biomedclip

Production-grade medical AI framework using BioMedCLIP (ViT-B/16) for multi-label chest X-ray pathology detection. Features Monte Carlo Dropout for uncertainty quantification, per-class threshold calibration, ViT-GradCAM explainability, and LLaMA-3.3 reporting. FastAPI + Next.js.

SecureMed-LLM: A privacy-preserving framework for clinical report generation from chest X-rays, integrating Med-Guard anonymization, DP-SGD (ε=3.0), adversarial training, IDS-LLM validation, and ECIES/Curve25519 encryption. PeerJ Computer Science 2025.

End-to-end multimodal medical AI pipeline — VLM benchmarking, FAISS semantic search, clinical NER, and wav2vec2 speech transcription | PyTorch | HuggingFace

Differential Attention-Augmented BiomedCLIP for multi-label VCE classification - ICPR 2026 RARE-VISION Competition submission from MINDH Lab, IIT Hyderabad. Achieves mAP@0.5 of 0.2456 on temporal event detection across 17 anatomical and pathological classes.

Reproducibility package for a PRISMA-2020 systematic review and meta-analysis comparing pretrained foundation-model embeddings vs handcrafted radiomics across 28 head-to-head studies. Under peer review at Insights into Imaging.

Chest X-ray Visual Question Answering: zero-shot BiomedCLIP + trainable 14-finding head on CheXpert/CheXlocalize. yes/no/uncertain answers, calibrated thresholds, Gradio demo.

Federated Adaptive BiomedCLIP with instance-level clinical prompts for brain tumor classification.

A dried tear leaves a fractal fingerprint. Lacrima is the AI that learned to read it — detecting 5 chronic diseases through multi-agent LLM orchestration.

Improving tumor segmentation performance using DPO based on MedCLIP-SAMv2

LangGraph multi-agent pipeline for neuroimaging classification - MedGemma 1.5 4B triage, SAM3 lesion segmentation, CNN classification (VGG16/DenseNet/ResNet), and BiomedCLIP re-ranking across brain tumour, MS, and stroke tasks.