According to a recent paper of Babak Ehteshami Bejnordi, Jeroen van der Laak and colleagues, deep learning based analysis of digitized microscopic images could accurately identify tumor-associated morphological alterations in the stroma neighboring breast cancer.abstract
The breast stromal microenvironment is a pivotal factor in breast cancer development, growth and metastases. Although pathologists often detect morphologic changes in stroma by light microscopy, visual classification of such changes is subjective and non-quantitative, limiting its diagnostic utility. To gain insights into stromal changes associated with breast cancer, we applied automated machine learning techniques to digital images of 2387 hematoxylin and eosin stained tissue sections of benign and malignant image-guided breast biopsies performed to investigate mammographic abnormalities among 882 patients, ages 40–65 years, that were enrolled in the Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project. Using deep convolutional neural networks, we trained an algorithm to discriminate between stroma surrounding invasive cancer and stroma from benign biopsies. In test sets (928 whole-slide images from 330 patients), this algorithm could distinguish biopsies diagnosed as invasive cancer from benign biopsies solely based on the stromal characteristics (area under the receiver operator characteristics curve = 0.962). Furthermore, without being trained specifically using ductal carcinoma in situ as an outcome, the algorithm detected tumor-associated stroma in greater amounts and at larger distances from grade 3 versus grade 1 ductal carcinoma in situ. Collectively, these results suggest that algorithms based on deep convolutional neural networks that evaluate only stroma may prove useful to classify breast biopsies and aid in understanding and evaluating the biology of breast lesions.
Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies.
Ehteshami Bejnordi B, Mullooly M, Pfeiffer RM, Fan S, Vacek PM, Weaver DL, Herschorn S, Brinton LA, van Ginneken B, Karssemeijer N, Beck AH, Gierach GL, van der Laak JAWM, Sherman ME.
Nico Karssemeijer and Jeroen van der Laak are both members of theme Women's cancers. Bram van Ginneken is member of theme Rare cancers.
Related news items
Working energetically from home3 December 2020
By now, you may have gotten used to it: working from home. The page ‘Working energetically from home‘ offers you tips to help you work from home better, from setting up a good workspace to working more effectively and maintaining a good work-life balance.read more
Radboudumc research most lungs recover well after COVID-1926 November 2020
In severe COVID-19 patients the lung tissue recovers well in most cases. This is shown in research by the Radboudumc, published in Clinical Infectious Diseases. Striking conclusion: patients who were referred by the general practitioner recover worse than ICU patients.read more
Marianne Boenink has been appointed professor in Ethics of Healthcare26 November 2020
Health scientist and philosopher Marianne Boenink has been appointed professor in Ethics of Healthcare at the Radboud University/ Radboudumc, as of 1 August 2020.read more
Patrick Jeurissen member Scientific Advisory Board for European Commission on health care policy in pandemics26 November 2020
Patrick Jeurissen, Professor of Affordability of Care, has been appointed as a member of the Scientific Advisory Board for the Pan-European Commission on Health and Sustainable Development. This committee will study healthcare policy in the light of pandemics in the coming year.read more
Erik van der Heijden received The Distinguished WABIP Regent Award26 November 2020
The 21st World Conference on Bronchoscopy and Intervention Pulmonology (WCBIP) is currently taking place in Shanghai. This is organized by the WABIP. Erik van der Heijden, member of the scientific organizing committee, received the prize ‘The Distinguished WABIP Regent Award'.read more