A Synthetic Data-Driven Radiology Foundation Model for Pan-tumor Clinical Diagnosis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908830451892224 |
|---|---|
| author | Lei, Wenhui Chen, Hanyu Zhang, Zitian Luo, Luyang Xiao, Qiong Gu, Yannian Gao, Peng Jiang, Yankai Wang, Ci Wu, Guangtao Xu, Tongjia Zhang, Yingjie Rajpurkar, Pranav Zhang, Xiaofan Zhang, Shaoting Wang, Zhenning |
| author_facet | Lei, Wenhui Chen, Hanyu Zhang, Zitian Luo, Luyang Xiao, Qiong Gu, Yannian Gao, Peng Jiang, Yankai Wang, Ci Wu, Guangtao Xu, Tongjia Zhang, Yingjie Rajpurkar, Pranav Zhang, Xiaofan Zhang, Shaoting Wang, Zhenning |
| contents | AI-assisted imaging made substantial advances in tumor diagnosis and management. However, a major barrier to developing robust oncology foundation models is the scarcity of large-scale, high-quality annotated datasets, which are limited by privacy restrictions and the high cost of manual labeling. To address this gap, we present PASTA, a pan-tumor radiology foundation model built on PASTA-Gen, a synthetic data framework that generated 30,000 3D CT scans with pixel-level lesion masks and structured reports of tumors across ten organ systems. Leveraging this resource, PASTA achieves state-of-the-art performance on 45 of 46 oncology tasks, including non-contrast CT tumor screening, lesion segmentation, structured reporting, tumor staging, survival prediction, and MRI-modality transfer. To assess clinical applicability, we developed PASTA-AID, a clinical decision support system, and ran a retrospective simulated clinical trial across two scenarios. For pan-tumor screening on plain CT with fixed reading time, PASTA-AID increased radiologists' throughput by 11.1-25.1% and improved sensitivity by 17.0-31.4% and precision by 10.5-24.9%; additionally, in a diagnosis-aid workflow, it reduced segmentation time by up to 78.2% and reporting time by up to 36.5%. Beyond gains in accuracy and efficiency, PASTA-AID narrowed the expertise gap, enabling less-experienced radiologists to approach expert-level performance. Together, this work establishes an end-to-end, synthetic data-driven pipeline spanning data generation, model development, and clinical validation, thereby demonstrating substantial potential for pan-tumor research and clinical translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06171 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Synthetic Data-Driven Radiology Foundation Model for Pan-tumor Clinical Diagnosis Lei, Wenhui Chen, Hanyu Zhang, Zitian Luo, Luyang Xiao, Qiong Gu, Yannian Gao, Peng Jiang, Yankai Wang, Ci Wu, Guangtao Xu, Tongjia Zhang, Yingjie Rajpurkar, Pranav Zhang, Xiaofan Zhang, Shaoting Wang, Zhenning Image and Video Processing Computer Vision and Pattern Recognition AI-assisted imaging made substantial advances in tumor diagnosis and management. However, a major barrier to developing robust oncology foundation models is the scarcity of large-scale, high-quality annotated datasets, which are limited by privacy restrictions and the high cost of manual labeling. To address this gap, we present PASTA, a pan-tumor radiology foundation model built on PASTA-Gen, a synthetic data framework that generated 30,000 3D CT scans with pixel-level lesion masks and structured reports of tumors across ten organ systems. Leveraging this resource, PASTA achieves state-of-the-art performance on 45 of 46 oncology tasks, including non-contrast CT tumor screening, lesion segmentation, structured reporting, tumor staging, survival prediction, and MRI-modality transfer. To assess clinical applicability, we developed PASTA-AID, a clinical decision support system, and ran a retrospective simulated clinical trial across two scenarios. For pan-tumor screening on plain CT with fixed reading time, PASTA-AID increased radiologists' throughput by 11.1-25.1% and improved sensitivity by 17.0-31.4% and precision by 10.5-24.9%; additionally, in a diagnosis-aid workflow, it reduced segmentation time by up to 78.2% and reporting time by up to 36.5%. Beyond gains in accuracy and efficiency, PASTA-AID narrowed the expertise gap, enabling less-experienced radiologists to approach expert-level performance. Together, this work establishes an end-to-end, synthetic data-driven pipeline spanning data generation, model development, and clinical validation, thereby demonstrating substantial potential for pan-tumor research and clinical translation. |
| title | A Synthetic Data-Driven Radiology Foundation Model for Pan-tumor Clinical Diagnosis |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.06171 |