Abstract
Our goal in this paper is to build parametric models for a dictionary of histological patterns that aid in the differential diagnosis of atypical breast lesions and evaluate the inferential power of these hand-crafted features. Diagnosis of high-risk atypical breast lesions is challenging and remains a critical component of breast cancer screening, presenting even for experienced pathologists a more difficult classification problem than the binary detection task of cancer vs not-cancer. Following guidelines in the WHO classification of the tumors of the breast (an essential reference for pathologists, clinicians and researchers) and in consultation with our team of breast sub-specialists (N = 3), we assembled a visual dictionary of sixteen histological patterns (e.g., cribriform, picket-fence), a subset that pathologists frequently use in making complex diagnostic decisions of atypical breast lesions. We invoke parametric models for each pattern using a mix of unary, binary and ternary features that account for morphological and architectural tissue properties. We use 1441 ductal regions of interest (ROIs) extracted automatically from 93 whole slide images (WSIs) with a computational pathology pipeline. We collected diagnostic labels for all of the ROIs: normal and columnar cell changes (CCC) as low-risk benign lesions (= 1124), and flat epithelium atypia (FEA) and atypical ductal hyperplasia (ADH) as high-risk benign lesions (= 317). We generate likelihood maps for each dictionary pattern across a given ROI and integrate this information to determine a diagnostic label of high- or low-risk. Our method has comparable classification accuracies to the pool of breast pathology sub-specialists. Our study enables a deeper understanding of the discordance among pathologists in diagnosing atypical breast lesions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Figueroa, J.D., et al.: Standardized measures of lobular involution and subsequent breast cancer risk among women with benign breast disease: a nested case-control study. Breast Cancer Res. Treat. 159(1), 163–172 (2016)
Santen, R.J.: Benign breast disease in women. In: Endotext [Internet]. MDText.com, Inc. (2018)
Dyrstad, S.W., et al.: Breast cancer risk associated with benign breast disease: systematic review and meta-analysis. Breast Cancer Res. Treat. 149(3), 569–575 (2015)
Elmore, J.G., et al.: Diagnostic concordance among pathologists interpreting breast biopsy specimens. JAMA 313(11), 1122–1132 (2015)
Lakhani, S.R.: WHO Classification of Tumours of the Breast. International Agency for Research on Cancer (2012)
Tosun, A.B., et al.: Histological detection of high-risk benign breast lesions from whole slide images. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 144–152. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66185-8_17
Mercan, E., et al.: Assessment of machine learning of breast pathology structures for automated differentiation of breast cancer and high-risk proliferative lesions. JAMA Netw. Open 2(8), e198777 (2019)
Bejnordi, B.E., et al.: Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images. J. Med. Imaging (Bellingham) 4(4), 044504 (2017)
Li, H., et al.: Quantitative nuclear histomorphometric features are predictive of Oncotype DX risk categories in ductal carcinoma in situ: preliminary findings. Breast Cancer Res. 21(1), 114 (2019)
Dong, F., et al.: Computational pathology to discriminate benign from malignant intraductal proliferations of the breast. PLoS ONE 9(12), e114885 (2014)
Schindelin, J., et al.: Fiji: an open-source platform for biological-image analysis. Nat. Meth. 9(7), 676–682 (2012)
Achanta, R., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Chan, T.F., et al.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266–277 (2001)
Pienta, K.J., et al.: Correlation of nuclear morphometry with progression of breast cancer. Cancer 68(9), 2012–2016 (1991)
Cui, Y., et al.: Nuclear morphometric features in benign breast tissue and risk of subsequent breast cancer. Breast Cancer Res. Treat. 104(1), 103–107 (2007)
Kashyap, A., et al.: Study of nuclear morphometry on cytology specimens of benign and malignant breast lesions: a study of 122 cases. J. Cytol. 34(1), 10 (2017)
Narasimha, A., et al.: Significance of nuclear morphometry in benign and malignant breast aspirates. Int. J. Appl. Basic Med. Res. 3(1), 22 (2013)
Mommers, E.C.M., et al.: Prognostic value of morphometry in patients with normal breast tissue or usual ductal hyperplasia of the breast. Int. J. Cancer 95(5), 282–285 (2001)
Yamashita, Y., et al.: Does flat epithelial atypia have rounder nuclei than columnar cell change/hyperplasia? A morphometric approach to columnar cell lesions of the breast. Virchows Arch. 468(6), 663–673 (2016)
Logullo, A.F., et al.: Columnar cell lesions of the breast: a practical review for the pathologist. Surg. Exp. Pathol. 2(1), 1–8 (2019)
Pinder, S.E., et al.: Non-operative breast pathology: columnar cell lesions. J. Clin. Pathol. 60(12), 1307–1312 (2007)
Allison, K.H., et al.: Histological features associated with diagnostic agreement in atypical ductal hyperplasia of the breast: illustrative cases from the B-Path study. Histopathology 69(6), 1028–1046 (2016)
Sergio R., et al.: pysal/pointpats: pointpats 2.1.0 (2019). https://doi.org/10.5281/zenodo.3265637
Zhou, N., et al.: Large scale digital prostate pathology image analysis combining feature extraction and deep neural network. arXiv:1705.02678 (2017)
Chawla, N.V., et al.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Ely, K.A., et al.: Core biopsy of the breast with atypical ductal hyperplasia: a probabilistic approach to reporting. Am. J. Surg. Pathol. 25(8), 1017–1021 (2001)
Chen, L., et al.: Diagnostic upgrade of atypical ductal hyperplasia of the breast based on evaluation of histopathological features and calcification on core needle biopsy. Histopathology 75(3), 320–328 (2019)
LeCun, Y., et al.: LeNet-5, convolutional neural networks, vol. 20, no. 5 (2015). http://yann.lecun.com/exdb/lenet
Krizhevsky, A., et al.: Imagenet classification with deep convolutional neural networks. In: NeurIPS, pp. 1097–1105 (2012)
Sermanet, P., et al.: OverFeat: integrated recognition, localization and detection using convolutional networks. In: ICLR, CBLS (2014)
Acknowledgments
The grant NIH-NCI U01CA204826 to SCC supported this work. The work of AP and OC was partially supported by the sub-contracts 9F-60178 and 9F-60287 from Argonne National Laboratory (ANL) to the University of Pittsburgh from the parent grant DE-AC02-06CH1135 titled, Co-Design of Advanced Artificial Intelligence Systems for Predicting Behavior of Complex Systems Using Multimodal Datasets, from the Department of Energy to ANL.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Parvatikar, A. et al. (2020). Modeling Histological Patterns for Differential Diagnosis of Atypical Breast Lesions. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12265. Springer, Cham. https://doi.org/10.1007/978-3-030-59722-1_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-59722-1_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59721-4
Online ISBN: 978-3-030-59722-1
eBook Packages: Computer ScienceComputer Science (R0)