Curriculum Vitae

Research Profile

I am a Biomedical AI Early-Career Researcher with experience in medical image analysis, multimodal clinical AI, explainable AI, and robust representation learning especially under limited and noisy label settings. My work focuses on building clinically meaningful machine learning systems for imaging and structured health data, with attention to generalization, interpretability, and clinical translation.

Research Interests

My research interests include: Medical Image Analysis; Multimodal Clinical AI; Trustworthy and Explainable AI; Robustness and Generalization; Representation Learning; Clinical Decision Support; Low-resource Health AI.

Technical Skills

ML/DL: PyTorch, TensorFlow/Keras, scikit-learn, transformers, multimodal learning
Programming: Python, R, C/C++
Systems: Linux, Windows, High Performance Computing with SLURM (HPC), Grid Computing with Oracle Sun Grid Engine, Docker, GCP, GPU Computing
Data and Scientific Computing: SQL, NumPy, Pandas, Matplotlib, Seaborn
Neuroimaging Data and Tools: BIDS, FSL, FreeSurfer
Medical Imaging: OpenCV, SimpleITK, NiBabel, Pydicom, ANTsPy, scikit-image
Explainable, Fair, and Trustworthy AI: SHAP, Captum, Fairlearn, AIF360, LIME, TorchCAM, iNNvestigate

Soft Skills

Organization and project management; Communication; Independent working and self-responsibility; Solution-oriented problem solving; Flexibility and adaptability; Teamwork and collaboration; Leadership and mentorship; Cross-cultural communication; Time management; Critical thinking and creativity; Resilience and perseverance; Ethical awareness and integrity; Continuous learning and growth mindset

Languages

English (Bilingual Proficiency); German (Good); French (Elementary); Krio (Native); Kono (Native)

Education

Ph.D. in Cognitive Science

Universität Osnabrück, Germany (Nov 2021 – Nov 2025)

Research focus: Deep Neural Representation Learning
Advisors: Prof. Günther Heidemann and Prof. Simone Pika
Funded by the DFG Research Training Group in Computational Cognition

M.Sc. in Mathematical Sciences

African Institute for Mathematical Sciences (AIMS), Rwanda (Sept 2020 – Jul 2021)

Thesis: Deep Transfer Learning for Chest X-ray Image Analysis
Award: AIMS / Mastercard Foundation Scholarship

M.Sc. in Computer Science and Engineering

University of Dhaka, Bangladesh (Jul 2018 – Aug 2020)

Thesis: Deep Learning for Brain Tumor Detection using MRI Data in collaboration with clinicians
Award: Queen Elizabeth Commonwealth Scholarship

B.Sc. in Computer Science

University of Makeni, Sierra Leone

(Sept 2012 – Feb 2017)

Undergraduate Merit Scholarship

Professional Experience

Co-Founder & Biomedical AI Researcher

International Research Collaboration with Rhodes University and Global Academic Partners
Dec 2024 – Present

Conduct research in multimodal representation learning for clinical data, focusing on early diagnosis, and prognosis with emphasis on robustness, explainability, fairness, and generalization.
Contribute to collaborative research projects in biomedical AI using multi-institutional healthcare datasets spanning Africa, Asia, South America and Europe.
Co-supervise 3 students (2 PhDs and 1 BSc) on projects in medical imaging and clinical AI, including transformer-based 3D medical image analysis and explainable/fair AI for low-resource healthcare settings.
Contribute to scientific writing and dissemination of research outputs, including peer-reviewed manuscripts and preprints in biomedical AI.
Co-created and lead an interdisciplinary research consortium comprising 33 members across 21 institutions focused on AI applications in neglected tropical diseases (NTDs).
Coordinate research work packages, project milestones, and collaborative activities across the aforementioned consortium members.

Research Associate (PhD Researcher)

RTG Computational Cognition, Universität Osnabrück
Nov 2021 – Dec 2024

Conducted research in deep representation learning for artificial intelligence, with a focus on self-supervised learning methods including contrastive, generative, and joint-embedding approaches.
Developed joint-embedding, contrastive, and generative models for disentangled representation learning, including methods such as Barlow Twins, variational autoencoders (VAEs), and supervised contrastive learning.
Improved data processing efficiency by at least 20\% and increased model performance by at least 25\% across target machine learning tasks.
Curated and maintained the SynSpeech dataset and managed associated open-source research codebases and accessibility.
Presented research at international conferences and doctoral consortia, including NeurIPS (2023), German Conference on Artificial Intelligence (KI) Doctoral Consortium (2023), and ICLR (2024).
Supervised and mentored Master’s students in machine learning and deep learning research projects.

Research and Teaching Assistant

University of Makeni, University of Makeni, Makeni, Sierra Leone
Feb 2017 – Jul 2018 (part-time)

Taught four undergraduate Computer Science courses with approximately 40 students per course.
Designed and developed course materials, assignments, and examination assessments.
Mentored and supervised student thesis.

Lecturer

Limkokwing University of Creative Technology, Limkokwing University of Creative Technology, Freetown, Sierra Leone Jan 2018 – Jul 2018 (part-time)

Taught Principles of Programming Logic and Design to more than 120 undergraduate students per semester.
Delivered lectures, prepared teaching materials, and supported student assessment and academic evaluation.
Facilitated practical programming exercises and supported students in foundational software development concepts.

Registrar

African Accents International Institute of Computer Technology

Selected Publications

Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift

Brima Y, Atemkeng M, Kallon LH, Niyukuri D, Vacavant A, Saidu S, Chen DG. Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift. arXiv preprint arXiv:2605.26589. 2026 May 26.

Bridging visual saliency and large language models for explainable deep learning in medical imaging

Nguezet PV, Fute ET, Brima Y, Azanguezet BM, Atemkeng M. Bridging visual saliency and large language models for explainable deep learning in medical imaging. arXiv preprint arXiv:2605.06197. 2026 May 7.

Artificial intelligence in neglected tropical diseases: current applications, challenges, and opportunities

Brima Y, Atemkeng M, Ngueajio MK, Ngueabou Y, Nguembang Fadja A, Bonginkosi N, et al. Artificial intelligence in neglected tropical diseases: current applications, challenges, and opportunities. NPJ Digit Med. 2026. Submitted for publication.

An Empirical Study of Machine Learning Robustness and Scalability for Imbalanced Tabular Clinical Data in Emergency and Critical Care

Brima Y, Atemkeng M. Robustness and Scalability Of Machine Learning for Imbalanced Clinical Data in Emergency and Critical Care. arXiv preprint arXiv:2512.21602. 2025 Dec 25.

An unsupervised XAI framework for dementia detection with context enrichment

Singh, D., Brima, Y., Levin, F., Becker, M., Hiller, B., Hermann, A., Villar-Munoz, I., Beichert, L., Bernhardt, A., Buerger, K. and Butryn, M., 2025. An unsupervised XAI framework for dementia detection with context enrichment. Scientific reports, 15(1), p.39554

A systematic review of low-rank and local low-rank matrix approximation in big data medical imaging

Hamlomo, S., Atemkeng, M., Brima, Y. et al. A systematic review of low-rank and local low-rank matrix approximation in big data medical imaging. Neural Comput & Applic (2025). https://doi.org/10.1007/s00521-025-11055-2

Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction

Brima, Y., et al. (2024). Understanding Self-Supervised Learning of Speech Representation via Invariance and Redundancy Reduction. MDPI Information, 15(2), 114. DOI: 10.3390/info15020114

Saliency-driven Explainable Deep Learning in Medical Imaging: Bridging Visual Explainability and Statistical Quantitative Analysis

Brima, Y., Atemkeng, M. (2024). Saliency-driven explainable deep learning in medical imaging: bridging visual explainability and statistical quantitative analysis. BioData Mining, 17, 18. DOI: 10.1186/s13040-024-00370-4

Bridging the Gap: Exploring Interpretability in Deep Learning Models for Brain Tumor Detection and Diagnosis from MRI Images

Nhlapho, W., Atemkeng, M., Brima, Y., et al. (2024). Bridging the Gap: Exploring Interpretability in Deep Learning Models for Brain Tumor Detection and Diagnosis from MRI Images. Information, 15(4), 182. DOI: 10.3390/info15040182

Learning Disentangled Audio Representations through Controlled Synthesis

Brima Y, Krumnack U, Pika S, Heidemann G. (2023). Learning Disentangled Audio Representations through Controlled Synthesis. ICLR Tiny Papers Track 2024.

Learning Disentangled Speech Representations

Brima, Y., Krumnack, U., Pika, S., & Heidemann, G. (2023). Learning Disentangled Speech Representations. New in Machine Learning Workshop, NeurIPS 2023.

Self-Supervised Learning of Speech Representation via Redundancy Reduction

Brima, Yusuf (2023): Self-Supervised Learning of Speech Representation via Redundancy Reduction. DC@KI2023: Proceedings of Doctoral Consortium at KI 2023. DOI: 10.18420/ki2023-dc-02. Gesellschaft für Informatik e.V.. pp. 11-19. Doctoral Consortium at KI 2023. Berlin. 45195

A Mathematical Framework for Understanding Recognition Systems

Brima, Yusuf. "A Mathematical Framework for Understanding Recognition Systems" biorxiv preprint biorxiv:2023.06.08.544240 (2023).

Deep Transfer Learning for Brain Magnetic Resonance Image Multi-class Classification

Brima, Y., Kamal Tushar, M. H., Kabir, U., Islam, T. (2022). Deep Transfer Learning for Brain Magnetic Resonance Image Multi-class Classification. Dhaka University Journal of Applied Science and Engineering, 6(2), 14–29. DOI: 10.3329/dujase.v6i2.59215

Transfer Learning for the Detection and Diagnosis of Types of Pneumonia including Pneumonia Induced by COVID-19 from Chest X-ray Images

Brima, Y., Atemkeng, M., Tankio Djiokap, S., Ebiele, J., & Tchakounté, F. (2021). Transfer Learning for the Detection and Diagnosis of Types of Pneumonia including Pneumonia Induced by COVID-19 from Chest X-ray Images. Diagnostics, 11(8), 1480. DOI: 10.3390/diagnostics11081480

Brain MRI Dataset

Yusuf Brima, Mossadek Hossain Kamal, Upama Kabir, and Tariqul Islam (2021). "Brain MRI Dataset." Figshare/Dataset. 1(1).

Competitive Scholarships and Awards

CIFAR Deep Learning and Reinforcement Learning (DLRL) Summer School Inclusive AI Scholarship, Canada, 2024
Deep Learning Indaba Scholarship, 2023
Cambridge Ellis Machine Learning Summer School Fully-funded Scholarship, 2022

Further Training and Certifications

DeepLearning.AI AI for Medicine Specialization (Coursera, online, 2026) — (3 months)
Focus: diagnostic, prognostic, and treatment-effect AI models in healthcare.
Certificate Link
Stanford University AI for Healthcare Specialization (Coursera, online, 2025) — (8 weeks)
Focus: clinical data, healthcare systems, and evaluation of AI in medicine.
Certificate Link
MUST Deep Learning Bootcamp (North-West University, South Africa, 2025) — (2 weeks intensive)
Focus: CNNs, optimization, gradient descent, regularization, supervised learning.
IBM AI Engineering Professional Certificate (Coursera, online, 2023) — (5 months)
Focus: deep learning, TensorFlow, Keras, neural networks, hyperparameter tuning.
Certificate Link
IBM Data Science Professional Certificate (Coursera, online, 2023) — (6 months)
Focus: Python, SQL, machine learning, data visualization, cloud computing.
Certificate Link
Python Programming and Data Structures (University of Michigan, Coursera, online, 2023) — (8 weeks)
Focus: Python, algorithms, recursion, object-oriented programming.
Certificate Link
Mediterranean Machine Learning School (Università Milano Bicocca, Italy, 2022) — (5-day intensive)
Focus: advanced deep learning lectures and hands-on sessions.
Deep Learning Program (Neuromatch Academy, online, 2022) — (3-week intensive program)
Focus: end-to-end deep learning from theory to implementation.
Machine Learning Summer School (Bandung, Indonesia, 2020) — (2-week intensive)
Focus: CNNs, VAEs, NLP, TensorFlow, transfer learning.
Machine Learning Summer School (University of Oxford, UK, 2020) — (2-week intensive)
Focus: Bayesian ML, computer vision, NLP, reinforcement learning, causal inference.
Mathematics for Machine Learning (Imperial College London, Coursera, online, 2020) — (3 months)
Focus: linear algebra, multivariate calculus, optimization, PCA.
Certificate Link

Data Access, Governance, and Compliance

Approved access to Demographic and Health Surveys (DHS) data for research on trustworthy disease diagnosis.
Credentialed access and training for controlled biomedical datasets and platforms, including UK Biobank/MRC, PhysioNet, LONI IDA, and the German FDPG framework.
Training in research ethics, data privacy, and responsible data use (CITI Program); experienced with IRB-compliant workflows and secure handling of sensitive health data.

Talks

Multimodal Representation for Robustness and Generalization in Biomedical Applications

May 06, 2026

Talk at Max Delbrück Center for Molecular Medicine (MDC), Berlin, Germany

Multimodal Federated Learning for Robust Lung Cancer Prognosis

February 19, 2025

Talk at Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Bonn, Germany

Assessing Explainability in Deep Learning for Medical Image Analysis

December 16, 2024

Talk at Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Bonn, Germany

Trustworthy Healthcare AI for Mental Health Risk Prediction

December 10, 2024

Talk at Neurobiology Research Unit, Copenhagen University Hospital, Copenhagen, Denmark

Assessing Fusarium Oxysporum Disease Severity in Cotton Using Unmanned Aerial System Images and a Hybrid Domain Adaptation Deep Learning Time Series Model

July 10, 2024

Talk at Leibniz Institute for Agricultural Engineering and Bioeconomy, Potsdam, Germany

Causal Representation Learning

March 13, 2024

Talk at Computer Vision Colloquium, Osnabrueck University, Osnabrück, Germany

Disentangled Speech Representation Learning via Self-Supervision

December 10, 2023

Poster Presentation at NeurIPS 2023, New Orleans, USA

Self-Supervised Learning of Speech Representation via Redundancy Reduction

July 26, 2023

Oral Presentation at KI 2023 – 46th German Conference on Artificial Intelligence, Berlin, Germany

Supervised Contrastive Representation Learning for Individual Recognition in the Wild

November 16, 2022

Talk at Language and Communication colloquium, Institute of Cognitive Science, Osnabrueck University, Germany, Building 50, Room 50/E07, Wachsbleiche 27, Osnabrueck, Germany

Supervised Contrastive Deep Learning for Individual Recognition in Chimpanzees in the Wild

August 08, 2022

Talk at Department of Comparative Cultural Psychology, Max Planck Institute for Evolutionary Anthropology, Germany, Virtual