| MS Seminar

Name of the Speaker: Ms. KUMARI RASHMI (EE20S051)
Guide: Prof. Mohanasankar S
Online meeting link: https://meet.google.com/oph-xfrd-bnz
Date/Time: 6th June 2024 (Thursday), 3:30 PM
Title: Unsupervised Anomaly Detection in brain MRI using Transformer based Masked Autoencoders.

Abstract :

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 minimize the occurrence of pathological features, we propose to utilize an Autoencoder that deploys a masking strategy to reconstruct images. Additionally, the masked regions need to be meaningfully in-painted 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 generalization capability of the method in a cross-modality data setup.