DeepTumorVQA v2

DeepTumorVQA v2 3D abdominal-CT diagnostic Visual Question Answering benchmark with 42 clinical subtypes and 438K total QA pairs (10K curated benchmark + 428K training pool). Includes pre-extracted 2D and video modalities, 20K agent training trajectories with tool-use traces, and a paper-locked leaderboard. Resources 📄 Paper (arXiv) 💻 Code (GitHub) 🤗 Dataset (this… See the full description on the dataset page: 2.0.

Source: Hugging Face Hub (tumor-vqa/DeepTumorVQA_2.0). Metadata imported from the dataset’s Hub tags.