Md. Asif Uddin

Research

1. HierarchiRetina

   2026

   HierarchiRetina: A Lesion-Aware Hierarchical Deep Learning Framework Enabling Interpretable Diabetic Retinopathy Severity Assessment via Multi-Stage Retinal Fundus Image Analysis

   depositedSupervisors: Rafeed Rahman, Niloy Farhan, Md. Golam Rabiul Alam. Co-authors: Hosni Rabbani, Shahrin Tabassum.

   Macro-AUC 0.9422 · Ungradable detection AUC 0.9995 · DDR 5-class QWK, 5-fold ensemble 0.8533 · End-to-end pipeline QWK 0.7942 · Per-dataset QWK 0.83 – 0.93

2. Rank Radii Transfer as Quantiles

   2026

   Rank Radii Transfer as Quantiles: Taxonomic Placement and Sub-Taxonomy Construction for Unseen Species

   in preparationSupervisors: Niloy Farhan.

3. Automated Renal Analysis

   2026

   Automated Renal Analysis and Report Generation from Thick-Slice Non-Contrast CT

   in preparationSupervisors: Niloy Farhan.

4. HCGT-PG

   2026

   HCGT-PG: Hierarchical Counterfactual Graph Transformer, Perturbation-Grounded — causal biomarker discovery in Alzheimer's disease microglia

   proposal acceptedSupervisors: Dr. Badhan Das.

Papers and manuscripts

1. HierarchiRetina: A Multi-Stage Deep Learning Pipeline for Diabetic Retinopathy Severity Assessment

   2026

   publishedBSc thesis, BRAC University

2. Automated Renal Analysis

   2026

   in preparation

3. Rank Radii Transfer as Quantiles: Taxonomic Placement and Sub-Taxonomy Construction for Unseen Species

   2026

   in preparation

Education

1. MSc, Computer Science and Engineering

   Fall 2026 —

   BRAC University, Dhaka.Thesis proposal accepted: HCGT-PG. Supervisor: Dr. Badhan Das.

2. BSc, Computer Science and Engineering

   Fall 2021 – Summer 2026

   BRAC University, Dhaka.CGPA 3.30 / 4.00.Thesis: HierarchiRetina, supervised by Rafeed Rahman, deposited in the BRAC University institutional repository. Coursework in machine learning, deep learning, compilers, theory of computation, DBMS, operating systems, algorithms and software engineering.

3. Higher Secondary Certificate

   2020

   Uttara High School and College, Dhaka.GPA 5.00 / 5.00.Science.

4. Secondary School Certificate

   2018

   Ullapara Merchant Pilot High School, Sirajganj.GPA 4.72 / 5.00.Science.

Technical

Languages

Python (primary). C (coursework level).

Deep learning

PyTorch, timm, segmentation_models_pytorch. Mixed-precision training with GradScaler tuning, EMA, test-time augmentation, k-fold CV with resumable per-fold checkpointing, class-imbalance handling (pos_weight, weighted samplers), threshold calibration on validation only, ordinal regression (CORN), mixture-of-experts, cross-attention fusion, attention gates, ASPP, GeM pooling, deep supervision, frozen-backbone transfer, Grad-CAM.

Architectures used hands-on

ConvNeXt V2, Swin UNETR V2, DINOv2/v3, EfficientNet, U-Net, U-Net++, Attention U-Net, SwinHRUNetPP, HSMoE-AUNet, image-text encoders.

Medical imaging

Fundus photography, non-contrast CT, NIfTI and DICOM handling, FOV masking with morphological erosion, CLAHE on the green channel, retinal cropping, patch extraction and stitching, lesion-level connected-component evaluation, de-identification, radiologist report parsing.

Evaluation

QWK, ICC, AUC-ROC, AUC-PR, Dice, IoU, NMI, lesion-level and image-level recall, sensitivity/specificity tradeoff analysis, per-dataset breakdowns, held-out test discipline and leakage assertions.

Causal inference and computational biology

Causal graphs and DAGs, d-separation, interventions, counterfactual reasoning, gene perturbation analysis, gene regulatory network inference, multi-omics integration and biomarker discovery.

Data

pandas, NumPy, Albumentations, OpenCV, Matplotlib, Seaborn, scikit-learn, nbformat.

Backend

FastAPI, REST APIs, SQLAlchemy, JWT auth, Alembic, AWS S3, CloudFront.

MODEL FAMILIARITY

Beyond the architectures I have used hands-on, I regularly study modern vision, multimodal, language, medical imaging and computational biology models. This includes SigLIP 2, EVA-CLIP, SAM 3, nnU-Net, ViT, Qwen, Llama, DeepSeek, Kimi, MedGemma and genomic models such as AlphaGenome and Geneformer. I focus on understanding their architecture, training objective, scaling behavior, benchmarks, limitations and practical use rather than treating familiarity with a model as equivalent to hands-on experience. The model notes I keep are part of this ongoing study.

READING

I love reading books and research papers. My current reading is centered on machine learning, causality and computational biology. Key books include The Book of Why, Causality: Models, Reasoning, and Inference, Causal Inference in Statistics: A Primer, and Elements of Causal Inference: Foundations and Learning Algorithms. The reading is not separate from the research work. It is mainly about understanding what can be inferred from data, where the assumptions enter, and how interventions can provide stronger evidence than observation alone.

Other

Git, Jupyter, LaTeX, lex/yacc, CUDA-level debugging. Trained on an NVIDIA RTX A6000.

Languages. Bangla, native. English, full professional proficiency and the medium of instruction throughout secondary and undergraduate study.

Engineering

1. CSMMS — Campus Student Management and Marketplace System

   FastAPI backend: REST API design, filtered and paginated marketplace, S3 and CloudFront image upload, service impact metrics, SQLAlchemy, JWT, Alembic.

2. Leveraging CNN and Random Forest for Accurate Food Expiry Prediction

   AI-driven food expiry prediction model combining CNNs for image analysis with Random Forest and MLP algorithms to evaluate environmental metadata (temperature, humidity, storage duration) and minimize food waste.

3. Compiler symbol table

   Scoped symbol table for a compiler front end using lex and yacc/bison, with cross-platform builds on Linux and macOS.