Multi-scale Whole Slide Image Assessment Improves Deep Learning based WHO 2021 Glioma Classification

Shubham Innani, MacLean P. Nasrallah, W. Robert Bell, Bhakti Baheti, Spyridon Bakas
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 254:142-153, 2024.

Abstract

The 2021 WHO classification of tumors of the central nervous system necessitates the integration of molecular and histologic profiling for a conclusive diagnosis of glioma. Molecular profiling is time-consuming and may not always be available. We hypothesize that subvisual cues in whole slide images (WSI), not perceivable by the naked eye, carry a predictive value of molecular characteristics and can allow categorization of the adult infiltrative gliomas in one of three major types: i) oligodendroglioma, ii) astrocytoma, and iii) glioblastoma. Towards this end, we present a computational pipeline comprising patch analysis of Hematoxylin and Eosin (H&E)-stained WSIs, feature encoding with ImageNet pretrained ResNet50, and an attention-based multiple instance learning paradigm. We trained individual models at four distinct magnification levels (20x, 10x, 5x, 2.5x), and assessed the fusion of various ensemble combinations to mimic the WSI assessment by expert pathologists, to capture local and global context. Our results using a multi-scale approach demonstrate 3-9% improvement in classification accuracy when compared with models utilising a single magnification level. This advancement underscores the efficacy of attention-based models combined with multi-scale approaches in augmenting traditional assessment of WSIs. The implications of our findings are significant in enhancing glioma diagnosis and treatment planning in neuro-oncology, by enabling diagnostics in low-resource environments where molecular profiling is not available.

Cite this Paper

BibTeX
@InProceedings{pmlr-v254-innani24a, title = {Multi-scale Whole Slide Image Assessment Improves Deep Learning based WHO 2021 Glioma Classification}, author = {Innani, Shubham and Nasrallah, MacLean P. and Bell, W. Robert and Baheti, Bhakti and Bakas, Spyridon}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {142--153}, year = {2024}, editor = {Ciompi, Francesco and Khalili, Nadieh and Studer, Linda and Poceviciute, Milda and Khan, Amjad and Veta, Mitko and Jiao, Yiping and Haj-Hosseini, Neda and Chen, Hao and Raza, Shan and Minhas, FayyazZlobec, Inti and Burlutskiy, Nikolay and Vilaplana, Veronica and Brattoli, Biagio and Muller, Henning and Atzori, Manfredo and Raza, Shan and Minhas, Fayyaz}, volume = {254}, series = {Proceedings of Machine Learning Research}, month = {06 Oct}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v254/main/assets/innani24a/innani24a.pdf}, url = {https://proceedings.mlr.press/v254/innani24a.html}, abstract = {The 2021 WHO classification of tumors of the central nervous system necessitates the integration of molecular and histologic profiling for a conclusive diagnosis of glioma. Molecular profiling is time-consuming and may not always be available. We hypothesize that subvisual cues in whole slide images (WSI), not perceivable by the naked eye, carry a predictive value of molecular characteristics and can allow categorization of the adult infiltrative gliomas in one of three major types: i) oligodendroglioma, ii) astrocytoma, and iii) glioblastoma. Towards this end, we present a computational pipeline comprising patch analysis of Hematoxylin and Eosin (H&E)-stained WSIs, feature encoding with ImageNet pretrained ResNet50, and an attention-based multiple instance learning paradigm. We trained individual models at four distinct magnification levels (20x, 10x, 5x, 2.5x), and assessed the fusion of various ensemble combinations to mimic the WSI assessment by expert pathologists, to capture local and global context. Our results using a multi-scale approach demonstrate 3-9% improvement in classification accuracy when compared with models utilising a single magnification level. This advancement underscores the efficacy of attention-based models combined with multi-scale approaches in augmenting traditional assessment of WSIs. The implications of our findings are significant in enhancing glioma diagnosis and treatment planning in neuro-oncology, by enabling diagnostics in low-resource environments where molecular profiling is not available.} }
Endnote
%0 Conference Paper %T Multi-scale Whole Slide Image Assessment Improves Deep Learning based WHO 2021 Glioma Classification %A Shubham Innani %A MacLean P. Nasrallah %A W. Robert Bell %A Bhakti Baheti %A Spyridon Bakas %B Proceedings of the MICCAI Workshop on Computational Pathology %C Proceedings of Machine Learning Research %D 2024 %E Francesco Ciompi %E Nadieh Khalili %E Linda Studer %E Milda Poceviciute %E Amjad Khan %E Mitko Veta %E Yiping Jiao %E Neda Haj-Hosseini %E Hao Chen %E Shan Raza %E Fayyaz MinhasInti Zlobec %E Nikolay Burlutskiy %E Veronica Vilaplana %E Biagio Brattoli %E Henning Muller %E Manfredo Atzori %E Shan Raza %E Fayyaz Minhas %F pmlr-v254-innani24a %I PMLR %P 142--153 %U https://proceedings.mlr.press/v254/innani24a.html %V 254 %X The 2021 WHO classification of tumors of the central nervous system necessitates the integration of molecular and histologic profiling for a conclusive diagnosis of glioma. Molecular profiling is time-consuming and may not always be available. We hypothesize that subvisual cues in whole slide images (WSI), not perceivable by the naked eye, carry a predictive value of molecular characteristics and can allow categorization of the adult infiltrative gliomas in one of three major types: i) oligodendroglioma, ii) astrocytoma, and iii) glioblastoma. Towards this end, we present a computational pipeline comprising patch analysis of Hematoxylin and Eosin (H&E)-stained WSIs, feature encoding with ImageNet pretrained ResNet50, and an attention-based multiple instance learning paradigm. We trained individual models at four distinct magnification levels (20x, 10x, 5x, 2.5x), and assessed the fusion of various ensemble combinations to mimic the WSI assessment by expert pathologists, to capture local and global context. Our results using a multi-scale approach demonstrate 3-9% improvement in classification accuracy when compared with models utilising a single magnification level. This advancement underscores the efficacy of attention-based models combined with multi-scale approaches in augmenting traditional assessment of WSIs. The implications of our findings are significant in enhancing glioma diagnosis and treatment planning in neuro-oncology, by enabling diagnostics in low-resource environments where molecular profiling is not available.
APA
Innani, S., Nasrallah, M.P., Bell, W.R., Baheti, B. & Bakas, S.. (2024). Multi-scale Whole Slide Image Assessment Improves Deep Learning based WHO 2021 Glioma Classification. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 254:142-153 Available from https://proceedings.mlr.press/v254/innani24a.html.

Related Material