medical-ai

TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.

[TMLR 2025🔥] A survey for the autoregressive models in vision.

[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.

Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.

Build a complete experiment pipeline for your PyTorch MIP model in 10 seconds.

[Nature Communications 2025] Towards Expert-level Autonomous Carotid Ultrasonography with Large-scale Learning-based Robotic System

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.

OpenLens AI: A Fully Autonomous Multimodal Research Agent｜ OpenLens AI：全自主多模态科研智能体

[Nature Medicine'25] A Multimodal Vision Foundation Model for Clinical Dermatology

Frontiers in Intelligent Colonoscopy [ColonSurvey | ColonINST | ColonGPT]

[ICML 2026] Official UniMedVL implementation — a unified medical vision-language model for multimodal understanding, medical image generation, and interleaved tasks in a single checkpoint, trained on UniMed-5M (5.6M+ samples).

[JAMA] "Complete AI-Enabled Echocardiography Interpretation with Multitask Deep Learning" by Gregory Holste, Evangelos K. Oikonomou, Márton Tokodi, Attila Kovács, Zhangyang Wang, & Rohan Khera

ClinVec: Unified Embeddings of Clinical Codes Enable Knowledge-Grounded AI in Medicine

Open-source multimodal dataset: 98K+ clinical cases & 139K+ medical images from PubMed Central

[ICCV'25 Highlight] Derm1M: A Million‑Scale Vision‑Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

Unofficial OpenEvidence MCP server — query OpenEvidence from Claude Code, Codex, and any MCP client through your own logged-in browser tab (no API key). Fire-and-forget asks, a shared relay daemon for concurrent sessions, BibTeX + Crossref citations.

The source code and data link of paper "MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare".

This repository houses machine learning models and pipelines for predicting various diseases, coupled with an integration with a Large Language Model for Diet and Food Recommendation. Each disease prediction task has its dedicated directory structure to maintain organization and modularity.

This is the official repository for our paper "Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning" published in ICRL 2026.