I study Computer Science and Engineering at the Islamic University of Technology (IUT) in Gazipur, Bangladesh, where I hold a CGPA of 3.91 / 4.00.
My research focuses on computer vision and medical image analysis, with particular interest in multiple instance learning, graph neural networks and implicit models. My undergraduate thesis develops a dual-view multiple instance learning framework that fuses MRI views with clinical data for Alzheimer's disease classification.
I have also worked as a trainee software engineer at Cefalo Bangladesh, building full-stack web applications with NestJS and Next.js.
Dual-View MIL with Clinical Fusion for Alzheimer's Classification
Under Review
Undergraduate Thesis
Axial and coronal MRI slices fused through separate DINOv3 ViT backbones with bidirectional cross-view attention and gated-attention MIL pooling, combined with tokenized clinical covariates via cross-modal fusion.
Achieved 94% test accuracy on CN/MCI/AD classification on ADNI-1 using strict subject-level splits.
Under review at the 41st International Conference on Image and Vision Computing New Zealand.
Implicit Vision Graph Networks for Semantic Segmentation
In Progress
Research Project
Image patches treated as graph nodes and processed by a single weight-tied Vision-GNN block, iterated to a fixed point to act as an infinite-depth backbone without any CNN.
Contributed to the full-stack development of Cefalo's official recruitment portal, enhancing platform usability for both prospective candidates and recruiters.
Engineered robust RESTful APIs utilizing NestJS to handle backend business logic and data persistence.
Optimized frontend components in Next.js, improving UI behaviour and state management.
