Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study
Introduction: Early predictive pathological complete response (pCR) is beneficial for optimizing neoadjuvant chemotherapy (NAC) strategies for breast cancer. The hematoxylin and eosin (HE)-stained slices of biopsy tissues contain a large amount of information on tumor epithelial cells and stromal. T...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-01-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2024.1279982/full |
| _version_ | 1827368390138789888 |
|---|---|
| author | Huancheng Zeng Siqi Qiu Siqi Qiu Shuxin Zhuang Xiaolong Wei Jundong Wu Ranze Zhang Kai Chen Zhiyong Wu Zhemin Zhuang |
| author_facet | Huancheng Zeng Siqi Qiu Siqi Qiu Shuxin Zhuang Xiaolong Wei Jundong Wu Ranze Zhang Kai Chen Zhiyong Wu Zhemin Zhuang |
| author_sort | Huancheng Zeng |
| collection | DOAJ |
| description | Introduction: Early predictive pathological complete response (pCR) is beneficial for optimizing neoadjuvant chemotherapy (NAC) strategies for breast cancer. The hematoxylin and eosin (HE)-stained slices of biopsy tissues contain a large amount of information on tumor epithelial cells and stromal. The fusion of pathological image features and clinicopathological features is expected to build a model to predict pCR of NAC in breast cancer.Methods: We retrospectively collected a total of 440 breast cancer patients from three hospitals who underwent NAC. HE-stained slices of biopsy tissues were scanned to form whole-slide images (WSIs), and pathological images of representative regions of interest (ROI) of each WSI were selected at different magnifications. Based on several different deep learning models, we propose a novel feature extraction method on pathological images with different magnifications. Further, fused with clinicopathological features, a multimodal breast cancer NAC pCR prediction model based on a support vector machine (SVM) classifier was developed and validated with two additional validation cohorts (VCs).Results: Through experimental validation of several different deep learning models, we found that the breast cancer pCR prediction model based on the SVM classifier, which uses the VGG16 model for feature extraction of pathological images at ×20 magnification, has the best prediction efficacy. The area under the curve (AUC) of deep learning pathological model (DPM) were 0.79, 0.73, and 0.71 for TC, VC1, and VC2, respectively, all of which exceeded 0.70. The AUCs of clinical model (CM), a clinical prediction model established by using clinicopathological features, were 0.79 for TC, 0.73 for VC1, and 0.71 for VC2, respectively. The multimodal deep learning clinicopathological model (DPCM) established by fusing pathological images and clinicopathological features improved the AUC of TC from 0.79 to 0.84. The AUC of VC2 improved from 0.71 to 0.78.Conclusion: Our study reveals that pathological images of HE-stained slices of pre-NAC biopsy tissues can be used to build a pCR prediction model. Combining pathological images and clinicopathological features can further enhance the predictive efficacy of the model. |
| first_indexed | 2024-03-08T09:30:45Z |
| format | Article |
| id | doaj.art-35aff297f51641eeae62a831b88498d7 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-03-08T09:30:45Z |
| publishDate | 2024-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-35aff297f51641eeae62a831b88498d72024-01-31T04:24:54ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2024-01-011510.3389/fphys.2024.12799821279982Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter studyHuancheng Zeng0Siqi Qiu1Siqi Qiu2Shuxin Zhuang3Xiaolong Wei4Jundong Wu5Ranze Zhang6Kai Chen7Zhiyong Wu8Zhemin Zhuang9The Breast Center, Cancer Hospital of Shantou University Medical College, Shantou, ChinaDiagnosis and Treatment Center of Breast Diseases, Shantou Central Hospital, Shantou, ChinaClinical Research Center, Shantou Central Hospital, Shantou, ChinaSchool of Biomedical Engineering, Sun Yat-sen University, Shenzhen, ChinaThe Pathology Department, Cancer Hospital of Shantou University Medical College, Shantou, ChinaThe Breast Center, Cancer Hospital of Shantou University Medical College, Shantou, ChinaBreast Tumor Center, Sun Yat-Sen Memorial Hospital, Guangzhou, ChinaBreast Tumor Center, Sun Yat-Sen Memorial Hospital, Guangzhou, ChinaDiagnosis and Treatment Center of Breast Diseases, Shantou Central Hospital, Shantou, ChinaEngineering College, Shantou University, Shantou, ChinaIntroduction: Early predictive pathological complete response (pCR) is beneficial for optimizing neoadjuvant chemotherapy (NAC) strategies for breast cancer. The hematoxylin and eosin (HE)-stained slices of biopsy tissues contain a large amount of information on tumor epithelial cells and stromal. The fusion of pathological image features and clinicopathological features is expected to build a model to predict pCR of NAC in breast cancer.Methods: We retrospectively collected a total of 440 breast cancer patients from three hospitals who underwent NAC. HE-stained slices of biopsy tissues were scanned to form whole-slide images (WSIs), and pathological images of representative regions of interest (ROI) of each WSI were selected at different magnifications. Based on several different deep learning models, we propose a novel feature extraction method on pathological images with different magnifications. Further, fused with clinicopathological features, a multimodal breast cancer NAC pCR prediction model based on a support vector machine (SVM) classifier was developed and validated with two additional validation cohorts (VCs).Results: Through experimental validation of several different deep learning models, we found that the breast cancer pCR prediction model based on the SVM classifier, which uses the VGG16 model for feature extraction of pathological images at ×20 magnification, has the best prediction efficacy. The area under the curve (AUC) of deep learning pathological model (DPM) were 0.79, 0.73, and 0.71 for TC, VC1, and VC2, respectively, all of which exceeded 0.70. The AUCs of clinical model (CM), a clinical prediction model established by using clinicopathological features, were 0.79 for TC, 0.73 for VC1, and 0.71 for VC2, respectively. The multimodal deep learning clinicopathological model (DPCM) established by fusing pathological images and clinicopathological features improved the AUC of TC from 0.79 to 0.84. The AUC of VC2 improved from 0.71 to 0.78.Conclusion: Our study reveals that pathological images of HE-stained slices of pre-NAC biopsy tissues can be used to build a pCR prediction model. Combining pathological images and clinicopathological features can further enhance the predictive efficacy of the model.https://www.frontiersin.org/articles/10.3389/fphys.2024.1279982/fullbreast cancerdeep learningneoadjuvant chemotherapypathological complete responsepathological images |
| spellingShingle | Huancheng Zeng Siqi Qiu Siqi Qiu Shuxin Zhuang Xiaolong Wei Jundong Wu Ranze Zhang Kai Chen Zhiyong Wu Zhemin Zhuang Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study Frontiers in Physiology breast cancer deep learning neoadjuvant chemotherapy pathological complete response pathological images |
| title | Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study |
| title_full | Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study |
| title_fullStr | Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study |
| title_full_unstemmed | Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study |
| title_short | Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study |
| title_sort | deep learning based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images a multicenter study |
| topic | breast cancer deep learning neoadjuvant chemotherapy pathological complete response pathological images |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2024.1279982/full |
| work_keys_str_mv | AT huanchengzeng deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT siqiqiu deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT siqiqiu deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT shuxinzhuang deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT xiaolongwei deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT jundongwu deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT ranzezhang deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT kaichen deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT zhiyongwu deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy AT zheminzhuang deeplearningbasedpredictivemodelforpathologicalcompleteresponsetoneoadjuvantchemotherapyinbreastcancerfrombiopsypathologicalimagesamulticenterstudy |