Multi-head Attention-based Deep Multiple Instance Learning

Hassan Keshvarikhojasteh, Josien P. W. Pluim, Mitko Veta
Proceedings of the MICCAI Workshop on Computational Pathology, PMLR 254:1-12, 2024.

Abstract

This paper introduces MAD-MIL, a Multi-head Attention-based Deep Multiple Instance Learning model, designed for weakly supervised Whole Slide Images (WSIs) classification in digital pathology. Inspired by the multi-head attention mechanism of the Transformer, MAD-MIL simplifies model complexity while achieving competitive results against advanced models like CLAM and DS-MIL. Evaluated on the MNIST-BAGS and public datasets, including TUPAC16, TCGA BRCA, TCGA LUNG, and TCGA KIDNEY MAD-MIL consistently outperforms ABMIL. This demonstrates enhanced information diversity, interpretability, and efficiency in slide representation. The model’s effectiveness, coupled with fewer trainable parameters and lower computational complexity makes it a promising solution for automated pathology workflows. Our code is available at https://github.com/tueimage/MAD-MIL.

Cite this Paper

BibTeX
@InProceedings{pmlr-v254-keshvarikhojasteh24a, title = {Multi-head Attention-based Deep Multiple Instance Learning}, author = {Keshvarikhojasteh, Hassan and Pluim, Josien P. W. and Veta, Mitko}, booktitle = {Proceedings of the MICCAI Workshop on Computational Pathology}, pages = {1--12}, 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/keshvarikhojasteh24a/keshvarikhojasteh24a.pdf}, url = {https://proceedings.mlr.press/v254/keshvarikhojasteh24a.html}, abstract = {This paper introduces MAD-MIL, a Multi-head Attention-based Deep Multiple Instance Learning model, designed for weakly supervised Whole Slide Images (WSIs) classification in digital pathology. Inspired by the multi-head attention mechanism of the Transformer, MAD-MIL simplifies model complexity while achieving competitive results against advanced models like CLAM and DS-MIL. Evaluated on the MNIST-BAGS and public datasets, including TUPAC16, TCGA BRCA, TCGA LUNG, and TCGA KIDNEY MAD-MIL consistently outperforms ABMIL. This demonstrates enhanced information diversity, interpretability, and efficiency in slide representation. The model’s effectiveness, coupled with fewer trainable parameters and lower computational complexity makes it a promising solution for automated pathology workflows. Our code is available at https://github.com/tueimage/MAD-MIL. } }
Endnote
%0 Conference Paper %T Multi-head Attention-based Deep Multiple Instance Learning %A Hassan Keshvarikhojasteh %A Josien P. W. Pluim %A Mitko Veta %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-keshvarikhojasteh24a %I PMLR %P 1--12 %U https://proceedings.mlr.press/v254/keshvarikhojasteh24a.html %V 254 %X This paper introduces MAD-MIL, a Multi-head Attention-based Deep Multiple Instance Learning model, designed for weakly supervised Whole Slide Images (WSIs) classification in digital pathology. Inspired by the multi-head attention mechanism of the Transformer, MAD-MIL simplifies model complexity while achieving competitive results against advanced models like CLAM and DS-MIL. Evaluated on the MNIST-BAGS and public datasets, including TUPAC16, TCGA BRCA, TCGA LUNG, and TCGA KIDNEY MAD-MIL consistently outperforms ABMIL. This demonstrates enhanced information diversity, interpretability, and efficiency in slide representation. The model’s effectiveness, coupled with fewer trainable parameters and lower computational complexity makes it a promising solution for automated pathology workflows. Our code is available at https://github.com/tueimage/MAD-MIL.
APA
Keshvarikhojasteh, H., Pluim, J.P.W. & Veta, M.. (2024). Multi-head Attention-based Deep Multiple Instance Learning. Proceedings of the MICCAI Workshop on Computational Pathology, in Proceedings of Machine Learning Research 254:1-12 Available from https://proceedings.mlr.press/v254/keshvarikhojasteh24a.html.

Related Material