Transformer based Models for Unsupervised Anomaly Segmentation in Brain MR Images

07/05/2022
by   Ahmed Ghorbel, et al.
18

The quality of patient care associated with diagnostic radiology is proportionate to a physician workload. Segmentation is a fundamental limiting precursor to diagnostic and therapeutic procedures. Advances in Machine Learning (ML) aim to increase diagnostic efficiency to replace single application with generalized algorithms. In Unsupervised Anomaly Detection (UAD), Convolutional Neural Network (CNN) based Autoencoders (AEs) and Variational Autoencoders (VAEs) are considered as a de facto approach for reconstruction based anomaly segmentation. Looking for anomalous regions in medical images is one of the main applications that use anomaly segmentation. The restricted receptive field in CNNs limit the CNN to model the global context and hence if the anomalous regions cover parts of the image, the CNN-based AEs are not capable to bring semantic understanding of the image. On the other hand, Vision Transformers (ViTs) have emerged as a competitive alternative to CNNs. It relies on the self-attention mechanism that is capable to relate image patches to each other. To reconstruct a coherent and more realistic image, in this work, we investigate Transformer capabilities in building AEs for reconstruction based UAD task. We focus on anomaly segmentation for Brain Magnetic Resonance Imaging (MRI) and present five Transformer-based models while enabling segmentation performance comparable or superior to State-of-The-Art (SOTA) models. The source code is available on Github https://github.com/ahmedgh970/Transformers_Unsupervised_Anomaly_Segmentation.git

READ FULL TEXT

page 13

page 19

page 20

research
04/28/2021

Inpainting Transformer for Anomaly Detection

Anomaly detection in computer vision is the task of identifying images w...
research
08/14/2023

Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation

Vision transformers are effective deep learning models for vision tasks,...
research
08/26/2021

Evaluating Transformer based Semantic Segmentation Networks for Pathological Image Segmentation

Histopathology has played an essential role in cancer diagnosis. With th...
research
11/30/2022

Automated anomaly-aware 3D segmentation of bones and cartilages in knee MR images from the Osteoarthritis Initiative

In medical image analysis, automated segmentation of multi-component ana...
research
01/21/2022

SegTransVAE: Hybrid CNN – Transformer with Regularization for medical image segmentation

Current research on deep learning for medical image segmentation exposes...
research
09/25/2022

Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection

Anomaly detection has recently gained increasing attention in the field ...
research
03/31/2023

Unsupervised crack detection on complex stone masonry surfaces

Computer vision for detecting building pathologies has interested resear...

Please sign up or login with your details

Forgot password? Click here to reset