Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses
Abstract Treatment decisions for an incidental renal mass are mostly made with pathologic uncertainty. Improving the diagnosis of benign renal masses and distinguishing aggressive cancers from indolent ones is key to better treatment selection. We analyze 13261 pre-operative computed computed tomogr...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-56784-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861833049571328 |
|---|---|
| author | Ying Xiong Linpeng Yao Jinglai Lin Jiaxi Yao Qi Bai Yuan Huang Xue Zhang Risheng Huang Run Wang Kang Wang Yu Qi Pingyi Zhu Haoran Wang Li Liu Jianjun Zhou Jianming Guo Feng Chen Chenchen Dai Shuo Wang |
| author_facet | Ying Xiong Linpeng Yao Jinglai Lin Jiaxi Yao Qi Bai Yuan Huang Xue Zhang Risheng Huang Run Wang Kang Wang Yu Qi Pingyi Zhu Haoran Wang Li Liu Jianjun Zhou Jianming Guo Feng Chen Chenchen Dai Shuo Wang |
| author_sort | Ying Xiong |
| collection | DOAJ |
| description | Abstract Treatment decisions for an incidental renal mass are mostly made with pathologic uncertainty. Improving the diagnosis of benign renal masses and distinguishing aggressive cancers from indolent ones is key to better treatment selection. We analyze 13261 pre-operative computed computed tomography (CT) volumes of 4557 patients. Two multi-phase convolutional neural networks are developed to predict the malignancy and aggressiveness of renal masses. The first diagnostic model designed to predict the malignancy of renal masses achieves area under the curve (AUC) of 0.871 in the prospective test set. This model surpasses the average performance of seven seasoned radiologists. The second diagnostic model differentiating aggressive from indolent tumors has AUC of 0.783 in the prospective test set. Both models outperform corresponding radiomics models and the nephrometry score nomogram. Here we show that the deep learning models can non-invasively predict the likelihood of malignant and aggressive pathology of a renal mass based on preoperative multi-phase CT images. |
| format | Article |
| id | doaj-art-a6d8267454c5467cae43dee99f793d7a |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-a6d8267454c5467cae43dee99f793d7a2025-02-09T12:45:17ZengNature PortfolioNature Communications2041-17232025-02-0116111410.1038/s41467-025-56784-zArtificial intelligence links CT images to pathologic features and survival outcomes of renal massesYing Xiong0Linpeng Yao1Jinglai Lin2Jiaxi Yao3Qi Bai4Yuan Huang5Xue Zhang6Risheng Huang7Run Wang8Kang Wang9Yu Qi10Pingyi Zhu11Haoran Wang12Li Liu13Jianjun Zhou14Jianming Guo15Feng Chen16Chenchen Dai17Shuo Wang18Department of Urology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, The First Affiliated Hospital, Zhejiang University School of MedicineDepartment of Urology, Zhongshan Hospital (Xiamen), Fudan UniversityDepartment of Urology, Zhangye People’s Hospital affiliated to Hexi UniversityDepartment of Urology, Zhongshan Hospital, Fudan UniversityDepartment of Applied Mathematics and Theoretical Physics, Centre for Mathematical Sciences, University of CambridgeDepartment of Radiology, the First People’s Hospital of LianyungangDepartment of Imaging, Quanzhou First Hospital, Fujian Medical UniversityDepartment of Pathology, Sir Run Run Shaw HospitalDigital Medical Research Center, School of Basic Medical Sciences, Fudan UniversityDepartment of Urology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, Zhongshan Hospital, Fudan UniversityDigital Medical Research Center, School of Basic Medical Sciences, Fudan UniversityDepartment of Urology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, Zhongshan Hospital (Xiamen), Fudan UniversityDepartment of Urology, Zhongshan Hospital, Fudan UniversityDepartment of Radiology, The First Affiliated Hospital, Zhejiang University School of MedicineDepartment of Radiology, Zhongshan Hospital, Fudan UniversityDigital Medical Research Center, School of Basic Medical Sciences, Fudan UniversityAbstract Treatment decisions for an incidental renal mass are mostly made with pathologic uncertainty. Improving the diagnosis of benign renal masses and distinguishing aggressive cancers from indolent ones is key to better treatment selection. We analyze 13261 pre-operative computed computed tomography (CT) volumes of 4557 patients. Two multi-phase convolutional neural networks are developed to predict the malignancy and aggressiveness of renal masses. The first diagnostic model designed to predict the malignancy of renal masses achieves area under the curve (AUC) of 0.871 in the prospective test set. This model surpasses the average performance of seven seasoned radiologists. The second diagnostic model differentiating aggressive from indolent tumors has AUC of 0.783 in the prospective test set. Both models outperform corresponding radiomics models and the nephrometry score nomogram. Here we show that the deep learning models can non-invasively predict the likelihood of malignant and aggressive pathology of a renal mass based on preoperative multi-phase CT images.https://doi.org/10.1038/s41467-025-56784-z |
| spellingShingle | Ying Xiong Linpeng Yao Jinglai Lin Jiaxi Yao Qi Bai Yuan Huang Xue Zhang Risheng Huang Run Wang Kang Wang Yu Qi Pingyi Zhu Haoran Wang Li Liu Jianjun Zhou Jianming Guo Feng Chen Chenchen Dai Shuo Wang Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses Nature Communications |
| title | Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses |
| title_full | Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses |
| title_fullStr | Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses |
| title_full_unstemmed | Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses |
| title_short | Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses |
| title_sort | artificial intelligence links ct images to pathologic features and survival outcomes of renal masses |
| url | https://doi.org/10.1038/s41467-025-56784-z |
| work_keys_str_mv | AT yingxiong artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT linpengyao artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT jinglailin artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT jiaxiyao artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT qibai artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT yuanhuang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT xuezhang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT rishenghuang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT runwang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT kangwang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT yuqi artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT pingyizhu artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT haoranwang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT liliu artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT jianjunzhou artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT jianmingguo artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT fengchen artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT chenchendai artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses AT shuowang artificialintelligencelinksctimagestopathologicfeaturesandsurvivaloutcomesofrenalmasses |