Supplementary Grant for DATICAN - Summary The Data Science and Medical Image Analysis Training for Improved Health Care Delivery in Nigeria (DATICAN) project is a UE5 DS-I Africa project funded by NIH. The main aim of DATICAN is to build capacity in Data Science and medical image analysis. DATICAN’s overarching objective is to produce a new generation of data scientists possessing the requisite data science skills in medical image analysis and the potential to become the clinical research leaders needed to improve healthcare delivery in sub-Saharan Africa (SSA). DATICAN is a collaborative effort amongst 4 universities, 3 in Nigeria and 1 in the USA, these are Lagos State University, The University of Ibadan, Redeemer’s University and The University of Chicago. The project is funded for 3 years from September 2023 to September 2026. Project implementation started immediately after receiving the award letter in September 2023 and we have met our target for year 1 recruitment. We have recruited 36 participants, comprising PhD and MSc students, postdocs, and Faculty members. We are currently training and as contained in our year 1 plan, the USA trainers have visited Nigeria and the Nigerian trainers have visited the USA this year. DATICAN was structured to be skills acqusition-driven, hands-on and project-driven. To achieve these, each trainee was given a project work related to improved healthcare delivery in SSA using data science and AI knowledge. This implies that we have 36 use cases already. There are 3 major requirements for implementing these use cases, these are the relevant skills set, local data peculiar to the SSA and computational resources. We have started training the students and the progress recorded so far shows that DATICAN has the potential to give the students the relevant skills required to execute their use cases. On local data, we have collected medical images of 2000 individuals with different modalities (e.g. ultrasound, MRI, CT, etc) and different body parts (brain, liver, abdomen, etc) and stored them on our hard drives, and there are many more to collect. The unfortunate thing is that these images are unstructured, un-curated and some of them are even unlabelled. This implies that the data are not in a useful form. On computational resources, imaging data are huge and processing them requires access to compute infrastructure such as High-Performance Computing (HPC) with Graphic Processing Units (GPUs). UChicago has given our trainees access to its HPC, the downside of this is the lack of sustainability and scalability. DATICAN has a lifespan of 3 years and lack of access to computational resources afterwards will make the acquired skills useless. The aims of this supplementary project are (1) to extend DATICAN to include data curation and proper data management, this is to make data sharing amongst the three institutions possible. (2) to procure an HPC with a GPU that will meet the computational needs of our trainees. We strongly believe that both the computational resources and repository will be useful not only for the member institutions of DATICAN, but for all data scientists and clinicians interested in using AI and data science technologies to improve healthcare delivery in Africa.

Project – Supplementary Grant for DATICAN Title: Data Management and Compute Platform for Data Science Training - 1. Aim of this Supplementary Grant Request This supplementary grant request aims to increase data management and data sharing infrastructure amongst three African Institutions. These African institutions are members of DS-I Africa through DATICAN, a UE5 project funded by NIH. The full meaning of DATICAN is Data Science and Medical Image Analysis Training for Improved Health Care Delivery in Nigeria 2. The aim of the Parent Project called DATICAN The main aim of DATICAN is to build capacity in Data Science and medical image analysis. DATICAN is a collaborative effort amongst 4 universities, 3 in Nigeria and 1 in the USA, these are Lagos State University, The University of Ibadan, Redeemer’s University and The University of Chicago. The project is funded for 3 years from September 2023 to September 2026. 3. Measurable and Obtainable Objectives of DATICAN DATICAN’s overarching objective is to produce a new generation of data scientists possessing the requisite data science skills in medical image analysis and the potential to become the clinical research leaders needed to improve healthcare delivery in sub-Saharan Africa (SSA). Our specific objectives are as follows. 1. Train participants in the use of Python and specific libraries, e.g., scikit-learn, pandas, pytorch, tensorflow and keras. 2. Equip participants with practical skills required for extracting diagnostic information from medical images and related medical data. 3. Train participants on how to define new biomedical research problems and hypotheses. 4. Train participants on how to identify the appropriate machine learning model or technology for solving a particular biomedical research problem. 5. Train participants on organization, processing and management of large medical data. 6. Train participants on ethical issues and responsible conduct in biomedical research. 7. Create a repository of data and teaching materials during the training that will subsequently be open and accessible to other researchers; that is, FAIR - Findable, Accessible, Interoperable and Reusable. 4. The Current Status of DATICAN Project implementation started immediately after receiving the award letter in September 2023. The following is a summary of the progress so far a. Recruitments of Trainees. We started by recruiting the trainees proposed for year 1 of the project. We were able to recruit 36 participants, comprising 12 PhD students, 12 MSc students, 6 postdocs and 6 Faculties. We achieved 100% of the recruitment target for year 1. b. Training of PG students, Postdocs and Faculty. This is ongoing, conducted by UChicago colleagues c. Training of Secondary School Students. This is ongoing. Conducted by Nigerian trainers d. Hackathon in Lagos. This was held in the first week of April 2024. It was very successful and the feedbacks were very positive. 5. Justification for Supplemental Project The focus of DATICAN is to produce a new generation of data scientists who will be able to use their skills to improve healthcare delivery in SSA. There are 3 major requirements for achieving this, these are the relevant skills set, local data peculiar to the SSA and computational resources. 1 a. Relevant skills set in Data Science and Medical Image Analysis. Our partner in the USA has commenced training towards meeting the skills set requirement. The training started in December 2023 as virtual classes. They visited Nigeria in the first week of April 2024 to conduct practical physical and hands-on training. They will also be training the Nigerian trainers in Chicago in the third week of April. The Nigerian trainers were visiting UChicago when this supplementary grant application was submitted, to receive hands-on training through the training-the-trainer programme organized by UChicago. These Nigerian trainers will take over the training responsibilities from our USA partner in the second year of the project. This approach was to allow Nigerians to take charge and own the training thereby making the project sustainable. With the progress so far, we are optimistic that DATICAN already has the potential to bridge the skill gap in data science with application in medical image analysis. b. Local Data and Repository. Irrespective of the skill sets of our trainees, it will be impossible for those skills to give good products that could help to improve healthcare delivery without access to local data. This is because data science and Artificial Intelligence technologies are data- driven and African data is unique because of many factors, such as lifestyles and genetic compositions. Through our partnership with some teaching hospitals in Nigeria, we have identified some medical imaging data like Magnetic Resonance Images, Computed Tomography, Mammograms, Ultrasound, X-Rays, etc. We have collected some of these imaging data and stored them on our hard disk. We were excited to see that there are hundreds of thousands of medical imaging data available in Nigeria. We planned to build a repository for these images, but unfortunately, the data are unstructured, un-curated and some of them are even unlabelled. This implies that the data are not in a useful form. We need data common to collect and store de-identified data from our partnering hospitals. The data will be used for training and for implementing the different projects to be executed by our trainees. We also need a platform that is Health Insurance Portability and Accountability Act (HIPAA) - compliant to avoid violation of the privacy and security of the data. Our number one priority in this supplementary project is to extend DATICAN to include data curation and proper data management, this is to make data sharing amongst the three institutions possible. The data curation will contain the following stages 1) Data Collection and Data Integration. This will require visiting 5 teaching hospitals that we currently partner with. University College Hospital Ibadan (UCH), Lagos State University Teaching Hospital (LASUTH), Obafemi Awolowo University Teaching Hospital (OAUTH), Afe Babalola University (ABUAD) and University of Lagos Teaching Hospital (LUTH). The data were acquired for different purposes and using different protocols but most of them are in dicom formats. We will arrange and integrate them based on the clinical conditions, image modalities, anatomy and diagnosis 2) Data Cleaning. The datasets are unstructured and contain a mixture of modalities and anatomy. We will need to separate them, remove dirty data and sort them into a usable form 3) Data Labelling. Most of the images do not have diagnosis information. We will work with the medical experts to supply diagnosis information and then label the images appropriately 4) Data Anonymization. All the datasets contain patient’s information. We will need to write computer programs to anonymize the data before use. 5) Data Storage. All cleaned, well sorted and anonymized data will be stored in a dedicated server. 6) Local Repository development. The dataset will be used to build a repository. This will be the first repository containing Nigerian medical images. We anticipate that the repository will contain about 10,000 medical images of different modalities, anatomy and from different sites within Nigeria. We will make efforts in the future to secure grants to extend the repository to contain more images. c. Computational Resources. Application of Data Science and AI technologies in medical image analysis requires access to compute infrastructure such as High-Performance Computing (HPC) with Graphic Processing Units (GPUs). This is mainly because medical images are huge and 2 processing them on CPU alone is not feasible, most especially when training large volumes. Our original plan was to leverage the HPC of our USA partner, the University of Chicago (UChicago). We have submitted a request to UChicago for all our trainees to be given access to the HPC of UChicago. We got the approval in March 2024 and DATICAN-LAB has been created for us. All our trainees now have access to the HPC of UChicago. This is, obviously, a great achievement for us and we are grateful to UChicago and NIH for this unique opportunity given to Nigerians through DATICAN. The downside of this is the lack of sustainability and scalability. The lifespan of DATICAN is 3 years, so what happens to our trainees in terms of access to HPC after DATICAN? The only way forward is for us to have our own HPC. Additionally, the skills acquired by our trainees will be useless if they do not have access to computational resources similar to the ones that we are currently training them on. Our number two priority in this supplementary project is to acquire an HPC with a GPU that will be housed in a secured data center in LASUTH and accessible to all partnering institutions. A desktop system equipped with GPU will also be procured at the training location at LASUTH for faster data processing and visualization. 6. Science Drivers and Use Cases 6.1 Case Study DATICAN currently has 36 trainees, comprising of PhD students, MSc students, postdocs and early career Faculties from 3 Universities. An additional 36 participants will be recruited in years 2 and 3 of the project. Each of the current participants has a project focusing on using data science technology and medical image analysis skills to solve health-related problems in Africa. All the projects require access to African medical data and an HPC. Please see Table 1 for the list of project topics of the current 36 trainees. The topics cover patients with breast cancer, stroke, pulmonary tumour, cervical cancer, lung cancer, sickle cell anaemia, stroke, tooth problems, skin cancer, dementia, tuberculosis, prostate cancer and traumatic brain injury using diverse imaging modalities like MRI, ultrasound, mammogram, Computed Tomography and X-rays images. We have data available at 5 teaching hospitals that we currently partnering with us, these are University College Hospital (UCH), LASUTH, OAUTH, ABUAD and LUTH. These data were acquired after securing the Institutional Review Board (IRB). The data were acquired for different clinical conditions and using different protocols but most of them are in dicom formats. We have collected about 2000 of these datasets already. 6.2 Sample Use Cases We have 36 use cases but we will explain two here. First, one of our trainees is working on the detection of hyperacute and acute staged ischemic brain stroke and his focus is to use MRI images. We already have about 1000 images of brain MRI. To execute this project, the trainee will need to collect the brain MRI images from DATICAN. Then clean, anonymize, and use it to build his deep learning model. Then the raw data and processed data will be curated. The trainee will be supported by the data Curator and Radiologist to be hired as part of this project. The data curator will help with data cleaning, anonymization and curation while the radiologist will help with labelling. Another example is about a trainee working on the early detection of breast cancer using machine learning techniques. We have already collected about 1000 mammogram images. The trainee will collect the data from us. Then clean, anonymize, and use it to build his machine learning model. Then the raw data and processed data will be curated. The trainee will be supported by the data Curator and Radiologist to be hired as part of this project. The data curator will help with data cleaning, anonymization and curation while the radiologist will help with labelling. 6.3 Data Curation and Integration 3 The current dataset are not labelled, not anonymized and not curated. We will get the data labelled, cleaned, anonymized and curated. We will also integrate the data because they come from different succes and for different purposes. We will build a repository with a user interface to allow easy search and querries. Table 1: Use cases for DATICAN Trainees Name Uni Degree in View Use Case 1 Adebowale, Ahmed Adedayo LASU PhD Improved Detection of Hyperacute and Acute Staged Ischemic Brain Stroke using Medical Imaging and Deep Learning Approach. 2 Azeez, Rahman Diekola LASU PhD Enhancing CNN-Based Pulmonary Tumor Detection using Generative Adversarial Networks (GANs) for Low-Quality Medical Imaging Data 3 Salami-Ohida, Sefiyat Oyiza LASU PhD Development of Machine learning model for cervical cancer detection using ultrasound images 4 Tijani, Rukayat Adetoun LASU PhD Predictive Modeling for High-Risk Lung Cancer Patient Identification 5 Oluwole Olajide UI PhD Leveraging Data Science and Medical Images Techniques to Enhance Early Diagnosis and Treatment of Sickle Cell Anemia (SCA) 6 Adebiyi Yemisi UI PhD An improved Region-Convolution Neural Network (RCNN) Detection Algorithm for Breast Cancer from Medical Images. 7 Ogunseye Elizabeth UI PhD Multi-label Classification and Severity Evaluation in Clinical and Medical Image Data using Deep Learning 8 Augustine Onyekwelu UI PhD Automated Detection, Localization, and Classification of Haemorrhagic Stroke using 9 Otun, Yetunde Deborah RUN PhD Development of deep learning models for early detection of breast cancer in women 10 Olorunfemi, Blessing Oluwatobi RUN PhD Integration of Deep Learning Models, and Sequential Ensemble Methods for Early Detection and Classification of Breast Cancer 11 Alu, Micheal Damilola RUN PhD Early Detection of Breast Cancer in Nigerian Women: A Multi-Modal Imaging Approach with Deep Neural Network 12 Awoniran, Temitayo RUN PhD Development of a Deep Learning Model for Breast Cancer Prediction in Nigerian women. 13 Olabayo, Oluwasegun LASU MSc Revolutionizing Tooth Decay Detection With Analytics: The Advancements In Early Intervention And Paradigm Shift In Monitoring Progression 14 Charles, Edward LASU MSc Data Analysis for Early Detection of Breast Cancer in Nigeria: The Advancements in Early Intervention and Monitoring Progression 15 WHETO, Paul LASU MSc Computational model for generating synthetic brain medical data 16 KAREEM, Wahab LASU MSc Medical image analysis using artificial intelligence (AI): Image retrieval (finding anomalies, such as brain tumors) A Case Study of Lagos State University Teaching Hospital 4 17 Oke, Monday Whenayon UI MSc Deep Learning Approach on Low-Resolution CT images in Resource-Constrained 18 Akintola, Mayode Mercy UI MSc Modeling a Machine Learning Mechanism for the Detection and Classification of Skin Cancer 19 Akinola Marvellous Timothy UI MSc A Localized Chest X-Ray Imaging Repository for Enhanced Predictive Healthcare 20 Ola Ayokunle Joshua UI MSc Development of a Predictive Deep Learning Model for Enhanced Breast 21 Adegoke, Ayomide David RUN MSc Development of an Ensemble of Deep Neural Networks for Early Detection of Breast Cancer Using Multi-Modal Imaging. 22 OYETUNDE, Oluwabukunmi RUN MSc Automated brain tumor segmentation in MRI images using transfer learning 23 Oyekunle, Isaac Olusegun RUN MSc Computational model for generating synthetic brain medical data 24 Amore, Oluwaseun RUN MSc Design and Implementation of Early Breast Cancer Detection System Using Computer Vision. 25 Kehinde Sotonwa Faculty LASU Development of a Deep Learning Model using Biomarkers for Digital Pathology 26 Hanat Raji-Lawal Faculty LASU Dementia Prediction and Detection Using Machine Learning Techniques 27 Mauton Asokere Faculty LASU Development of a Deep Learning Model for predicting Prostate cancer using Digital Pathology Images 28 Ayodele Oloyede Faculty LASU Multilabel Concepts Detection in Large Biomedical Images 29 Babatunde Ayinla Faculty UI Panoptic Multiorgan Multi-Climate Medical Image Analysis for Abnormality Detection Using CNN 30 Kadijat Ladoja Faculty UI Improved Machine Learning Model for Skin Cancer Classification 31 Oludele Adeleke Faculty UI Disorder(ASD) and traumatic brain injury diagnosis 32 Oladimeji Arowolo Faculty UI Development of Deep Learning Models for Tuberculosis Detection on Chest x-Ray Images 33 Adenike Adegoke Elijah Faculty RUN Deep Learning Approach for The Classification of Infective Pneumonia Using X-Ray Data 34 Toluwase Olowookere Faculty RUN Investigating the Few-Shot Learning Approach in the Classification and Detection of Rare Dental Conditions and/or Oral Cancers in Nigeria Using Dental X-Ray Imaging Data 35 Theresa O. Ojewumi Faculty RUN Development of a pneumonia disease detection system using Convolutional Neural Networks 36 Idowu Oyetade Faculty RUN Stroke Detection Using MRI Images and Deep Learning Note. LASU = Lagos State University, RUN= Redeemer’s University, UI=Universirty of Ibadan 7. Proposed Needs for Data Curation and Computational Resources 5 a. We need 2 Information Technology (IT) experts to help with data curation and anonymization. They will have BSc. Degree in IT related field. The 2 people will be hired for 1 year, 2024 to 2025 and will work under the direct supervision of the PI for DATICAN. Their main responsibilities will be 1) Data cleaning 2) Data anonymization 3) Data curation 4) Data storage 5) Repository development 6) Development of pipeline for 1 to 4 above 7) Development of data request policy to enhance seamless data sharing b. We need two radiologists to help with the labelling of the images. The Radiologists must be interested in research and be willing to support our trainees. The right candidates will be early career persons at each site who will work under the direct supervision of the MPI in Ibadan. He/She will be hired for 1 year, 2024 to 2025. c. Computational Resources 1) GPU server and central storage i. A node with 2 GPUs ii. (A network attached storage: ~100-200 TB => supported by DATICAN budget ) 2) Desktop with a commodity grade GPU 3) Note that the hardware will be procured with a minimum of 3-year hardware warranty and support for stability of services 8. Timelines Implementation of this supplemental project will commence upon funding of the project. The project is to cover 1 year and the time plan is given in Table 2. In summary, we will start by recruiting the technical staff and purchasing the requested hardware. These will be followed by the data collection, data cleaning, anonymization, etc. The project is planned for 1 year. Table 2. Activity Plan SN Deliverables Qtr 1 Qtr 2 Qtr 3 Qtr 4 1 Recruitment of IT experts and Radiologist X 2 Procurement of GPU X X X 3 Data Collection X X 4 Data Cleaning X X 5 Data Anonymization X X X 6 Data curation X X X 7 Data Storage X X X 8 Repository development X X 9 Development of pipelines for Data Engineering X 10 Development of data request policy to enhance seamless data sharing X 6 9. Personnel 9.1 Program Director / Principal Investigator at LASU Benjamin Aribisala, PhD - LASU, Nigeria (PI) - Professor of Computer Science, a data scientist and a medical image analyst. He has held many high-profile administrative positions in the University. For example, he was the Dean of Faculty of Science and former member of the governing council of Lagos State University. He was also a member of the Technical Advisory Board of African Open Science, Chairman of the Computer Science and the immediate past Director of Information Communication Technology (ICT) directorate. He led the committee that developed policies for the University, E.g., examination policy, revised promotion policy and automated promotion process in Lagos State University. He obtained his PhD degree in Computer Science from the University of Birmingham, UK and worked as an academic staff in 2 Universities in the UK before going back to Nigeria. He has over 28 years of teaching and research experience out of which about 11 were in leadership positions. He has supervised many PhD students and mentored many faculties. Some of his ex-students are now full professors. He has more than 100 peer reviewed papers published at reputable journals including nature. According to google scholar, he has been cited more than 8000 times in more than 80 countries. He has been awarded a number of grants, for example grants by British Council, Federal Government of Nigeria, Lagos State and IBM. He has served as an accreditation team member at national level and has led many training and mentoring programs, for example, he collaborated with Catania University in Italy in 2017 to organize Hackfest on development of e-infrastructure and science gateway in Nigeria. Benjamin was a Fulbright Scholar at the University of Chicago as a visiting professor in 2022 when DATICAN was conceived. The visiting position at the University of Chicago gave him the opportunity to work closely with the faculties, have access to health data, have access to computational resources and to set up the team for the DATICAN project. 9.2 Principal Investigators at UChicago, RUN, and UI 1. Alexander Pearson, MD, PhD - UChicago, USA (PI) – Earned multiple degrees in statistics and pursued post-doctoral work combining cancer biology and applied mathematics. He runs a multi-disciplinary systems biology research group to develop new computational precision oncology approaches for patient care. His primary appointments are in the Section of Hematology/Oncology, joint appointments in the Section of Computational Biomedicine and at Argonne National Laboratory. He is the Director of the Head and Neck Cancer Program and Director of Data Sciences in the Section of Hematology/Oncology. 2. Adenike Adeniji-Sofoluwe, MBBS, FWACS, FMCR, MS - UI, Nigeria (PI) – Senior Lecturer in Radiology and director of the radiology residency training program at the University College Hospital, Ibadan. She is one of the most experienced breast radiologists in the Nigerian breast cancer study group and the genomics group at UI. 3. Happi Christian (PI) . He is a professor of molecular biology and has a lot of experience in project management and training. We we leverage on his experience from his ongoing project on antimicrobial study for treatmentment of infectious diseases. He will provide some data which will be useful for training on infectious diseases. He will also provide guideance when necessary. 9.3 Co - Investigators at UChicago, RUN, and UI Olufunmilayo (Funmi) I. Olopade, MBBS, FACP – UChicago, USA (Co-I) – is the Chair of the Steering Committee for DATICAN. She is the Walter L. Palmer Distinguished Service Professor of Medicine and Human Genetics, and Dean for Global Health at the UChicago. Olopade is Program Director for NCI funded R25, T32 and K12 grants at UChicago. As a hematologist/oncologist, she has led teams of interdisciplinary researchers in conducting research on genomic determinants of breast cancer in women of African ancestry in the U.S. and internationally. The Doris Duke Charitable Foundation has recognized Olopade as a Distinguished Clinical Scientist and Exceptional Mentor. She is committed to fostering the careers of others and to helping the UChicago strengthen its international reputation as a leader in academic medicine by mentoring the next generation of global leaders in biomedical research. Godwin Ogbole, MBBS, FMCR, FWACS, MSc, MRP, MSCI - UI, Nigeria (Co-I) - A neuroradiologist, medical image analyst and clinician, Ogbole has wealth of experience in clinical research related to neuropsychological conditions using MRI, CT and X-ray. He has been involved in coordinating imaging seminars and 7 interdisciplinary brain workshops in Nigeria's largest teaching hospital and the West African sub region for the past ten years. These were designed to optimize care and imaging intervention in resource-poor settings to foster prevention and mitigation of non-communicable diseases through research and education. As regional Secretary of the Society for Brain Mapping and Therapeutics in Nigeria, he is building a platform for developing capacity in advanced brain imaging analysis techniques. Steffen Sammet, MD, PhD, DABR, DABMRS, FAMP - UChicago, USA (Co-I) - Professor of Radiology and Medical Physics, Director of Clinical MR Physics, Vice Chair of the Point of Care Ultrasound Council, is a physician and board-certified medical physicist by the American Board of Radiology with 25 years of experience in medical imaging. Hakizumwami Birali Runesha, Ph.D., USA (Co-I) – Associate Vice President for Research Computing and founding Director of the University of Chicago Research Computing Center (RCC) with more than 28 year of expericience in High Performance Computing, data science and application software development. His research interests are in sparse numerical libraries, AI/Deep learning, and reproducibility of scientific research. He was the PI of the NSF award for the Acquisition of a Data lifecycle Instrument for the Management and Sharing of Data from instruments and observations (Award # 162552) and the Research Data Management implementations: Impact on Science (RDMI) (Award #1661523). Abiodun Adewuya, MBChB, FWACP, FMCPsych, MPH, MD - LASU, Nigeria (co-I): Prof. Adewuya is a professor of public mental health and consultant in psychiatry research at the Federal Neuropsychiatric Hospital Yaba, Lagos. He has served as the current provost of the College of Medicine in LASU. He is currently a member of the governing council of LASU and a member of the board of directors of the College of Medicine in LASU. 3.4 Collaborators – Current PIs of DS-I Africa in Nigeria Mayowa Owolabi is the PI of the DS-I Africa project called GRASP (Growing Data-science Research in Africa to Stimulate Progress). GRASP is a capacity building project and the focus is on data science and image analysis of the brain. He is a Professor of neuroradiology and one of the topmost experts on stroke in Africa. He has thousands of MRI and CT images. GRASP and DATICAN will benefit from the proposed repository. Professor Temidayo Ogundiran is the PI of the DS-I Africa Consortium in UI. He is also the dean of UI’s college of Medicine. He is a clinician with an interest in ethics and legal issues in clinical studies. We will leverage his experience from his ongoing project on ethical and legal issues on data science studies. He will provide some training materials on ethical and legal issues, most especially as it relates to Nigeria. He will also provide guideance when necessary. 10. Conclusion The NIH-funded capacity building project in Africa is a collaborative project between LASU and two Nigerian universities (RUN and UI) and with UChicago. The project is funded for 3 years from 2023. Project implementation started in September 2023 and we have achieved all the deliverables proposed for the first 2 quarters of the first year. While collecting data needed for the training and the use cases, we discovered that the medical imaging data are unstructured and not in a usable form. We also discovered that there is an urgent need for computational resources. We hereby request for funds for data curation and the purchase of computational resources. We strongly believe that both the computational resources and repository will be useful not only for the member institutions of DATICAN, but for all data scientists and clinicians interested in using AI and data science technologies to improve healthcare delivery in Africa. 8