TY - JOUR
T1 - Learning to detect lymphocytes in immunohistochemistry with deep learning
AU - Swiderska-Chadaj, Zaneta
AU - Pinckaers, Hans
AU - van Rijthoven, Mart
AU - Balkenhol, Maschenka
AU - Melnikova, Margarita
AU - Geessink, Oscar
AU - Manson, Quirine
AU - Sherman, Mark
AU - Polonia, Antonio
AU - Parry, Jeremy
AU - Abubakar, Mustapha
AU - Litjens, Geert
AU - van der Laak, Jeroen
AU - Ciompi, Francesco
N1 - Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/12
Y1 - 2019/12
N2 - The immune system is of critical importance in the development of cancer. The evasion of destruction by the immune system is one of the emerging hallmarks of cancer. We have built a dataset of 171,166 manually annotated CD3+ and CD8+ cells, which we used to train deep learning algorithms for automatic detection of lymphocytes in histopathology images to better quantify immune response. Moreover, we investigate the effectiveness of four deep learning based methods when different subcompartments of the whole-slide image are considered: normal tissue areas, areas with immune cell clusters, and areas containing artifacts. We have compared the proposed methods in breast, colon and prostate cancer tissue slides collected from nine different medical centers. Finally, we report the results of an observer study on lymphocyte quantification, which involved four pathologists from different medical centers, and compare their performance with the automatic detection. The results give insights on the applicability of the proposed methods for clinical use. U-Net obtained the highest performance with an F1-score of 0.78 and the highest agreement with manual evaluation (κ=0.72), whereas the average pathologists agreement with reference standard was κ=0.64. The test set and the automatic evaluation procedure are publicly available at lyon19.grand-challenge.org.
AB - The immune system is of critical importance in the development of cancer. The evasion of destruction by the immune system is one of the emerging hallmarks of cancer. We have built a dataset of 171,166 manually annotated CD3+ and CD8+ cells, which we used to train deep learning algorithms for automatic detection of lymphocytes in histopathology images to better quantify immune response. Moreover, we investigate the effectiveness of four deep learning based methods when different subcompartments of the whole-slide image are considered: normal tissue areas, areas with immune cell clusters, and areas containing artifacts. We have compared the proposed methods in breast, colon and prostate cancer tissue slides collected from nine different medical centers. Finally, we report the results of an observer study on lymphocyte quantification, which involved four pathologists from different medical centers, and compare their performance with the automatic detection. The results give insights on the applicability of the proposed methods for clinical use. U-Net obtained the highest performance with an F1-score of 0.78 and the highest agreement with manual evaluation (κ=0.72), whereas the average pathologists agreement with reference standard was κ=0.64. The test set and the automatic evaluation procedure are publicly available at lyon19.grand-challenge.org.
KW - Computational pathology
KW - Deep learning
KW - Immune cell detection
KW - Immunohistochemistry
UR - http://www.scopus.com/inward/record.url?scp=85071517962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071517962&partnerID=8YFLogxK
U2 - 10.1016/j.media.2019.101547
DO - 10.1016/j.media.2019.101547
M3 - Article
C2 - 31476576
AN - SCOPUS:85071517962
SN - 1361-8415
VL - 58
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 101547
ER -