Abstract
Residual cancer burden (RCB) has been proposed to measure the postneoadjuvant breast cancer response. In the workflow of RCB assessment, estimation of cancer cellularity is a critical task, which is conventionally achieved by manually reviewing the hematoxylin and eosin- (H&E-) stained microscopic slides of cancer sections. In this work, we develop an automatic and direct method to estimate cellularity from histopathological image patches using deep feature representation, tree boosting, and support vector machine (SVM), avoiding the segmentation and classification of nuclei. Using a training set of 2394 patches and a test set of 185 patches, the estimations by our method show strong correlation to those by the human pathologists in terms of intraclass correlation (ICC) (0.94 with 95% CI of (0.93, 0.96)), Kendall's tau (0.83 with 95% CI of (0.79, 0.86)), and the prediction probability (0.93 with 95% CI of (0.91, 0.94)), compared to two other methods (ICC of 0.74 with 95% CI of (0.70, 0.77) and 0.83 with 95% CI of (0.79, 0.86)). Our method improves the accuracy and does not rely on annotations of individual nucleus.
Highlights
Breast cancer is the most common malignant cancer occurring in women [1]
The predictive potential of Pathologic complete response (pCR) on longterm prognosis is impaired by its blurry definition [4] and the roughness of dichotomizing the tumor response [5]
Materials. e data used in our research are acquired from the SPIE-AAPM-NCI BreastPathQ Challenge [34] and are from the same batch as those in [22, 23]. e dataset consists of 69 hematoxylin and eosin (H&E) stained whole slide images (WSIs) collected from the resection specimens of 37 post-neoadjuvant therapy (NAT) patients with invasive residual breast cancer. e specimens are processed following regular histopathological protocols, and the WSIs are scanned at 20x magnification (0.5 μm/pixel). e tumor beds of these slides are roughly segmented into 4 regions (normal (0), low cellularity (1–30%), medium cellularity (31–70%), and high cellularity (71–100%)), and approximately equal numbers of patches are selected from each of them
Summary
Breast cancer is the most common malignant cancer occurring in women [1]. Preoperative neoadjuvant therapy (NAT) [2] can reduce the breast tumor size, so as to facilitate the complete resection of tumor and the performance of breast-conserving surgery instead of mastectomy for patients with large tumor. Unlike pCR, the residual cancer burden (RCB) index is improved by measuring both in situ and invasive cancer in residual tumor and the metastasis through lymph nodes [5]. RCB is a new staging system basically devised to continuously quantify the residual breast cancer that ranges from complete response to chemotherapy resistance. It is standardized by defining a pipeline of specimen collection and tumor bed identification and has proved to be a significant indicator of distant relapse-free survival of breast cancer [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Computational and Mathematical Methods in Medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
