Symmetric Dense Inception Network for Simultaneous Cell Detection and Classification in Multiplex Immunohistochemistry Images

Hanyun Zhang, Tami Grunewald, Ayse U. Akarca, Jonathan A. Ledermann, Teresa Marafioti, Yinyin Yuan
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:246-257, 2021.

Abstract

Deep-learning based automatic analysis of the multiplex immunohistochemistry (mIHC) enables distinct cell populations to be localized on a large scale, providing insights into disease biology and therapeutic targets. However, standard deep-learning pipelines performed cell detection and classification as two-stage tasks, which is computationally inefficient and faces challenges to incorporate neighbouring tissue context for determining the cell identity. To overcome these limitations and to obtain a more accurate mapping of cell phenotypes, we presented a symmetric dense inception neural network for detecting and classifying cells in mIHC slides simultaneously. The model was applied with a novel stop-gradient strategy and a loss function accounted for class imbalance. When evaluated on an ovarian cancer dataset containing 6 cell types, the model achieved an F1 score of 0.835 in cell detection, and a weighted F1-score of 0.867 in cell classification, which outperformed separate models trained on individual tasks by 1.9% and 3.8% respectively. Taken together, the proposed method boosts the learning efficiency and prediction accuracy of cell detection and classification by simultaneously learning from both tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-zhang21a, title = {Symmetric Dense Inception Network for Simultaneous Cell Detection and Classification in Multiplex Immunohistochemistry Images}, author = {Zhang, Hanyun and Grunewald, Tami and Akarca, Ayse U. and Ledermann, Jonathan A. and Marafioti, Teresa and Yuan, Yinyin}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {246--257}, year = {2021}, editor = {Atzori, Manfredo and Burlutskiy, Nikolay and Ciompi, Francesco and Li, Zhang and Minhas, Fayyaz and Müller, Henning and Peng, Tingying and Rajpoot, Nasir and Torben-Nielsen, Ben and van der Laak, Jeroen and Veta, Mitko and Yuan, Yinyin and Zlobec, Inti}, volume = {156}, series = {Proceedings of Machine Learning Research}, month = {27 Sep}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v156/zhang21a/zhang21a.pdf}, url = {https://proceedings.mlr.press/v156/zhang21a.html}, abstract = {Deep-learning based automatic analysis of the multiplex immunohistochemistry (mIHC) enables distinct cell populations to be localized on a large scale, providing insights into disease biology and therapeutic targets. However, standard deep-learning pipelines performed cell detection and classification as two-stage tasks, which is computationally inefficient and faces challenges to incorporate neighbouring tissue context for determining the cell identity. To overcome these limitations and to obtain a more accurate mapping of cell phenotypes, we presented a symmetric dense inception neural network for detecting and classifying cells in mIHC slides simultaneously. The model was applied with a novel stop-gradient strategy and a loss function accounted for class imbalance. When evaluated on an ovarian cancer dataset containing 6 cell types, the model achieved an F1 score of 0.835 in cell detection, and a weighted F1-score of 0.867 in cell classification, which outperformed separate models trained on individual tasks by 1.9% and 3.8% respectively. Taken together, the proposed method boosts the learning efficiency and prediction accuracy of cell detection and classification by simultaneously learning from both tasks.} }
Endnote
%0 Conference Paper %T Symmetric Dense Inception Network for Simultaneous Cell Detection and Classification in Multiplex Immunohistochemistry Images %A Hanyun Zhang %A Tami Grunewald %A Ayse U. Akarca %A Jonathan A. Ledermann %A Teresa Marafioti %A Yinyin Yuan %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2021 %E Manfredo Atzori %E Nikolay Burlutskiy %E Francesco Ciompi %E Zhang Li %E Fayyaz Minhas %E Henning Müller %E Tingying Peng %E Nasir Rajpoot %E Ben Torben-Nielsen %E Jeroen van der Laak %E Mitko Veta %E Yinyin Yuan %E Inti Zlobec %F pmlr-v156-zhang21a %I PMLR %P 246--257 %U https://proceedings.mlr.press/v156/zhang21a.html %V 156 %X Deep-learning based automatic analysis of the multiplex immunohistochemistry (mIHC) enables distinct cell populations to be localized on a large scale, providing insights into disease biology and therapeutic targets. However, standard deep-learning pipelines performed cell detection and classification as two-stage tasks, which is computationally inefficient and faces challenges to incorporate neighbouring tissue context for determining the cell identity. To overcome these limitations and to obtain a more accurate mapping of cell phenotypes, we presented a symmetric dense inception neural network for detecting and classifying cells in mIHC slides simultaneously. The model was applied with a novel stop-gradient strategy and a loss function accounted for class imbalance. When evaluated on an ovarian cancer dataset containing 6 cell types, the model achieved an F1 score of 0.835 in cell detection, and a weighted F1-score of 0.867 in cell classification, which outperformed separate models trained on individual tasks by 1.9% and 3.8% respectively. Taken together, the proposed method boosts the learning efficiency and prediction accuracy of cell detection and classification by simultaneously learning from both tasks.
APA
Zhang, H., Grunewald, T., Akarca, A.U., Ledermann, J.A., Marafioti, T. & Yuan, Y.. (2021). Symmetric Dense Inception Network for Simultaneous Cell Detection and Classification in Multiplex Immunohistochemistry Images. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:246-257 Available from https://proceedings.mlr.press/v156/zhang21a.html.

Related Material