Enhanced CATBraTS for Brain Tumour Semantic Segmentation

The early and precise identification of a brain tumour is imperative for enhancing a patient’s life expectancy; this can be facilitated by quick and efficient tumour segmentation in medical imaging. Automatic brain tumour segmentation tools in computer vision have integrated powerful deep learning a...

Full description

Saved in:
Bibliographic Details
Main Authors: Rim El Badaoui, Ester Bonmati Coll, Alexandra Psarrou, Hykoush A. Asaturyan, Barbara Villarini
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/11/1/8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832588260053876736
author Rim El Badaoui
Ester Bonmati Coll
Alexandra Psarrou
Hykoush A. Asaturyan
Barbara Villarini
author_facet Rim El Badaoui
Ester Bonmati Coll
Alexandra Psarrou
Hykoush A. Asaturyan
Barbara Villarini
author_sort Rim El Badaoui
collection DOAJ
description The early and precise identification of a brain tumour is imperative for enhancing a patient’s life expectancy; this can be facilitated by quick and efficient tumour segmentation in medical imaging. Automatic brain tumour segmentation tools in computer vision have integrated powerful deep learning architectures to enable accurate tumour boundary delineation. Our study aims to demonstrate improved segmentation accuracy and higher statistical stability, using datasets obtained from diverse imaging acquisition parameters. This paper introduces a novel, fully automated model called Enhanced Channel Attention Transformer (E-CATBraTS) for Brain Tumour Semantic Segmentation; this model builds upon 3D CATBraTS, a vision transformer employed in magnetic resonance imaging (MRI) brain tumour segmentation tasks. E-CATBraTS integrates convolutional neural networks and Swin Transformer, incorporating channel shuffling and attention mechanisms to effectively segment brain tumours in multi-modal MRI. The model was evaluated on four datasets containing 3137 brain MRI scans. Through the adoption of E-CATBraTS, the accuracy of the results improved significantly on two datasets, outperforming the current state-of-the-art models by a mean DSC of 2.6% while maintaining a high accuracy that is comparable to the top-performing models on the other datasets. The results demonstrate that E-CATBraTS achieves both high segmentation accuracy and elevated generalisation abilities, ensuring the model is robust to dataset variation.
format Article
id doaj-art-279fc51c231f423cb0bd8bc9063945c1
institution Kabale University
issn 2313-433X
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-279fc51c231f423cb0bd8bc9063945c12025-01-24T13:36:15ZengMDPI AGJournal of Imaging2313-433X2025-01-01111810.3390/jimaging11010008Enhanced CATBraTS for Brain Tumour Semantic SegmentationRim El Badaoui0Ester Bonmati Coll1Alexandra Psarrou2Hykoush A. Asaturyan3Barbara Villarini4School of Computer Science and Engineering, University of Westminster, London W1W 6UW, UKSchool of Computer Science and Engineering, University of Westminster, London W1W 6UW, UKSchool of Computer Science and Engineering, University of Westminster, London W1W 6UW, UKSchool of Computer Science and Engineering, University of Westminster, London W1W 6UW, UKSchool of Computer Science and Engineering, University of Westminster, London W1W 6UW, UKThe early and precise identification of a brain tumour is imperative for enhancing a patient’s life expectancy; this can be facilitated by quick and efficient tumour segmentation in medical imaging. Automatic brain tumour segmentation tools in computer vision have integrated powerful deep learning architectures to enable accurate tumour boundary delineation. Our study aims to demonstrate improved segmentation accuracy and higher statistical stability, using datasets obtained from diverse imaging acquisition parameters. This paper introduces a novel, fully automated model called Enhanced Channel Attention Transformer (E-CATBraTS) for Brain Tumour Semantic Segmentation; this model builds upon 3D CATBraTS, a vision transformer employed in magnetic resonance imaging (MRI) brain tumour segmentation tasks. E-CATBraTS integrates convolutional neural networks and Swin Transformer, incorporating channel shuffling and attention mechanisms to effectively segment brain tumours in multi-modal MRI. The model was evaluated on four datasets containing 3137 brain MRI scans. Through the adoption of E-CATBraTS, the accuracy of the results improved significantly on two datasets, outperforming the current state-of-the-art models by a mean DSC of 2.6% while maintaining a high accuracy that is comparable to the top-performing models on the other datasets. The results demonstrate that E-CATBraTS achieves both high segmentation accuracy and elevated generalisation abilities, ensuring the model is robust to dataset variation.https://www.mdpi.com/2313-433X/11/1/8brain tumourconvolutional neural networksemantic segmentationtransformertumour segmentation
spellingShingle Rim El Badaoui
Ester Bonmati Coll
Alexandra Psarrou
Hykoush A. Asaturyan
Barbara Villarini
Enhanced CATBraTS for Brain Tumour Semantic Segmentation
Journal of Imaging
brain tumour
convolutional neural network
semantic segmentation
transformer
tumour segmentation
title Enhanced CATBraTS for Brain Tumour Semantic Segmentation
title_full Enhanced CATBraTS for Brain Tumour Semantic Segmentation
title_fullStr Enhanced CATBraTS for Brain Tumour Semantic Segmentation
title_full_unstemmed Enhanced CATBraTS for Brain Tumour Semantic Segmentation
title_short Enhanced CATBraTS for Brain Tumour Semantic Segmentation
title_sort enhanced catbrats for brain tumour semantic segmentation
topic brain tumour
convolutional neural network
semantic segmentation
transformer
tumour segmentation
url https://www.mdpi.com/2313-433X/11/1/8
work_keys_str_mv AT rimelbadaoui enhancedcatbratsforbraintumoursemanticsegmentation
AT esterbonmaticoll enhancedcatbratsforbraintumoursemanticsegmentation
AT alexandrapsarrou enhancedcatbratsforbraintumoursemanticsegmentation
AT hykoushaasaturyan enhancedcatbratsforbraintumoursemanticsegmentation
AT barbaravillarini enhancedcatbratsforbraintumoursemanticsegmentation