases similarity with the normal tissues. MRI is an advanced medical imaging technique providing rich information about the human soft-tissue anatomy. There are different brain tumor detection and segmentation methods to detect and segment a brain tumor from MRI images. These detection and segmentation approache…
Tumor Location-weighted MRI-Report Contrastive Learning: A Framework for Improving the Explainability of Pediatric Brain Tumor Diagnosis
The Hospital for Sick Children（病童医院）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）；University Hospital Augsburg（奥格斯堡大学医院）
The brain tumor segmentation on MRI images is a very difficult and important task which is used in surgical and medical planning and assessments. If experts do the segmentation manually with their own medical knowledge, it will be time-consuming. Therefore, researchers propose methods and systems which can do the segmentation automatically and without any interference. In this article, an unsupervised automatic method for brain tumor segmentation on MRI images is presented. In this method, at first in the pre-processing level, the extra parts which are outside the skull and don't have any help…
The Brain Tumor Segmentation (BraTS) Challenge 2023: Glioma Segmentation in Sub-Saharan Africa Patient Population (BraTS-Africa)
Medical Artificial Intelligence Laboratory (MAI Lab)（医学人工智能实验室（MAI实验室））；Department of Radiation Biology, Radiotherapy and Radiodiagnosis, University of Lagos（拉各斯大学放射生物学、放射治疗与放射诊断系）；Department of Radiology, University of California, San Diego（加州大学圣地亚哥分校放射科）；Crestview Radiology Limited（Crestview放射科有限公司）；Lagos University Teaching Hospital（拉各斯大学教学医院）；Lagos State University Teaching Hospital, Ikeja, Lagos, Nigeria（拉各斯州大学教学医院，伊凯贾，拉各斯，尼日利亚）；NSIA-Kano Diagnostic Center, Kano Nigeria（NSIA-卡诺诊断中心，卡诺，尼日利亚）；Nnamdi Azikiwe University Teaching Hospital, Nnewi, Anambra State, Nigeria（恩内迪·阿齐基韦大学教学医院，恩韦伊，安纳博拉州，尼日利亚）；Federal Medical Centre, Abeokuta, Ogun State, Nigeria（阿博库塔联邦医疗中心，奥贡州，尼日利亚）；Federal Medical Centre, Umahia, Abia State, Nigeria（乌马希亚联邦医疗中心，阿比亚州，尼日利亚）；National Hospital Abuja, FCT, Nigeria（阿布贾国家医院，联邦首都区，尼日利亚）；Benue State University Teaching Hospital, Markurdi, Benue State, Nigeria（贝努埃州大学教学医院，马库尔迪，贝努埃州，尼日利亚）；Duke University Medical Center, Department of Radiology, USA（达特茅斯大学医学中心，放射科，美国）；University of California San Francisco, CA, USA（加州大学旧金山分校，CA，美国）；Yale University, New Haven, CT, USA（耶鲁大学，新 Haven，CT，美国）；Children's National Hospital, Washington DC, USA（儿童医院华盛顿特区，华盛顿特区，美国）；George Washington University, Washington DC, USA（乔治·华盛顿大学，华盛顿特区，美国）；Sage Bionetworks, USA（Sage生物网络，美国）；Department of Neuroradiology, Technical University of Munich, Munich, Germany（慕尼黑技术大学神经放射科系，慕尼黑，德国）；Helmholtz Research Center, Munich, Germany（海德堡研究中心，慕尼黑，德国）；Duke University Medical Center, Department of Radiation Oncology, USA（达特茅斯大学医学中心，放射肿瘤科，美国）；Children’s Hospital of Philadelphia, University of Pennsylvania, Philadelphia, PA, USA（费城儿童医院，宾夕法尼亚大学，费城，PA，美国）；Center for AI and Data Science for Integrated Diagnostics (AI2D) & Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, USA（人工智能与数据科学整合诊断中心（AI2D）及生物医学影像计算与分析中心（CBICA），宾夕法尼亚大学，费城，PA，美国）；Athinoula A Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, USA（Athinoula A Martinos生物医学影像中心，马萨诸塞总医院，波士顿，MA，美国）；University of Zurich, Switzerland（苏黎世大学，瑞士）；Cancer Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, MD 20814, USA（癌症成像计划，国家癌症研究所，国家卫生研究院，贝塞斯达，MD 20814，美国）；Center for Clinical Epidemiology and Biostatistics, University of Pennsylvania, Philadelphia, USA（临床流行病学与生物统计学中心，宾夕法尼亚大学，费城，美国）；Department of Applied Mathematics and Computer Science, Technical University of Denmark, Denmark（应用数学与计算机科学系，丹麦技术大学，丹麦）；Mayo Clinic, MN, USA（梅奥诊所，MN，美国）；Precision FDA, U.S. Food and Drug Administration, Silver Spring, MD, USA（Precision FDA，美国食品药品监督管理局，Silver Spring，MD，美国）；Booz Allen Hamilton, McLean, VA, USA（Booz Allen Hamilton，麦肯，VA，美国）；Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA（放射科，佩尔曼医学院，宾夕法尼亚大学，费城，PA，美国）；Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA（病理学与实验室医学系，佩尔曼医学院，宾夕法尼亚大学，费城，PA，美国）；Center for Global Health, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA（全球健康中心，佩尔曼医学院，宾夕法尼亚大学，费城，宾夕法尼亚，美国）；Montreal Neurological Institute, McGill University, Montreal, Canada（蒙特利尔神经科学研究所，麦吉尔大学，蒙特利尔，加拿大）；Department of Medicine, University of Cape Town, South Africa（医学系，开普敦大学，南非）；Department of Radiation Medicine, University of Cape Town, South Africa（放射医学系，开普敦大学，南非）
Beijing-Dublin International College（北京-都柏林国际学院）；University College Dublin（都柏林大学）
This technical report presents a comparative analysis of existing deep learning (DL) based approaches for brain tumor segmentation with missing MRI modalities. Approaches evaluated include the Adversarial Co-training Network (ACN) and a combination of mmGAN and DeepMedic. A more stable and easy-to-use version of mmGAN is also open-sourced at a GitHub repository. Using the BraTS2018 dataset, this work demonstrates that the state-of-the-art ACN performs better especially when T1c is missing. While a simple combination of mmGAN and DeepMedic also shows strong potentials when only one MRI modality…
Automatic MRI brain tumor segmentation is of vital importance for the disease diagnosis, monitoring, and treatment planning. In this paper, we propose a two-stage encoder-decoder based model for brain tumor subregional segmentation. Variational autoencoder regularization is utilized in both stages to prevent the overfitting issue. The second-stage network adopts attention gates and is trained additionally using an expanded dataset formed by the first-stage outputs. On the BraTS 2020 validation dataset, the proposed method achieves the mean Dice score of 0.9041, 0.8350, and 0.7958, and Hausdorf…
School of Computer Science, University of Lincoln（林肯大学计算机科学学院）；National Heart & Lung Institute, Imperial College London（帝国理工学院国家心肺研究所）
In this paper, we propose a novel learning based method for automated segmentation of brain tumor in multimodal MRI images, which incorporates two sets of machine -learned and hand crafted features. Fully convolutional networks (FCN) forms the machine learned features and texton based features are considered as hand-crafted features. Random forest (RF) is used to classify the MRI image voxels into normal brain tissues and different parts of tumors, i.e. edema, necrosis and enhancing tumor. The method was evaluated on BRATS 2017 challenge dataset. The results show that the proposed method provi…
Medical Resonance Imaging or MRI is a medical image processing technique that used radio waves to scan the body. It is a tomographic imaging technique, principally used in the field of radiology. With the advantage of being a painless diagnostic procedure, MRI allows medical personnel to illustrate clear pictures of the anatomy and the physiological processes occurring in the body, thus allowing early detection and treatment of diseases. These images, combined with image processing techniques may be used in the detection of tumors, difficult to identify with the naked eye. This digital assignm…
A Comparison and Evaluation of Fine-tuned Convolutional Neural Networks to Large Language Models for Image Classification and Segmentation of Brain Tumors on MRI
In this paper, we propose a novel learning based method for automated segmenta-tion of brain tumor in multimodal MRI images. The machine learned features from fully convolutional neural network (FCN) and hand-designed texton fea-tures are used to classify the MRI image voxels. The score map with pixel-wise predictions is used as a feature map which is learned from multimodal MRI train-ing dataset using the FCN. The learned features are then applied to random for-ests to classify each MRI image voxel into normal brain tissues and different parts of tumor. The method was evaluated on BRATS 2013 …
Resource-Efficient Glioma Segmentation on Sub-Saharan MRI
BAC School of Computing；Information Systems, Botswana Faculty of Medicine of Sfax, University of Sfax, Sfax, Tunisia Laboratory of Biophysics；Medical Technologies, Higher Institute of Medical Technologies of Tunis, University ElManar, Tunis, Tunisia London School of Hygiene；Tropical Medicine, London, UK Lawson Health Research Institute, London, Ontario, Canada Department of Radiology, Bayero University, Kano-Nigeria Department of Radiology, Aminu Kano Teaching Hospital, Kano-Nigeria Department of Anatomy, Federal University Lokoja college of health sciences, Kogi State, Nigeria Department of Computer Science；Information, College of Science, Majmaah University, AL-Majmaah, 11952, Saudi Arabia CES Laboratory, National School of Engineers of Sfax, Sfax, Tunisia Department of Computer Science；IT, Mulungushi University, Zambia Multimodal Imaging of Neurodegenerative Diseases (MiND) Lab, Department of Neurology；Neurosurgery, McGill University, Montreal, QC, Canada Department of Electrical；Computer Engineering, University of British Columbia, Vancouver, Canada Medical Artificial Intelligence Laboratory (MAI Lab), Lagos, Nigeria Montreal Neurological Institute, McGill University, Montréal, Canada Department of Medicine, University of Cape Town, South Africa Department of Clinical \& Radiation Oncology, University of Cape Town, South Africa
