Amanour Rahman

Amanour Rahman

Aspiring ML Researcher | Medical AI & Multimodal Learning | CSE Undergrad @AUST | Turning Data into Diagnostics

Introduction

I hold a B.Sc. in Computer Science and Engineering from Ahsanullah University of Science and Technology (AUST), Bangladesh. My research focuses on medical image analysis and trustworthy AI for healthcare, including explainable, uncertainty-aware, federated, and continual learning for ultrasound and other clinical imaging. I aim to build models that are not only accurate but also transparent, calibrated, and ready for real clinical use.
🤝 I am always open to collaboration! ✉ amanourrahman609@gmail.com
Research Interests
Medical Image Analysis Explainable AI (XAI) Ultrasound Segmentation Uncertainty Quantification Conformal Prediction Federated Learning Continual Learning Domain Shift & Generalization Green Learning Radiomics State Space Models (Mamba) Trustworthy AI
Academic Service
Journal Reviewer
PLOS ONE
Intelligence-Based Medicine (Elsevier)
NED University Journal of Research
Workshop Reviewer
NeurIPS MedReasoner Workshop
MICCAI 2026 Workshop on Efficient Medical AI (EMA)
Open-Source Contributor
Project MONAI (NVIDIA) — fixed PerceptualLoss docs (Issue #8592)
Author & Maintainer
MedXAI — open-source medical imaging toolkit
More details →
Honors & Awards
2026 EMA 2026 Best Reviewer Award
MICCAI 2026 Workshop on Efficient Medical AI
News
Publications
Journal Articles
  1. FedXAI: Federated Medical Imaging with Intrinsic Explainability and Differentially Private Explanation Auditing. Mohammad Amanour Rahman. [Machine Learning, Springer, Special Issue on Advances in Federated Learning for Critical Applications, 2026]
  2. FA-SSNet: A Frequency-Aware Semi-Supervised Network for Thyroid Nodule Segmentation in Ultrasound Images. Rowzatul Zannath Prerona, Mohammad Amanour Rahman. [IET Image Processing, 2026]
  3. TCB-Net: Topology-Constrained Boundary-Interior Decoupled Network for Breast Ultrasound Lesion Segmentation. Mohammad Amanour Rahman. [IET Image Processing, 2026] [Link]
  4. Spectral-Spatial Mamba with Uncertainty-Guided Refinement for Thyroid Nodule Diagnosis. Mohammad Amanour Rahman, Rowzatul Zannath Prerona. [Array, Elsevier, 2026] [Link]
  5. HyFormer-Net: A Synergistic CNN-Transformer with Interpretable Multi-Scale Fusion for Breast Lesion Segmentation and Classification in Ultrasound Images. Mohammad Amanour Rahman. [Intelligence-Based Medicine, Elsevier, 2026] [Link]
Conference & Workshop Papers
  1. UCBound-Net: Uncertainty-Guided Boundary-Aware Continual Learning for Domain-Incremental Ultrasound Segmentation. Mohammad Amanour Rahman. [MICCAI 2026 CLiMeM Workshop] [arXiv]
  2. MedSaab-US: A Backpropagation-Free Multi-Scale Wavelet-Saab Framework for Thyroid Nodule Segmentation in Ultrasound Images. Mohammad Amanour Rahman. [IEEE ICIP 2026 LBDL II Workshop] [arXiv]
  3. RadiomicNet: A Hybrid Radiomics-Guided Lightweight Architecture for Interpretable Medical Image Segmentation. Mohammad Amanour Rahman. [IEEE ICIP 2026 LBDL II Workshop] [arXiv]
Book Chapter
  1. Book chapter (abstract accepted). Mohammad Amanour Rahman. [AI for Medical Imaging and Precision Diagnostics: From Theory to Practice, Routledge, Taylor & Francis Group, 2026]