Ogundipe, O., Zhai, B. orcid.org/0000-0003-1635-1406, Kurt, Z. orcid.org/0000-0003-3186-8091 et al. (1 more author) (2025) Explainable colon cancer stage prediction with multimodal biodata through the attention-based transformer and squeeze-excitation framework. Current Bioinformatics. ISSN 1574-8936
Abstract
Introduction: The heterogeneity in tumours poses significant challenges to the accurate prediction of cancer stages, necessitating the expertise of highly trained medical professionals for diagnosis. Over the past decade, the integration of deep learning into medical diagnostics, particularly for predicting cancer stages, has been hindered by the black-box nature of these algorithms, which complicates the interpretation of their decision-making processes.
Method: This study seeks to mitigate these issues by leveraging the complementary attributes found within functional genomics datasets (including mRNA, miRNA, and DNA methylation) and stained histopathology images. We introduced the Extended Squeeze- and-Excitation Multiheaded Attention (ESEMA) model, designed to harness these modalities. This model efficiently integrates and enhances the multimodal features, capturing biologically pertinent patterns that improve both the accuracy and interpretability of cancer stage predictions.
Result: Our findings demonstrate that the explainable classifier utilised the salient features of the multimodal data to achieve an area under the curve (AUC) of 0.9985, significantly surpassing the baseline AUCs of 0.8676 for images and 0.995 for genomic data.
Conclusion: Furthermore, the extracted genomics features were the most relevant for cancer stage prediction, suggesting that these identified genes are promising targets for further clinical investigation.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2025 Except as otherwise noted, this author-accepted version of a journal article published in Current Bioinformatics is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ |
Keywords: | Multimodal; Explainable; genomics; H&E Images; Attention model; features-relevance |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Social Sciences (Sheffield) > Information School (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 17 Mar 2025 16:03 |
Last Modified: | 17 Mar 2025 16:28 |
Status: | Published online |
Publisher: | Bentham Science Publishers Ltd. |
Refereed: | Yes |
Identification Number: | 10.2174/0115748936309582240907160359 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:224542 |
Download
Filename: 2nd_rev_BMS-CBIO-2024-58_07022024_unmarked.pdf
Licence: CC-BY 4.0