Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images
Abstract Advances in computational algorithms and tools have made the prediction of cancer patient outcomes using computational pathology feasible. However, predicting clinical outcomes from pre-treatment histopathologic images remains a challenging task, limited by the poor understanding of tumor i...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-023-00352-5 |
| _version_ | 1797641660354527232 |
|---|---|
| author | Zhi Huang Wei Shao Zhi Han Ahmad Mahmoud Alkashash Carlo De la Sancha Anil V. Parwani Hiroaki Nitta Yanjun Hou Tongxin Wang Paul Salama Maher Rizkalla Jie Zhang Kun Huang Zaibo Li |
| author_facet | Zhi Huang Wei Shao Zhi Han Ahmad Mahmoud Alkashash Carlo De la Sancha Anil V. Parwani Hiroaki Nitta Yanjun Hou Tongxin Wang Paul Salama Maher Rizkalla Jie Zhang Kun Huang Zaibo Li |
| author_sort | Zhi Huang |
| collection | DOAJ |
| description | Abstract Advances in computational algorithms and tools have made the prediction of cancer patient outcomes using computational pathology feasible. However, predicting clinical outcomes from pre-treatment histopathologic images remains a challenging task, limited by the poor understanding of tumor immune micro-environments. In this study, an automatic, accurate, comprehensive, interpretable, and reproducible whole slide image (WSI) feature extraction pipeline known as, IMage-based Pathological REgistration and Segmentation Statistics (IMPRESS), is described. We used both H&E and multiplex IHC (PD-L1, CD8+, and CD163+) images, investigated whether artificial intelligence (AI)-based algorithms using automatic feature extraction methods can predict neoadjuvant chemotherapy (NAC) outcomes in HER2-positive (HER2+) and triple-negative breast cancer (TNBC) patients. Features are derived from tumor immune micro-environment and clinical data and used to train machine learning models to accurately predict the response to NAC in breast cancer patients (HER2+ AUC = 0.8975; TNBC AUC = 0.7674). The results demonstrate that this method outperforms the results trained from features that were manually generated by pathologists. The developed image features and algorithms were further externally validated by independent cohorts, yielding encouraging results, especially for the HER2+ subtype. |
| first_indexed | 2024-03-11T13:48:53Z |
| format | Article |
| id | doaj.art-1509f4f2194b4f669a875e33a5304cf6 |
| institution | Directory Open Access Journal |
| issn | 2397-768X |
| language | English |
| last_indexed | 2024-03-11T13:48:53Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj.art-1509f4f2194b4f669a875e33a5304cf62023-11-02T09:30:08ZengNature Portfolionpj Precision Oncology2397-768X2023-01-017111510.1038/s41698-023-00352-5Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic imagesZhi Huang0Wei Shao1Zhi Han2Ahmad Mahmoud Alkashash3Carlo De la Sancha4Anil V. Parwani5Hiroaki Nitta6Yanjun Hou7Tongxin Wang8Paul Salama9Maher Rizkalla10Jie Zhang11Kun Huang12Zaibo Li13School of Electrical and Computer Engineering, Purdue UniversityDepartment of Medicine, Indiana University School of MedicineDepartment of Medicine, Indiana University School of MedicineDepartment of Pathology, Indiana University School of MedicineDepartment of Pathology, Indiana University School of MedicineDepartment of Pathology, The Ohio State University Wexner Medical CenterRoche Tissue DiagnosticsUniversity Hospitals Cleveland Medical Center, Case Western Reserve UniversityDepartment of Computer Science, Indiana University BloomingtonDepartment of Electrical and Computer Engineering, Indiana University – Purdue University IndianapolisDepartment of Electrical and Computer Engineering, Indiana University – Purdue University IndianapolisDepartment of Medical and Molecular Genetics, Indiana University School of MedicineDepartment of Medicine, Indiana University School of MedicineDepartment of Pathology, The Ohio State University Wexner Medical CenterAbstract Advances in computational algorithms and tools have made the prediction of cancer patient outcomes using computational pathology feasible. However, predicting clinical outcomes from pre-treatment histopathologic images remains a challenging task, limited by the poor understanding of tumor immune micro-environments. In this study, an automatic, accurate, comprehensive, interpretable, and reproducible whole slide image (WSI) feature extraction pipeline known as, IMage-based Pathological REgistration and Segmentation Statistics (IMPRESS), is described. We used both H&E and multiplex IHC (PD-L1, CD8+, and CD163+) images, investigated whether artificial intelligence (AI)-based algorithms using automatic feature extraction methods can predict neoadjuvant chemotherapy (NAC) outcomes in HER2-positive (HER2+) and triple-negative breast cancer (TNBC) patients. Features are derived from tumor immune micro-environment and clinical data and used to train machine learning models to accurately predict the response to NAC in breast cancer patients (HER2+ AUC = 0.8975; TNBC AUC = 0.7674). The results demonstrate that this method outperforms the results trained from features that were manually generated by pathologists. The developed image features and algorithms were further externally validated by independent cohorts, yielding encouraging results, especially for the HER2+ subtype.https://doi.org/10.1038/s41698-023-00352-5 |
| spellingShingle | Zhi Huang Wei Shao Zhi Han Ahmad Mahmoud Alkashash Carlo De la Sancha Anil V. Parwani Hiroaki Nitta Yanjun Hou Tongxin Wang Paul Salama Maher Rizkalla Jie Zhang Kun Huang Zaibo Li Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images npj Precision Oncology |
| title | Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images |
| title_full | Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images |
| title_fullStr | Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images |
| title_full_unstemmed | Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images |
| title_short | Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images |
| title_sort | artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi stain histopathologic images |
| url | https://doi.org/10.1038/s41698-023-00352-5 |
| work_keys_str_mv | AT zhihuang artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT weishao artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT zhihan artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT ahmadmahmoudalkashash artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT carlodelasancha artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT anilvparwani artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT hiroakinitta artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT yanjunhou artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT tongxinwang artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT paulsalama artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT maherrizkalla artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT jiezhang artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT kunhuang artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages AT zaiboli artificialintelligencerevealsfeaturesassociatedwithbreastcancerneoadjuvantchemotherapyresponsesfrommultistainhistopathologicimages |