Abstract
The pathological differential diagnosis between breast ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) is of pivotal importance for determining optimum cancer treatment(s) and clinical outcomes. Since conventional diagnosis by pathologists using microscopes is limited in terms of human resources, it is necessary to develop new techniques that can rapidly and accurately diagnose large numbers of histopathological specimens. Computational pathology tools which can assist pathologists in detecting and classifying DCIS and IDC from whole slide images (WSIs) would be of great benefit for routine pathological diagnosis. In this paper, we trained deep learning models capable of classifying biopsy and surgical histopathological WSIs into DCIS, IDC, and benign. We evaluated the models on two independent test sets (n= 1382, n= 548), achieving ROC areas under the curves (AUCs) up to 0.960 and 0.977 for DCIS and IDC, respectively.
Similar content being viewed by others
References
Abadi M, Agarwal A, Barham P et al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. https://www.tensorflow.org/, software available from tensorflow.org
Bayramoglu N, Kannala J, Heikkilä J (2016) Deep learning for magnification independent breast cancer histopathology image classification. In: 2016 23rd international conference on pattern recognition (ICPR), IEEE, pp 2440–2445
Becker R, Mikel U, O’Leary T (1992) Morphometric distinction of sclerosing adenosis from tubular carcinoma of the breast. Pathology-Research and Practice 188(7):847–851
Bejnordi BE, Veta M, Van Diest PJ et al (2017) Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. Jama 318(22):2199–2210
Bianchi S, Giannotti E, Vanzi E et al (2012) Radial scar without associated atypical epithelial proliferation on image-guided 14-gauge needle core biopsy: analysis of 49 cases from a single-centre and review of the literature. The Breast 21(2):159–164
on Breast ECWG, Sloane JP, Amendoeira I et al (1998) Consistency achieved by 23 European pathologists in categorizing ductal carcinoma in situ of the breast using five classifications. Human Pathology 29 (10):1056–1062
Campanella G, Hanna MG, Geneslaw L et al (2019) Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med 25(8):1301–1309
Cho K, Van Merriënboer B, Gulcehre C et al (2014) Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:14061078
Coates AS, Winer EP, Goldhirsch A et al (2015) Tailoring therapies—improving the management of early breast cancer: St gallen international expert consensus on the primary therapy of early breast cancer 2015. Annals of Oncology 26(8):1533–1546
Collins L, Tamimi R, Baer H et al (2004) Risk of invasive breast cancer in patients with ductal carcinoma in situ (dcis) treated by diagnostic biopsy alone: results from the nurses’ health study. Breast Cancer Research and Treatment 88
Coudray N, Ocampo PS, Sakellaropoulos T et al (2018) Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nature Medicine 24(10):1559–1567
Coyne J, Dervan P, Barr L et al (2001) Mixed apocrine/endocrine ductal carcinoma in situ of the breast coexistent with lobular carcinoma in situ. Journal of Clinical Pathology 54(1):70–73
Cserni G, Wells CA, Kaya H et al (2016) Consistency in recognizing microinvasion in breast carcinomas is improved by immunohistochemistry for myoepithelial markers. Virchows Archiv 468(4):473–481
Dahlstrom J, Jain S, Sutton T et al (1996) Diagnostic accuracy of stereotactic core biopsy in a mammographic breast cancer screening programme. Histopathology 28(5):421–427
Damiani S, Dina R, Eusebi V (1999) Eosinophilic and granular cell tumors of the breast. In: Seminars in diagnostic pathology, pp 117–125
Dillon M, Quinn C, McDermott E et al (2006) Diagnostic accuracy of core biopsy for ductal carcinoma in situ and its implications for surgical practice. Journal of Clinical Pathology 59(7):740–743
van Dooijeweert C, van Diest PJ, Willems SM et al (2019) Significant inter-and intra-laboratory variation in grading of ductal carcinoma in situ of the breast: a nationwide study of 4901 patients in the netherlands. Breast Cancer Research and Treatment 174(2):479–488
Efron B, Tibshirani RJ (1994) An introduction to the bootstrap. CRC press
El-Tamer M, Axiotis C, Kim E et al (1999) Accurate prediction of the amount of in situ tumor in palpable breast cancers by core needle biopsy: implications for neoadjuvant therapy
Elshof LE, Schmidt MK, Emiel JT et al (2018) Cause-specific mortality in a population-based cohort of 9799 women treated for ductal carcinoma in situ. Annals of Surgery 267(5):952
Erber R, Hartmann A (2020) Histology of luminal breast cancer. Breast Care 15(4):327–336
Esserman LJ, Thompson IM, Reid B et al (2014) Addressing overdiagnosis and overtreatment in cancer: a prescription for change. The Lancet Oncology 15(6):e234–e242
Eusebi V, Collina G, Bussolati G (1989) Carcinoma in situ in sclerosing adenosis of the breast: an immunocytochemical study. In: Seminars in diagnostic pathology, pp 146–152
Gertych A, Swiderska-Chadaj Z, Ma Z et al (2019) Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides. Scientific Reports 9(1):1483
Goldhirsch A, Winer EP, Coates A et al (2013) Personalizing the treatment of women with early breast cancer: highlights of the st gallen international expert consensus on the primary therapy of early breast cancer 2013. Annals of Oncology 24(9):2206–2223
Goode A, Gilbert B, Harkes J et al (2013) Openslide: A vendor-neutral software foundation for digital pathology. Journal of pathology informatics 4
Gupta SK, Douglas-Jones AG, Fenn N et al (1997) The clinical behavior of breast carcinoma is probably determined at the preinvasive stage (ductal carcinoma in situ). Cancer: Interdisciplinary International Journal of the American Cancer Society 80(9):1740–1745
Hameed Z, Zahia S, Garcia-Zapirain B et al (2020) Breast cancer histopathology image classification using an ensemble of deep learning models. Sensors 20(16):4373. https://doi.org/10.3390/s20164373
Harris GC, Denley HE, Pinder SE et al (2003) Correlation of histologic prognostic factors in core biopsies and therapeutic excisions of invasive breast carcinoma. The American Journal of Surgical Pathology 27(1):11–15
Hilson JB, Schnitt SJ, Collins LC (2010) Phenotypic alterations in myoepithelial cells associated with benign sclerosing lesions of the breast. The American Journal of Surgical Pathology 34(6):896–900
Hou L, Samaras D, Kurc TM et al (2016) Patch-based convolutional neural network for whole slide tissue image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2424–2433
Huang N, Chen J, Xue J et al (2015) Breast sclerosing adenosis and accompanying malignancies: a clinicopathological and imaging study in a chinese population. Medicine 94(49)
Hunter JD (2007) Matplotlib: A 2d graphics environment. Comput Sci Eng 9(3):90–95. https://doi.org/10.1109/MCSE.2007.55
Iizuka O, Kanavati F, Kato K et al (2020) Deep learning models for histopathological classification of gastric and colonic epithelial tumours. Scientific Reports 10(1):1–11
Kanavati F, Tsuneki M (2021) Breast invasive ductal carcinoma classification on whole slide images with weakly-supervised and transfer learning. bioRxiv
Kanavati F, Tsuneki M (2021) Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning. arXiv:210205543
Kanavati F, Toyokawa G, Momosaki S et al (2020) Weakly-supervised learning for lung carcinoma classification using deep learning. Scientific Reports 10(1):1–11
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:14126980
Korbar B, Olofson AM, Miraflor AP et al (2017) Deep learning for classification of colorectal polyps on whole-slide images. Journal of Pathology Informatics 8
Kraus OZ, Ba JL, Frey BJ (2016) Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics 32(12):i52–i59
Litjens G, Sánchez CI, Timofeeva N et al (2016) Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Scientific Reports 6:26,286
Luo X, Zang X, Yang L et al (2017) Comprehensive computational pathological image analysis predicts lung cancer prognosis. Journal of Thoracic Oncology 12(3):501–509
Madabhushi A, Lee G (2016) Image analysis and machine learning in digital pathology: challenges and opportunities. Med Image Anal 33:170–175
Mi W, Li J, Guo Y et al (2021) Deep learning-based multi-class classification of breast digital pathology images. Cancer Management and Research 13:4605–4617. https://doi.org/10.2147/cmar.s312608
Moriya T, Sakamoto K, Sasano H et al (2000) Immunohistochemical analysis of ki-67, p53, p21, and p27 in benign and malignant apocrine lesions of the breast: Its correlation to histologic findings in 43 cases. Modern Pathology 13(1):13–18
Moriya T, Kozuka Y, Kanomata N et al (2009) The role of immunohistochemistry in the differential diagnosis of breast lesions. Pathology 41(1):68–76
Nassar H, Wallis T, Andea A et al (2001) Clinicopathologic analysis of invasive micropapillary differentiation in breast carcinoma. Modern Pathology 14(9):836–841
Oberman H, Markey B (1991) Noninvasive carcinoma of the breast presenting in adenosis. Modern Pathology 4(1):31–35
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825–2830
Perou CM, Sørlie T, Eisen MB et al (2000) Molecular portraits of human breast tumours. Nature 406(6797):747–752
Petersson F, Tan PH, Choudary Putti T (2010) Low-grade ductal carcinoma in situ and invasive mammary carcinoma with columnar cell morphology arising in a complex fibroadenoma in continuity with columnar cell change and flat epithelial atypia. International Journal of Surgical Pathology 18(5):352–357
Pijnappel RM, van Dalen A, Rinkes IHB et al (1997) The diagnostic accuracy of core biopsy in palpable and non-palpable breast lesions. European Journal of Radiology 24(2):120–123
Prasad ML, Osborne MP, Giri DD et al (2000) Microinvasive carcinoma (t1mic) of the breast: Clinicopathologic profile of 21 cases. The American Journal of Surgical Pathology 24(3):422–428
Rakha E, Ellis I (2007) An overview of assessment of prognostic and predictive factors in breast cancer needle core biopsy specimens. Journal of Clinical Pathology 60(12):1300–1306
Rosa M, Agosto-Arroyo E (2019) Core needle biopsy of benign, borderline and in-situ problematic lesions of the breast: diagnosis, differential diagnosis and immunohistochemistry. Annals of Diagnostic Pathology 43:151,407
Saltz J, Gupta R, Hou L et al (2018) Spatial organization and molecular correlation of tumor-infiltrating lymphocytes using deep learning on pathology images. Cell Reports 23(1):181–193
Sanders ME, Schuyler PA, Simpson JF et al (2015) Continued observation of the natural history of low-grade ductal carcinoma in situ reaffirms proclivity for local recurrence even after more than 30 years of follow-up. Modern Pathology 28(5):662–669
Sharma S, Mehra R (2020) Conventional machine learning and deep learning approach for multi-classification of breast cancer histopathology images—a comparative insight. Journal of Digital Imaging 33(3):632–654. https://doi.org/10.1007/s10278-019-00307-y
Sohail A, Khan A, Nisar H et al (2021) Mitotic nuclei analysis in breast cancer histopathology images using deep ensemble classifier. Med Image Anal 72:102,121. https://doi.org/10.1016/j.media.2021.102121
Sørlie T, Perou CM, Tibshirani R et al (2001) Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications. Proceedings of the National Academy of Sciences 98 (19):10,869–10,874
Spruill L (2016) Benign mimickers of malignant breast lesions. In: Seminars in diagnostic pathology, Elsevier, pp 2–12
Sung H, Ferlay J, Siegel RL et al (2021) Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians 71(3):209–249
Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, PMLR, pp 6105–6114
Thompson AM, Clements K, Cheung S et al (2018) Management and 5-year outcomes in 9938 women with screen-detected ductal carcinoma in situ: the uk sloane project. European Journal of Cancer 101:210–219
Tramm T, Kim JY, Tavassoli FA (2011) Diminished number or complete loss of myoepithelial cells associated with metaplastic and neoplastic apocrine lesions of the breast. The American Journal of Surgical Pathology 35(2):202–211
Wapnir IL, Dignam JJ, Fisher B et al (2011) Long-term outcomes of invasive ipsilateral breast tumor recurrences after lumpectomy in nsabp b-17 and b-24 randomized clinical trials for dcis. Journal of the National Cancer Institute 103(6):478–488
Wei JW, Tafe LJ, Linnik YA et al (2019) Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks. Scientific Reports 9(1):1–8
Wetstein SC, Stathonikos N, Pluim JPW et al (2021) Deep learning-based grading of ductal carcinoma in situ in breast histopathology images. Laboratory Investigation 101(4):525–533. https://doi.org/10.1038/s41374-021-00540-6
Yu BH, Tang SX, Xu XL et al (2018) Breast carcinoma in sclerosing adenosis: a clinicopathological and immunophenotypical analysis on 206 lesions. Journal of Clinical Pathology 71(6):546–553
Yu KH, Zhang C, Berry GJ et al (2016) Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nat Commun 7:12,474
Acknowledgements
We are grateful for the support provided by Professor Takayuki Shiomi at Department of Pathology, Faculty of Medicine, International University of Health and Welfare; Dr. Ryosuke Matsuoka at Diagnostic Pathology Center, International University of Health and Welfare, Mita Hospital. We thank pathologists and oncologists who have been engaged in reviewing cases and clinicopathological discussion for this study.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The experimental protocol was approved by the ethical board of the Sapporo-Kosei General Hospital (No. 580) and International University of Health and Welfare (No. 19-Im-007). All research activities complied with all relevant ethical regulations and were performed in accordance with relevant guidelines and regulations in the all hospitals mentioned above. Informed consent to use histopathological samples and pathological diagnostic reports for research purposes had previously been obtained from all patients prior to the surgical procedures at all hospitals, and the opportunity for refusal to participate in research had been guaranteed by an opt-out manner.
Conflict of Interest
F.K. and M.T. are employees of Medmain Inc. All authors declare no competing interests.
Additional information
Author contribution
F.K., S.I., and M.T. contributed equally to this study; F.K. and M.T. designed the studies; F.K., S.I., and M.T. performed experiments and analyzed the data; S.I. performed pathological diagnoses and reviewed cases; F.K. and M.T. performed computational studies; F.K., S.I., and M.T. wrote the manuscript; M.T. supervised the project. All authors reviewed and approved the final manuscript.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Fahdi Kanavati, Shin Ichihara and Masayuki Tsuneki contributed equally to this work.
Rights and permissions
About this article
Cite this article
Kanavati, F., Ichihara, S. & Tsuneki, M. A deep learning model for breast ductal carcinoma in situ classification in whole slide images. Virchows Arch 480, 1009–1022 (2022). https://doi.org/10.1007/s00428-021-03241-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00428-021-03241-z