Deep Learning Provides Rapid Screen for Breast Cancer Metastasis with Sentinel Lymph Nodes

Deep learning has been shown to be useful to detect breast cancer metastases by analyzing whole slide images (WSI) of sentinel lymph nodes (SLNs); however, it requires extensive scanning and analysis of all the lymph node slides for each case. Our deep learning study focuses on breast cancer screening with only a small set of image patches from any SLN to detect changes in tumor environment and not in the tumor itself. This study involves breast pathologists in our department and uses our in-house breast cancer cases and WSI scanners. We design a convolutional neural network in the Python language to build a diagnostic model for four diagnostic categories (macrometastasis, micrometastasis, isolated tumor cells, and negative metastasis). SLNs with macrometastasis and micrometastasis are defined as positive cases; while those with isolated tumor cells only or true negative for metastatic tumor cells are defined as negative cases. We obtained WSIs of Hematoxylin and Eosin-stained slides from 34 cases with near equal distribution in 4 diagnostic categories. A total of 2720 image patches, from which 2160 (79%) were used for training, 240 (9%) for validation, and 320 (12%) for testing. Interobserver variation was also examined among 3 users. The test results showed excellent diagnostic results: accuracy (91.15%), sensitivity (77.92%), specificity (92.09%), positive predictive value (90.86%), and negative predictive value (80.66%). No significant variation in results was observed among the 3 observers. This preliminary study provided a proof of concept for incorporating automated metastatic screen into the digital pathology workflow to augment the pathologists’ productivity. Our approach is unique since it provides a very rapid screen rather than an exhaustive search for tumor in all fields of all sentinel lymph nodes

[1]  Seung‐Mo Hong,et al.  Distribution pattern of tumor infiltrating lymphocytes and tumor microenvironment composition as prognostic indicators in anorectal malignant melanoma , 2020, Modern Pathology.

[2]  Andrew H. Beck,et al.  Report on computational assessment of Tumor Infiltrating Lymphocytes from the International Immuno-Oncology Biomarker Working Group , 2020, npj Breast Cancer.

[3]  Zhi Han,et al.  Deep-Learning–Based Characterization of Tumor-Infiltrating Lymphocytes in Breast Cancers From Histopathology Images and Multiomics Data , 2020, JCO clinical cancer informatics.

[4]  Ashish Sharma,et al.  Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer , 2019, The American journal of pathology.

[5]  Douglas Bowman,et al.  Introduction to Digital Image Analysis in Whole-slide Imaging: A White Paper from the Digital Pathology Association , 2019, Journal of pathology informatics.

[6]  Lei Chen,et al.  Automated Diagnosis of Lymphoma with Digital Pathology Images Using Deep Learning , 2018, Annals of clinical and laboratory science.

[7]  Navid Farahani,et al.  A Practical Guide to Whole Slide Imaging: A White Paper From the Digital Pathology Association. , 2018, Archives of pathology & laboratory medicine.

[8]  A. Choudhury,et al.  On the Intersection of Deep Learning and Chest Radiography: Background and Prospects , 2019, SSRN Electronic Journal.

[9]  Mita Nasipuri,et al.  Patch-based system for Classification of Breast Histology images using deep learning , 2019, Comput. Medical Imaging Graph..

[10]  Ashwini Patil,et al.  A Computational Approach Identifies Immunogenic Features of Prognosis in Human Cancers , 2018, Front. Immunol..

[11]  Cesare Furlanello,et al.  Evaluating reproducibility of AI algorithms in digital pathology with DAPPER , 2018, bioRxiv.

[12]  O. Schilling,et al.  Morphology of Immunomodulation in Breast Cancer Tumor Draining Lymph Nodes Depends on Stage and Intrinsic Subtype , 2018, Scientific Reports.

[13]  Alexander Rakhlin,et al.  Deep Convolutional Neural Networks for Breast Cancer Histology Image Analysis , 2018, bioRxiv.

[14]  E. Brogi,et al.  Sentinel Lymph Nodes for Breast Carcinoma: A Paradigm Shift. , 2016, Archives of pathology & laboratory medicine.

[15]  Dayong Wang,et al.  Deep Learning for Identifying Metastatic Breast Cancer , 2016, ArXiv.

[16]  E. Brogi,et al.  Sentinel lymph nodes for breast carcinoma: an update on current practice , 2016, Histopathology.

[17]  Joachim M. Buhmann,et al.  Computational Pathology: Challenges and Promises for Tissue Analysis , 2015, Comput. Medical Imaging Graph..

[18]  Stephen R. Marsland,et al.  Machine Learning - An Algorithmic Perspective , 2009, Chapman and Hall / CRC machine learning and pattern recognition series.

[19]  Ryszard S. Choras,et al.  Feature extraction for CBIR and biometrics applications , 2007 .