Transformer-Based Explainable Model for Breast Cancer Lesion Segmentation

Simple item page
dc.citation.issue3
dc.citation.volume15
dc.contributor.authorWang H
dc.contributor.authorWei L
dc.contributor.authorLiu B
dc.contributor.authorLi J
dc.contributor.authorLi J
dc.contributor.authorFang J
dc.contributor.authorMooney C
dc.contributor.editorGegov A
dc.contributor.editorJafari R
dc.contributor.editorArabikhan F
dc.date.accessioned2025-03-10T01:06:44Z
dc.date.available2025-03-10T01:06:44Z
dc.date.issued2025-01-27
dc.description.abstractBreast cancer is one of the most prevalent cancers among women, with early detection playing a critical role in improving survival rates. This study introduces a novel transformer-based explainable model for breast cancer lesion segmentation (TEBLS), aimed at enhancing the accuracy and interpretability of breast cancer lesion segmentation in medical imaging. TEBLS integrates a multi-scale information fusion approach with a hierarchical vision transformer, capturing both local and global features by leveraging the self-attention mechanism. This model addresses the limitations of existing segmentation methods, such as the inability to effectively capture long-range dependencies and fine-grained semantic information. Additionally, TEBLS incorporates visualization techniques to provide insights into the segmentation process, enhancing the model’s interpretability for clinical use. Experiments demonstrate that TEBLS outperforms traditional and existing deep learning-based methods in segmenting complex breast cancer lesions with variations in size, shape, and texture, achieving a mean DSC of 81.86% and a mean AUC of 97.72% on the CBIS-DDSM test set. Our model not only improves segmentation accuracy but also offers a more explainable framework, which has the potential to be used in clinical settings.
dc.description.confidentialfalse
dc.edition.editionFebruary-1 2025
dc.identifier.citationWang H, Wei L, Liu B, Li J, Li J, Fang J, Mooney C. (2025). Transformer-Based Explainable Model for Breast Cancer Lesion Segmentation. Applied Sciences (Switzerland). 15. 3.
dc.identifier.doi10.3390/app15031295
dc.identifier.eissn2076-3417
dc.identifier.elements-typejournal-article
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/72605
dc.languageEnglish
dc.publisherMDPI (Basel, Switzerland)
dc.publisher.urihttp://mdpi.com/2076-3417/15/3/1295
dc.relation.isPartOfApplied Sciences (Switzerland)
dc.rights(c) 2025 The Author/s
dc.rightsCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectbreast cancer lesion segmentation
dc.subjecttransformer
dc.subjectexplainable model
dc.titleTransformer-Based Explainable Model for Breast Cancer Lesion Segmentation
dc.typeJournal article
pubs.elements-id499923
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
499923 PDF.pdf
Size:
2.56 MB
Format:
Adobe Portable Document Format
Description:
Evidence
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
9.22 KB
Format:
Plain Text
Description:
Download
Collections
Journal Articles