Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2305.17100 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929454515748864 |
|---|---|
| author | Zhang, Kai Zhou, Rong Adhikarla, Eashan Yan, Zhiling Liu, Yixin Yu, Jun Liu, Zhengliang Chen, Xun Davison, Brian D. Ren, Hui Huang, Jing Chen, Chen Zhou, Yuyin Fu, Sunyang Liu, Wei Liu, Tianming Li, Xiang Chen, Yong He, Lifang Zou, James Li, Quanzheng Liu, Hongfang Sun, Lichao |
| author_facet | Zhang, Kai Zhou, Rong Adhikarla, Eashan Yan, Zhiling Liu, Yixin Yu, Jun Liu, Zhengliang Chen, Xun Davison, Brian D. Ren, Hui Huang, Jing Chen, Chen Zhou, Yuyin Fu, Sunyang Liu, Wei Liu, Tianming Li, Xiang Chen, Yong He, Lifang Zou, James Li, Quanzheng Liu, Hongfang Sun, Lichao |
| contents | Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners, and patients. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation, and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_17100 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks Zhang, Kai Zhou, Rong Adhikarla, Eashan Yan, Zhiling Liu, Yixin Yu, Jun Liu, Zhengliang Chen, Xun Davison, Brian D. Ren, Hui Huang, Jing Chen, Chen Zhou, Yuyin Fu, Sunyang Liu, Wei Liu, Tianming Li, Xiang Chen, Yong He, Lifang Zou, James Li, Quanzheng Liu, Hongfang Sun, Lichao Computation and Language Artificial Intelligence Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners, and patients. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation, and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency. |
| title | BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2305.17100 |