Automatic and explainable grading of meningiomas from histopathology images

Jonathan Ganz, Tobias Kirsch, Lucas Hoffmann, Christof A. Bertram, Christoph Hoffmann, Andreas Maier, Katharina Breininger, Ingmar Blümcke, Samir Jabari, Marc Aubreville
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 156:69-80, 2021.

Abstract

Meningioma is one of the most prevalent brain tumors in adults. To determine its malignancy, it is graded by a pathologist into three grades according to WHO standards. This grade plays a decisive role in treatment, and yet may be subject to inter-rater discordance. In this work, we present and compare three approaches towards fully automatic meningioma grading from histology whole slide images. All approaches are following a two-stage paradigm, where we first identify a region of interest based on the detection of mitotic figures in the slide using a state-of-the-art object detection deep learning network. This region of highest mitotic rate is considered characteristic for biological tumor behavior. In the second stage, we calculate a score corresponding to tumor malignancy based on information contained in this region using three different settings. In a first approach, image patches are sampled from this region and regression is based on morphological features encoded by a ResNet-based network. We compare this to learning a logistic regression from the determined mitotic count, an approach which is easily traceable and explainable. Lastly, we combine both approaches in a single network. We trained the pipeline on 951 slides from 341 patients and evaluated them on a separate set of 141 slides from 43 patients. All approaches yield a high correlation to the WHO grade. The logistic regression and the combined approach had the best results in our experiments, yielding correct predictions in $32$ and $33$ of all cases, respectively, with the image-based approach only predicting $25$ cases correctly. Spearman’s correlation was $0.7163$, $0.7926$ and $0.7900$ respectively. It might be counter-intuitive at first that morphological features provided by the image patches do not improve model performance. Yet, this mirrors the criteria of the grading scheme, where mitotic count is the only unequivocal parameter.

Cite this Paper

BibTeX
@InProceedings{pmlr-v156-ganz21a, title = {Automatic and explainable grading of meningiomas from histopathology images}, author = {Ganz, Jonathan and Kirsch, Tobias and Hoffmann, Lucas and Bertram, Christof A. and Hoffmann, Christoph and Maier, Andreas and Breininger, Katharina and Bl\"umcke, Ingmar and Jabari, Samir and Aubreville, Marc}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {69--80}, 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/ganz21a/ganz21a.pdf}, url = {https://proceedings.mlr.press/v156/ganz21a.html}, abstract = {Meningioma is one of the most prevalent brain tumors in adults. To determine its malignancy, it is graded by a pathologist into three grades according to WHO standards. This grade plays a decisive role in treatment, and yet may be subject to inter-rater discordance. In this work, we present and compare three approaches towards fully automatic meningioma grading from histology whole slide images. All approaches are following a two-stage paradigm, where we first identify a region of interest based on the detection of mitotic figures in the slide using a state-of-the-art object detection deep learning network. This region of highest mitotic rate is considered characteristic for biological tumor behavior. In the second stage, we calculate a score corresponding to tumor malignancy based on information contained in this region using three different settings. In a first approach, image patches are sampled from this region and regression is based on morphological features encoded by a ResNet-based network. We compare this to learning a logistic regression from the determined mitotic count, an approach which is easily traceable and explainable. Lastly, we combine both approaches in a single network. We trained the pipeline on 951 slides from 341 patients and evaluated them on a separate set of 141 slides from 43 patients. All approaches yield a high correlation to the WHO grade. The logistic regression and the combined approach had the best results in our experiments, yielding correct predictions in $32$ and $33$ of all cases, respectively, with the image-based approach only predicting $25$ cases correctly. Spearman’s correlation was $0.7163$, $0.7926$ and $0.7900$ respectively. It might be counter-intuitive at first that morphological features provided by the image patches do not improve model performance. Yet, this mirrors the criteria of the grading scheme, where mitotic count is the only unequivocal parameter.} }
Endnote
%0 Conference Paper %T Automatic and explainable grading of meningiomas from histopathology images %A Jonathan Ganz %A Tobias Kirsch %A Lucas Hoffmann %A Christof A. Bertram %A Christoph Hoffmann %A Andreas Maier %A Katharina Breininger %A Ingmar Blümcke %A Samir Jabari %A Marc Aubreville %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-ganz21a %I PMLR %P 69--80 %U https://proceedings.mlr.press/v156/ganz21a.html %V 156 %X Meningioma is one of the most prevalent brain tumors in adults. To determine its malignancy, it is graded by a pathologist into three grades according to WHO standards. This grade plays a decisive role in treatment, and yet may be subject to inter-rater discordance. In this work, we present and compare three approaches towards fully automatic meningioma grading from histology whole slide images. All approaches are following a two-stage paradigm, where we first identify a region of interest based on the detection of mitotic figures in the slide using a state-of-the-art object detection deep learning network. This region of highest mitotic rate is considered characteristic for biological tumor behavior. In the second stage, we calculate a score corresponding to tumor malignancy based on information contained in this region using three different settings. In a first approach, image patches are sampled from this region and regression is based on morphological features encoded by a ResNet-based network. We compare this to learning a logistic regression from the determined mitotic count, an approach which is easily traceable and explainable. Lastly, we combine both approaches in a single network. We trained the pipeline on 951 slides from 341 patients and evaluated them on a separate set of 141 slides from 43 patients. All approaches yield a high correlation to the WHO grade. The logistic regression and the combined approach had the best results in our experiments, yielding correct predictions in $32$ and $33$ of all cases, respectively, with the image-based approach only predicting $25$ cases correctly. Spearman’s correlation was $0.7163$, $0.7926$ and $0.7900$ respectively. It might be counter-intuitive at first that morphological features provided by the image patches do not improve model performance. Yet, this mirrors the criteria of the grading scheme, where mitotic count is the only unequivocal parameter.
APA
Ganz, J., Kirsch, T., Hoffmann, L., Bertram, C.A., Hoffmann, C., Maier, A., Breininger, K., Blümcke, I., Jabari, S. & Aubreville, M.. (2021). Automatic and explainable grading of meningiomas from histopathology images. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 156:69-80 Available from https://proceedings.mlr.press/v156/ganz21a.html.

Related Material