An end-to-end multifunctional AI platform for intraoperative diagnosis
Abstract Intraoperative frozen section diagnosis provides essential, real-time histological insights to guide surgical decisions. However, the quality of these time-sensitive sections is often suboptimal, posing significant diagnostic challenges for pathologists. To address these limitations, we uti...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01808-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234407049658368 |
|---|---|
| author | Xueyi Zheng Ke Zheng Yongqin Wen Jiajia Meng Xinke Zhang Xiaobo Wen Zihan Zhao Chengyou Zheng Xiaoxia Cai Jiliang Lin Jiewei Chen Jinling Duan Liwen Jiang Wei Yuan Xiaomei Li Dan Xie Yubo Cai Jiangyu Zhang Muyan Cai |
| author_facet | Xueyi Zheng Ke Zheng Yongqin Wen Jiajia Meng Xinke Zhang Xiaobo Wen Zihan Zhao Chengyou Zheng Xiaoxia Cai Jiliang Lin Jiewei Chen Jinling Duan Liwen Jiang Wei Yuan Xiaomei Li Dan Xie Yubo Cai Jiangyu Zhang Muyan Cai |
| author_sort | Xueyi Zheng |
| collection | DOAJ |
| description | Abstract Intraoperative frozen section diagnosis provides essential, real-time histological insights to guide surgical decisions. However, the quality of these time-sensitive sections is often suboptimal, posing significant diagnostic challenges for pathologists. To address these limitations, we utilized over 6700 whole slide images to develop GAS, a comprehensive platform comprising three modules: Generation, Assessment, and Support modules. The Generation module, based on a GAN-driven multimodal network guided by FFPE-style text descriptions, demonstrated effective enhancement of frozen section quality across various organs. The Assessment module, which fine-tuned quality control models using pathological foundation models, showed substantial improvements in microstructural quality for the generated images. Validated through a prospective study (ChiCTR2300076555) on the human–AI collaboration software, the Support module demonstrated that GAS significantly boosted diagnostic confidence for pathologists. In summary, this study highlights the clinical utility of the GAS platform in intraoperative diagnosis and establishes a new paradigm for integrating end-to-end AI solutions into clinical workflows. |
| format | Article |
| id | doaj-art-a46b947fd13c40aaa8a5224ac79368d1 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-a46b947fd13c40aaa8a5224ac79368d12025-08-20T04:03:11ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111210.1038/s41746-025-01808-7An end-to-end multifunctional AI platform for intraoperative diagnosisXueyi Zheng0Ke Zheng1Yongqin Wen2Jiajia Meng3Xinke Zhang4Xiaobo Wen5Zihan Zhao6Chengyou Zheng7Xiaoxia Cai8Jiliang Lin9Jiewei Chen10Jinling Duan11Liwen Jiang12Wei Yuan13Xiaomei Li14Dan Xie15Yubo Cai16Jiangyu Zhang17Muyan Cai18Department of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, The Tenth Affiliated Hospital, Southern Medical University, Dongguan People’s HospitalDepartment of Pathology, Huizhou Central People’s HospitalDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterState Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterState Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, Affiliated Cancer Hospital & Institute of Guangzhou Medical UniversityDepartment of Pathology, The Tenth Affiliated Hospital, Southern Medical University, Dongguan People’s HospitalDepartment of Pathology, Shenzhen People’s HospitalDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterDepartment of Pathology, Jiangmen Central HospitalDepartment of Pathology, Affiliated Cancer Hospital & Institute of Guangzhou Medical UniversityDepartment of Pathology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer CenterAbstract Intraoperative frozen section diagnosis provides essential, real-time histological insights to guide surgical decisions. However, the quality of these time-sensitive sections is often suboptimal, posing significant diagnostic challenges for pathologists. To address these limitations, we utilized over 6700 whole slide images to develop GAS, a comprehensive platform comprising three modules: Generation, Assessment, and Support modules. The Generation module, based on a GAN-driven multimodal network guided by FFPE-style text descriptions, demonstrated effective enhancement of frozen section quality across various organs. The Assessment module, which fine-tuned quality control models using pathological foundation models, showed substantial improvements in microstructural quality for the generated images. Validated through a prospective study (ChiCTR2300076555) on the human–AI collaboration software, the Support module demonstrated that GAS significantly boosted diagnostic confidence for pathologists. In summary, this study highlights the clinical utility of the GAS platform in intraoperative diagnosis and establishes a new paradigm for integrating end-to-end AI solutions into clinical workflows.https://doi.org/10.1038/s41746-025-01808-7 |
| spellingShingle | Xueyi Zheng Ke Zheng Yongqin Wen Jiajia Meng Xinke Zhang Xiaobo Wen Zihan Zhao Chengyou Zheng Xiaoxia Cai Jiliang Lin Jiewei Chen Jinling Duan Liwen Jiang Wei Yuan Xiaomei Li Dan Xie Yubo Cai Jiangyu Zhang Muyan Cai An end-to-end multifunctional AI platform for intraoperative diagnosis npj Digital Medicine |
| title | An end-to-end multifunctional AI platform for intraoperative diagnosis |
| title_full | An end-to-end multifunctional AI platform for intraoperative diagnosis |
| title_fullStr | An end-to-end multifunctional AI platform for intraoperative diagnosis |
| title_full_unstemmed | An end-to-end multifunctional AI platform for intraoperative diagnosis |
| title_short | An end-to-end multifunctional AI platform for intraoperative diagnosis |
| title_sort | end to end multifunctional ai platform for intraoperative diagnosis |
| url | https://doi.org/10.1038/s41746-025-01808-7 |
| work_keys_str_mv | AT xueyizheng anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT kezheng anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT yongqinwen anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT jiajiameng anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT xinkezhang anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT xiaobowen anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT zihanzhao anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT chengyouzheng anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT xiaoxiacai anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT jilianglin anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT jieweichen anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT jinlingduan anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT liwenjiang anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT weiyuan anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT xiaomeili anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT danxie anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT yubocai anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT jiangyuzhang anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT muyancai anendtoendmultifunctionalaiplatformforintraoperativediagnosis AT xueyizheng endtoendmultifunctionalaiplatformforintraoperativediagnosis AT kezheng endtoendmultifunctionalaiplatformforintraoperativediagnosis AT yongqinwen endtoendmultifunctionalaiplatformforintraoperativediagnosis AT jiajiameng endtoendmultifunctionalaiplatformforintraoperativediagnosis AT xinkezhang endtoendmultifunctionalaiplatformforintraoperativediagnosis AT xiaobowen endtoendmultifunctionalaiplatformforintraoperativediagnosis AT zihanzhao endtoendmultifunctionalaiplatformforintraoperativediagnosis AT chengyouzheng endtoendmultifunctionalaiplatformforintraoperativediagnosis AT xiaoxiacai endtoendmultifunctionalaiplatformforintraoperativediagnosis AT jilianglin endtoendmultifunctionalaiplatformforintraoperativediagnosis AT jieweichen endtoendmultifunctionalaiplatformforintraoperativediagnosis AT jinlingduan endtoendmultifunctionalaiplatformforintraoperativediagnosis AT liwenjiang endtoendmultifunctionalaiplatformforintraoperativediagnosis AT weiyuan endtoendmultifunctionalaiplatformforintraoperativediagnosis AT xiaomeili endtoendmultifunctionalaiplatformforintraoperativediagnosis AT danxie endtoendmultifunctionalaiplatformforintraoperativediagnosis AT yubocai endtoendmultifunctionalaiplatformforintraoperativediagnosis AT jiangyuzhang endtoendmultifunctionalaiplatformforintraoperativediagnosis AT muyancai endtoendmultifunctionalaiplatformforintraoperativediagnosis |