Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images
Abstract In breast cancer management, predicting axillary lymph node (ALN) metastasis using whole-slide images (WSIs) of primary tumor biopsies is a challenging and underexplored task for pathologists. We developed METACANS, an multimodal artificial intelligence (AI) model that integrates WSIs with...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-025-00914-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850207330461810688 |
|---|---|
| author | Doohyun Park Yong-Moon Lee Taejoon Eo Hee Jung An Haeyoun Kang Eunhyang Park Yoon Jin Cha Heejung Park Dohee Kwon Sun Young Kwon Hye-Ra Jung Su-Jin Shin Hyunjin Park Yangkyu Lee Sanghui Park Ji Min Kim Sung-Eun Choi Nam Hoon Cho Dosik Hwang |
| author_facet | Doohyun Park Yong-Moon Lee Taejoon Eo Hee Jung An Haeyoun Kang Eunhyang Park Yoon Jin Cha Heejung Park Dohee Kwon Sun Young Kwon Hye-Ra Jung Su-Jin Shin Hyunjin Park Yangkyu Lee Sanghui Park Ji Min Kim Sung-Eun Choi Nam Hoon Cho Dosik Hwang |
| author_sort | Doohyun Park |
| collection | DOAJ |
| description | Abstract In breast cancer management, predicting axillary lymph node (ALN) metastasis using whole-slide images (WSIs) of primary tumor biopsies is a challenging and underexplored task for pathologists. We developed METACANS, an multimodal artificial intelligence (AI) model that integrates WSIs with clinicopathological features to predict ALN metastasis. METACANS was trained on 1991 cases and externally validated across five cohorts with a total of 2166 cases. Across all validation cohorts, METACANS achieved an area under the curve (AUC) of 0.733 (95% CI, 0.711–0.755), with an overall negative predictive value of 0.846, sensitivity of 0.820, specificity of 0.504, and balanced accuracy of 0.662. Without additional annotations, METACANS identified pathological imaging patterns linked to metastatic status, such as micropapillary growth, infiltrative patterns, and necrosis. While its predictive performance may not yet support immediate clinical application, METACANS addresses the task of predicting ALN metastasis using WSIs and clinicopathological features, and demonstrates the feasibility of multimodal AI approaches for preoperative axillary staging in breast cancer. |
| format | Article |
| id | doaj-art-c6179b16f4fb4cb7828ae6288474a086 |
| institution | OA Journals |
| issn | 2397-768X |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-c6179b16f4fb4cb7828ae6288474a0862025-08-20T02:10:33ZengNature Portfolionpj Precision Oncology2397-768X2025-05-019111310.1038/s41698-025-00914-9Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide imagesDoohyun Park0Yong-Moon Lee1Taejoon Eo2Hee Jung An3Haeyoun Kang4Eunhyang Park5Yoon Jin Cha6Heejung Park7Dohee Kwon8Sun Young Kwon9Hye-Ra Jung10Su-Jin Shin11Hyunjin Park12Yangkyu Lee13Sanghui Park14Ji Min Kim15Sung-Eun Choi16Nam Hoon Cho17Dosik Hwang18School of Electrical and Electronic Engineering, Yonsei UniversityDepartment of Pathology, Dankook University College of MedicineSchool of Electrical and Electronic Engineering, Yonsei UniversityDepartment of Pathology, CHA University, CHA Bundang Medical CenterDepartment of Pathology, CHA University, CHA Bundang Medical CenterDepartment of Pathology, Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Keimyung University School of Medicine, Dongsan HospitalDepartment of Pathology, Keimyung University School of Medicine, Dongsan HospitalDepartment of Pathology, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Gangnam Severance Hospital, Yonsei University College of MedicineDepartment of Pathology, Ewha Womans University College of MedicineDepartment of Pathology, Ewha Womans University College of MedicineDepartment of Pathology, CHA Bundang Medical Center, CHA University School of MedicineDepartment of Pathology, Yonsei University College of MedicineSchool of Electrical and Electronic Engineering, Yonsei UniversityAbstract In breast cancer management, predicting axillary lymph node (ALN) metastasis using whole-slide images (WSIs) of primary tumor biopsies is a challenging and underexplored task for pathologists. We developed METACANS, an multimodal artificial intelligence (AI) model that integrates WSIs with clinicopathological features to predict ALN metastasis. METACANS was trained on 1991 cases and externally validated across five cohorts with a total of 2166 cases. Across all validation cohorts, METACANS achieved an area under the curve (AUC) of 0.733 (95% CI, 0.711–0.755), with an overall negative predictive value of 0.846, sensitivity of 0.820, specificity of 0.504, and balanced accuracy of 0.662. Without additional annotations, METACANS identified pathological imaging patterns linked to metastatic status, such as micropapillary growth, infiltrative patterns, and necrosis. While its predictive performance may not yet support immediate clinical application, METACANS addresses the task of predicting ALN metastasis using WSIs and clinicopathological features, and demonstrates the feasibility of multimodal AI approaches for preoperative axillary staging in breast cancer.https://doi.org/10.1038/s41698-025-00914-9 |
| spellingShingle | Doohyun Park Yong-Moon Lee Taejoon Eo Hee Jung An Haeyoun Kang Eunhyang Park Yoon Jin Cha Heejung Park Dohee Kwon Sun Young Kwon Hye-Ra Jung Su-Jin Shin Hyunjin Park Yangkyu Lee Sanghui Park Ji Min Kim Sung-Eun Choi Nam Hoon Cho Dosik Hwang Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images npj Precision Oncology |
| title | Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images |
| title_full | Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images |
| title_fullStr | Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images |
| title_full_unstemmed | Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images |
| title_short | Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images |
| title_sort | multimodal ai model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images |
| url | https://doi.org/10.1038/s41698-025-00914-9 |
| work_keys_str_mv | AT doohyunpark multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT yongmoonlee multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT taejooneo multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT heejungan multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT haeyounkang multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT eunhyangpark multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT yoonjincha multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT heejungpark multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT doheekwon multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT sunyoungkwon multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT hyerajung multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT sujinshin multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT hyunjinpark multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT yangkyulee multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT sanghuipark multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT jiminkim multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT sungeunchoi multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT namhooncho multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages AT dosikhwang multimodalaimodelforpreoperativepredictionofaxillarylymphnodemetastasisinbreastcancerusingwholeslideimages |