I am a deep learning researcher specializing in medical image analysis and trustworthy AI, with a B.Tech in Computer Science & Engineering (AI & ML) from VIT-AP University, India.
My research focuses on building AI systems that are not just accurate, but clinically reliable — models that know when they might be wrong. My two active research projects target open problems at the frontier of medical AI:
- Paper 1 — Dual-Branch LoRA adaptation of SAM for multi-modal brain tumor segmentation (target: MICCAI 2026)
- Paper 2 — Conformal prediction on vision-language models for uncertainty-aware chest X-ray diagnosis (target: IEEE TMI / NeurIPS 2026)
28+ peer-reviewed publications · 514 citations · h-index 12 · i10-index 15
|
Dual-branch LoRA adapter for SAM with cross-modal attention fusion across T1/T2/FLAIR MRI. Achieves multi-modal brain tumor segmentation with missing-modality robustness using <5% extra parameters. Key novelty: First LoRA-SAM with dual-branch multi-modal fusion + missing-modality dropout training |
Post-hoc RAPS conformal prediction on CheXagent VLM for chest X-ray diagnosis with provable coverage guarantees per pathology class. Zero retraining required. Key novelty: First class-conditional conformal head on a radiology VLM with clinical safety metrics |
| Year | Title | Venue | IF |
|---|---|---|---|
| 2025 | Tea Leaf Disease Detection using CNNs | Scientific Reports (Nature) | 3.9 |
| 2025 | Advanced NN for Tomato Leaf Disease | Discover Sustainability (Springer) | — |
| 2025 | MS-DSCCNet: Brain Tumor MRI Classification | IEEE DELCON 2025 | — |
| 2025 | PneuNet: Pediatric Pneumonia Detection | IEEE DELCON 2025 | — |
| 2024 | Alzheimer's Disease Classification from MRI | Springer | — |
| 2024 | Automated Haematology: Blood Cell Detection | Peer-reviewed journal | — |
| 2024 | Malaria Cell Image Classification | Peer-reviewed journal | — |
Full publication list: Google Scholar →
Deep Learning & ML
Languages & Tools
Medical Imaging & XAI
Medical Imaging AI ████████████████████ 100%
Uncertainty Quantification ████████████████░░░░ 80%
Foundation Model Adaptation ███████████████░░░░░ 75%
Precision Agriculture AI █████████████░░░░░░░ 65%
Computer Vision ████████████████████ 100%
- 📰 28+ peer-reviewed papers in Q1/Q2 journals and IEEE conferences
- 📈 514 citations, h-index 12, i10-index 15
- 🌍 5 international conference presentations — Germany, Slovakia, Dubai, India, Malaysia
- 🥇 Best Research Paper Award — ICISML 2023
- 🏅 Best Technical Club Award — VIT-AP University 2024 (ML Club President)
- 🔬 3 research internships — Saudi Arabia (PSAU), India (IFHE), Bangladesh (ADE)
- 📝 BMC Medical Imaging reviewer — invited to editorial board
Building medical AI systems that clinicians can actually trust — not just models that achieve high accuracy on benchmarks, but systems with formal uncertainty guarantees, interpretable decisions, and robustness to real-world clinical constraints (missing modalities, distribution shift, limited annotations).
Currently pursuing funded MS/PhD positions in AI for healthcare. If your lab works on trustworthy medical AI, foundation model adaptation, or uncertainty quantification — let's connect.
"The goal of AI in medicine is not to replace clinicians — it is to make sure they never have to make a critical decision alone and uninformed."