TY - JOUR
T1 - Artificial neural networks and pathologists recognize basal cell carcinomas based on different histological patterns
AU - Kimeswenger, Susanne
AU - Tschandl, Philipp
AU - Noack, Petar
AU - Hofmarcher, Markus
AU - Rumetshofer, Elisabeth
AU - Kindermann, Harald
AU - Silye, Rene
AU - Hochreiter, Sepp
AU - Kaltenbrunner, Martin
AU - Guenova, Emmanuella
AU - Klambauer, Guenter
AU - Hoetzenecker, Wolfram
N1 - Publisher Copyright:
© 2020, The Author(s), under exclusive licence to United States & Canadian Academy of Pathology.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2021/5
Y1 - 2021/5
N2 - Recent advances in artificial intelligence, particularly in the field of deep learning, have enabled researchers to create compelling algorithms for medical image analysis. Histological slides of basal cell carcinomas (BCCs), the most frequent skin tumor, are accessed by pathologists on a daily basis and are therefore well suited for automated prescreening by neural networks for the identification of cancerous regions and swift tumor classification. In this proof-of-concept study, we implemented an accurate and intuitively interpretable artificial neural network (ANN) for the detection of BCCs in histological whole-slide images (WSIs). Furthermore, we identified and compared differences in the diagnostic histological features and recognition patterns relevant for machine learning algorithms vs. expert pathologists. An attention-ANN was trained with WSIs of BCCs to identify tumor regions (n = 820). The diagnosis-relevant regions used by the ANN were compared to regions of interest for pathologists, detected by eye-tracking techniques. This ANN accurately identified BCC tumor regions on images of histologic slides (area under the ROC curve: 0.993, 95% CI: 0.990–0.995; sensitivity: 0.965, 95% CI: 0.951–0.979; specificity: 0.910, 95% CI: 0.859–0.960). The ANN implicitly calculated a weight matrix, indicating the regions of a histological image that are important for the prediction of the network. Interestingly, compared to pathologists’ eye-tracking results, machine learning algorithms rely on significantly different recognition patterns for tumor identification (p < 10−4). To conclude, we found on the example of BCC WSIs, that histopathological images can be efficiently and interpretably analyzed by state-of-the-art machine learning techniques. Neural networks and machine learning algorithms can potentially enhance diagnostic precision in digital pathology and uncover hitherto unused classification patterns.
AB - Recent advances in artificial intelligence, particularly in the field of deep learning, have enabled researchers to create compelling algorithms for medical image analysis. Histological slides of basal cell carcinomas (BCCs), the most frequent skin tumor, are accessed by pathologists on a daily basis and are therefore well suited for automated prescreening by neural networks for the identification of cancerous regions and swift tumor classification. In this proof-of-concept study, we implemented an accurate and intuitively interpretable artificial neural network (ANN) for the detection of BCCs in histological whole-slide images (WSIs). Furthermore, we identified and compared differences in the diagnostic histological features and recognition patterns relevant for machine learning algorithms vs. expert pathologists. An attention-ANN was trained with WSIs of BCCs to identify tumor regions (n = 820). The diagnosis-relevant regions used by the ANN were compared to regions of interest for pathologists, detected by eye-tracking techniques. This ANN accurately identified BCC tumor regions on images of histologic slides (area under the ROC curve: 0.993, 95% CI: 0.990–0.995; sensitivity: 0.965, 95% CI: 0.951–0.979; specificity: 0.910, 95% CI: 0.859–0.960). The ANN implicitly calculated a weight matrix, indicating the regions of a histological image that are important for the prediction of the network. Interestingly, compared to pathologists’ eye-tracking results, machine learning algorithms rely on significantly different recognition patterns for tumor identification (p < 10−4). To conclude, we found on the example of BCC WSIs, that histopathological images can be efficiently and interpretably analyzed by state-of-the-art machine learning techniques. Neural networks and machine learning algorithms can potentially enhance diagnostic precision in digital pathology and uncover hitherto unused classification patterns.
UR - http://www.scopus.com/inward/record.url?scp=85096019722&partnerID=8YFLogxK
U2 - 10.1038/s41379-020-00712-7
DO - 10.1038/s41379-020-00712-7
M3 - Article
AN - SCOPUS:85096019722
SN - 0893-3952
VL - 34
SP - 895
EP - 903
JO - Modern Pathology
JF - Modern Pathology
IS - 5
ER -
