Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.12661 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916703310446592 |
|---|---|
| author | Bansal, Hritik Israel, Daniel Zhao, Siyan Li, Shufan Nguyen, Tung Grover, Aditya |
| author_facet | Bansal, Hritik Israel, Daniel Zhao, Siyan Li, Shufan Nguyen, Tung Grover, Aditya |
| contents | Recent advancements in mixed-modal generative have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and generating multimodal patient reports. However, existing datasets face challenges such as small sizes, limited coverage of biomedical tasks and domains, and a reliance on narrow sources. To address these gaps, we present MedMax, a large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, including interleaved image-text generation, biomedical image captioning and generation, visual chat, and report understanding. These tasks span knowledge across diverse biomedical domains, including radiology and histopathology, grounded in medical papers and YouTube videos. Subsequently, we fine-tune a mixed-modal foundation model on the MedMax dataset, achieving significant performance improvements: a 26% gain over the Chameleon model and an 18.3% improvement over GPT-4o across 12 downstream biomedical visual question-answering tasks. Finally, we introduce a unified evaluation suite for biomedical tasks to guide the development of mixed-modal biomedical AI assistants. The data, model, and code is available at https://mint-medmax.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12661 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants Bansal, Hritik Israel, Daniel Zhao, Siyan Li, Shufan Nguyen, Tung Grover, Aditya Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Recent advancements in mixed-modal generative have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and generating multimodal patient reports. However, existing datasets face challenges such as small sizes, limited coverage of biomedical tasks and domains, and a reliance on narrow sources. To address these gaps, we present MedMax, a large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, including interleaved image-text generation, biomedical image captioning and generation, visual chat, and report understanding. These tasks span knowledge across diverse biomedical domains, including radiology and histopathology, grounded in medical papers and YouTube videos. Subsequently, we fine-tune a mixed-modal foundation model on the MedMax dataset, achieving significant performance improvements: a 26% gain over the Chameleon model and an 18.3% improvement over GPT-4o across 12 downstream biomedical visual question-answering tasks. Finally, we introduce a unified evaluation suite for biomedical tasks to guide the development of mixed-modal biomedical AI assistants. The data, model, and code is available at https://mint-medmax.github.io/. |
| title | MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.12661 |