Context-aware stacked convolutional neural networks for classification of breast carcinomas in whole-slide histopathology images

• DOI: 10.1117/1.jmi.4.4.044504
• Publication Date: 2017-12-14T15:21:58Z
• Authors: Babak Ehteshami B...; Guido Zuidhof; Maschenka Balkenhol; Meyke Hermsen; Peter Bult; Bram van Ginneken; Nico Karssemeijer; Geert Litjens; Jeroen van der Laak
• Keywords: FOS: Computer and information sciences; Computer Vision and Pattern Recognition (cs.CV); Data Science; Radboudumc 17: Women's cancers RIHS: Radboud Institute for Health Sciences; Pathology - Radboud University Medical Center; Computer Science - Computer Vision and Pattern Recognition; Radboudumc 9: Rare cancers RIHS: Radboud Institute for Health Sciences; Radboudumc 15: Urological cancers RIHS: Radboud Institute for Health Sciences; Radboudumc 17: Women's cancers RIMLS: Radboud Institute for Molecular Life Sciences; 3. Good health; 03 medical and health sciences; 0302 clinical medicine; Medical Imaging - Radboud University Medical Center

Automated classification of histopathological whole-slide images (WSI) of breast tissue requires analysis at very high resolutions with a large contextual area. In this paper, we present context-aware stacked convolutional neural networks (CNN) for classification of breast WSIs into normal/benign, ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (IDC). We first train a CNN using high pixel resolution patches to capture cellular level information. The feature responses generated by this model are then fed as input to a second CNN, stacked on top of the first. Training of this stacked architecture with large input patches enables learning of fine-grained (cellular) details and global interdependence of tissue structures. Our system is trained and evaluated on a dataset containing 221 WSIs of H&E stained breast tissue specimens. The system achieves an AUC of 0.962 for the binary classification of non-malignant and malignant slides and obtains a three class accuracy of 81.3% for classification of WSIs into normal/benign, DCIS, and IDC, demonstrating its potentials for routine diagnostics.