Ano-swinMAE: Unsupervised Anomaly Detection in Brain MRI using swin Transformer based Masked Auto Encoder

Kumari Rashmi, Ayantika Das, NagaGayathri Matcha, Keerthi Ram, Mohanasankar Sivaprakasam
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1221-1236, 2024.

Abstract

The advanced deep learning-based Autoencoding techniques have enabled the introduction of efficient Unsupervised Anomaly Detection (UAD) approaches. Several autoencoder-based approaches have been used to solve UAD tasks. However, most of these approaches do not have any constraints to ensure the removal of pathological features while restoring the healthy regions in the pseudo-healthy image reconstruction. To remove the occurrence of pathological features, we propose to utilize an Autoencoder which deploys a masking strategy to reconstruct images. Additionally, the masked regions need to be meaningfully inpainted to enforce global and local consistency in the generated images which makes transformer-based masked autoencoder a potential approach. Although the transformer models can incorporate global contextual information, they are often computationally expensive and dependent on a large amount of data for training. Hence we propose to employ a Swin transformer-based Masked Autoencoder (MAE) for anomaly detection (Ano-swinMAE) in brain MRI. Our proposed method Ano-swinMAE is trained on a healthy cohort by masking a certain percentage of information from the input images. While inferring, a pathological image is given to the model and different segments of the brain MRI slice are sequentially masked and their corresponding generation is accumulated to create a map indicating potential locations of pathologies. We have quantitatively and qualitatively validated the performance increment of our method on the following publicly available datasets: BraTS (Glioma), MSLUB (Multiple Sclerosis) and White Matter Hyperintensities (WMH). We have also empirically evaluated the generalisation capability of the method in a cross modality data setup.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-rashmi24a, title = {Ano-swinMAE: Unsupervised Anomaly Detection in Brain MRI using swin Transformer based Masked Auto Encoder}, author = {Rashmi, Kumari and Das, Ayantika and Matcha, NagaGayathri and Ram, Keerthi and Sivaprakasam, Mohanasankar}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1221--1236}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/rashmi24a/rashmi24a.pdf}, url = {https://proceedings.mlr.press/v250/rashmi24a.html}, abstract = {The advanced deep learning-based Autoencoding techniques have enabled the introduction of efficient Unsupervised Anomaly Detection (UAD) approaches. Several autoencoder-based approaches have been used to solve UAD tasks. However, most of these approaches do not have any constraints to ensure the removal of pathological features while restoring the healthy regions in the pseudo-healthy image reconstruction. To remove the occurrence of pathological features, we propose to utilize an Autoencoder which deploys a masking strategy to reconstruct images. Additionally, the masked regions need to be meaningfully inpainted to enforce global and local consistency in the generated images which makes transformer-based masked autoencoder a potential approach. Although the transformer models can incorporate global contextual information, they are often computationally expensive and dependent on a large amount of data for training. Hence we propose to employ a Swin transformer-based Masked Autoencoder (MAE) for anomaly detection (Ano-swinMAE) in brain MRI. Our proposed method Ano-swinMAE is trained on a healthy cohort by masking a certain percentage of information from the input images. While inferring, a pathological image is given to the model and different segments of the brain MRI slice are sequentially masked and their corresponding generation is accumulated to create a map indicating potential locations of pathologies. We have quantitatively and qualitatively validated the performance increment of our method on the following publicly available datasets: BraTS (Glioma), MSLUB (Multiple Sclerosis) and White Matter Hyperintensities (WMH). We have also empirically evaluated the generalisation capability of the method in a cross modality data setup.} }
Endnote
%0 Conference Paper %T Ano-swinMAE: Unsupervised Anomaly Detection in Brain MRI using swin Transformer based Masked Auto Encoder %A Kumari Rashmi %A Ayantika Das %A NagaGayathri Matcha %A Keerthi Ram %A Mohanasankar Sivaprakasam %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-rashmi24a %I PMLR %P 1221--1236 %U https://proceedings.mlr.press/v250/rashmi24a.html %V 250 %X The advanced deep learning-based Autoencoding techniques have enabled the introduction of efficient Unsupervised Anomaly Detection (UAD) approaches. Several autoencoder-based approaches have been used to solve UAD tasks. However, most of these approaches do not have any constraints to ensure the removal of pathological features while restoring the healthy regions in the pseudo-healthy image reconstruction. To remove the occurrence of pathological features, we propose to utilize an Autoencoder which deploys a masking strategy to reconstruct images. Additionally, the masked regions need to be meaningfully inpainted to enforce global and local consistency in the generated images which makes transformer-based masked autoencoder a potential approach. Although the transformer models can incorporate global contextual information, they are often computationally expensive and dependent on a large amount of data for training. Hence we propose to employ a Swin transformer-based Masked Autoencoder (MAE) for anomaly detection (Ano-swinMAE) in brain MRI. Our proposed method Ano-swinMAE is trained on a healthy cohort by masking a certain percentage of information from the input images. While inferring, a pathological image is given to the model and different segments of the brain MRI slice are sequentially masked and their corresponding generation is accumulated to create a map indicating potential locations of pathologies. We have quantitatively and qualitatively validated the performance increment of our method on the following publicly available datasets: BraTS (Glioma), MSLUB (Multiple Sclerosis) and White Matter Hyperintensities (WMH). We have also empirically evaluated the generalisation capability of the method in a cross modality data setup.
APA
Rashmi, K., Das, A., Matcha, N., Ram, K. & Sivaprakasam, M.. (2024). Ano-swinMAE: Unsupervised Anomaly Detection in Brain MRI using swin Transformer based Masked Auto Encoder. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1221-1236 Available from https://proceedings.mlr.press/v250/rashmi24a.html.

Related Material