Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies.
Using deep convolutional neural networks to identify and classify tumor-associated stroma in diagnostic breast biopsies.
复制标题
DOI：
10.1038/s41379-018-0073-z
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Sherman ME
中科院分区：
文献类型：
--
作者：
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
乳腺基质微环境是乳腺癌发生、生长和转移的关键因素。虽然病理学家经常通过光学显微镜检测间质的形态学变化，但这种变化的视觉分类是主观和非定量的，限制了其诊断实用性。为了深入了解与乳腺癌相关的间质变化，我们将自动机器学习技术应用于良性和恶性图像引导乳腺活检的2，387个苏木精和伊红染色组织切片的数字图像，以调查882名年龄在40-65岁之间的女性的乳房X线摄影异常，这些女性参加了乳腺放射学评价和组织研究（BREAST）邮票项目。使用深度卷积神经网络，我们训练了一种算法来区分浸润性癌症周围的基质和良性活检的基质。在测试集（来自330名患者的928张全载玻片图像）中，该算法可以仅基于间质特征（受试者操作特征曲线下的面积=0.962）区分诊断为浸润性癌症的活检组织和良性活检组织。此外，在没有专门使用导管原位癌作为结果进行训练的情况下，该算法检测到的肿瘤相关基质量更大，并且与3级导管原位癌相比，与1级导管原位癌的距离更大。总的来说，这些结果表明，基于仅评估基质的深度卷积神经网络的算法可能有助于对乳腺活检进行分类，并有助于理解和评估乳腺病变的生物学。
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 2,387 hematoxylin and eosin stained tissue sections of benign and malignant image-guided breast biopsies performed to investigate mammographic abnormalities among 882 women, 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.
登录
查看更多内容
DOI：
10.1109/tbme.2011.2110648
发表时间：
2011-07
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Dundar MM;Badve S;Bilgin G;Raykar V;Jain R;Sertel O;Gurcan MN
通讯作者：
Gurcan MN
影响因子：
7.3
作者：
Bombonati, Alessandro;Sgroi, Dennis C.
通讯作者：
Sgroi, Dennis C.
影响因子：
3.7
作者：
Dong F;Irshad H;Oh EY;Lerwill MF;Brachtel EF;Jones NC;Knoblauch NW;Montaser-Kouhsari L;Johnson NB;Rao LK;Faulkner-Jones B;Wilbur DC;Schnitt SJ;Beck AH
通讯作者：
Beck AH
影响因子：
19.7
作者：
HANLEY, JA;MCNEIL, BJ
通讯作者：
MCNEIL, BJ
影响因子：
8.4
作者：
Elshof, Lotte E.;Tryfonidis, Konstantinos;Wesseling, Jelle
通讯作者：
Wesseling, Jelle