SK Rakib Ul Islam Rahat
Graduate Researcher in Multimodal AI
I work on medical artificial intelligence with a focus on multimodal deep learning, medical image analysis, and probabilistic calibration. My research emphasizes conservative evaluation, robustness under dataset shift, and protocol-faithful reporting for clinical screening models.
Email:
skrakibulislamrahat@gmail.com
Phone: +1 (323) 471-5980
Google Scholar:
scholar.google.com/citations?user=0X1eRi8AAAAJ
About
My work lies at the intersection of machine learning and healthcare. I focus on identifying and quantifying failure modes in medical AI, including miscalibration, shortcut learning, and performance degradation under external validation.
Research Interests
- Medical Image Analysis (Fundus Imaging, Mammography)
- Probabilistic Calibration and Reliability
- External Validation and Dataset Shift
- Explainable AI (Grad-CAM, Reliability Diagrams)
- Multimodal Learning with Clinical Data
Education
- MBA, MIS — International American University (2024–2026)
- MSc, Global Business & Administration — Kyungsung University (2022–2023)
- BTech, Computer Science & Engineering — LPU (2017–2021)
Research Projects
Calibration Analysis for Referable Diabetic Retinopathy (IJBHI)
Multi-seed internal calibration analysis of a ResNet-18 fundus classifier trained on APTOS 2019 using Counterfactual Consistency Regularization, with constrained external evaluation on Messidor-2.
GitHubExposing Dataset Artifacts in Medical AI
Empirical study demonstrating shortcut learning driven by non-pathological artifacts in fundus imaging models.
GitHubLightweight DR Detection Models
Evaluation of MobileNetV2, EfficientNet-B0, and SqueezeNet focusing on accuracy–efficiency trade-offs for low-resource screening.
GitHubMultimodal Framework Research
Multimodal pipelines integrating medical images and structured clinical data to study robustness and interpretability.
GitHubSelected Publications
- Calibration Analysis Under Counterfactual Consistency Regularization for Referable Diabetic Retinopathy. IEEE JBHI (under review)
- TriGWONet: A Lightweight Multibranch CNN Using Gray Wolf Optimization. Discover AI, 2025
- Artificial Intelligence for Chronic Kidney Disease Risk Stratification. BJNS, 2025
- Advancing Diabetic Retinopathy Detection with AI. BJNS, 2025
- Deep Learning Framework for Early Breast Cancer Detection. BJNS, 2025