Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation

<p dir="ltr">The ability to predict breast cancer metastases is essential for making effective clinical decisions and managing patients. Traditional models predominantly rely on structured clinical data, which often lacks essential contextual details, limiting their predictive accura...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Faseela Abdullakutty (22564814) (author)
مؤلفون آخرون: Younes Akbari (16303286) (author), Somaya Al-Maadeed (5178131) (author), Ahmed Bouridane (2270131) (author), Rifat Rifat Hamoudi (22564817) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513533202399232
author Faseela Abdullakutty (22564814)
author2 Younes Akbari (16303286)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Rifat Rifat Hamoudi (22564817)
author2_role author
author
author
author
author_facet Faseela Abdullakutty (22564814)
Younes Akbari (16303286)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Rifat Rifat Hamoudi (22564817)
author_role author
dc.creator.none.fl_str_mv Faseela Abdullakutty (22564814)
Younes Akbari (16303286)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Rifat Rifat Hamoudi (22564817)
dc.date.none.fl_str_mv 2025-06-06T03:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s12559-025-10474-6
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Enhancing_the_Prediction_of_Breast_Cancer_Progression_Through_Multi-modal_Data_Transformation/30540857
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Breast cancer metastasis
Synthetic data generation
Multi-modality
Multi Co-Guided Attention (MCGA)
dc.title.none.fl_str_mv Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The ability to predict breast cancer metastases is essential for making effective clinical decisions and managing patients. Traditional models predominantly rely on structured clinical data, which often lacks essential contextual details, limiting their predictive accuracy. In order to address this limitation, a multi-modal approach is introduced in which structured data is transformed into unstructured text, while contextual richness is preserved. Using this text, synthetic images are generated across three key diagnostic modalities, histopathology, mammography, and ultrasound, to enhance predictive capabilities. Based on converted text data, a pre-trained diffusion model was used to generate synthetic medical images in histopathology, mammography, and ultrasound modalities. The impact of a variety of text description variants on image quality and metastasis prediction was assessed. Comprehensive tumor descriptions or a combination of histological type and differentiation status were the most effective generation strategies. A comparison was conducted between three prediction approaches: a unimodal approach, an early fusion approach based on concatenation, and the Multi Co-Guided Attention (MCGA) approach. Through mutual attention, MCGA enhances feature alignment by addressing inter- and intra-modal heterogeneity and capturing complex relationships. Unimodal and multi-modal methods were evaluated with the application of SMOTE to mitigate the impact of data imbalance. Multi-modal fusion significantly outperforms unimodal methods, especially when class imbalances are mitigated by using SMOTE. When SMOTE was applied, Ultrasound+BERT achieved the highest level of accuracy (0.90), followed by Histopathology+BERT (0.88), and Mammogram+BERT (0.88). As compared to early fusion, MCGA demonstrated better class balance and improved minority class detection. Incorporating unstructured text with synthetic imaging modalities improves the accuracy of metastasis prediction by preserving contextual information. A MCGA fusion is particularly effective in ensuring balanced class performance, particularly for rectifying class imbalances. Through this approach, the complementary strengths of textual and visual data are leveraged to overcome limitations in multi-modality integration. These results demonstrate the potential for advancing the prediction of breast cancer metastasis, offering a more robust and context-aware framework for clinical decision-making.</p><h2>Other Information</h2><p dir="ltr">Published in: Cognitive Computation<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s12559-025-10474-6" target="_blank">https://dx.doi.org/10.1007/s12559-025-10474-6</a></p>
eu_rights_str_mv openAccess
id Manara2_9b822f07c97d858d80b1978fdfe52a5f
identifier_str_mv 10.1007/s12559-025-10474-6
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30540857
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data TransformationFaseela Abdullakutty (22564814)Younes Akbari (16303286)Somaya Al-Maadeed (5178131)Ahmed Bouridane (2270131)Rifat Rifat Hamoudi (22564817)Biomedical and clinical sciencesOncology and carcinogenesisHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceMachine learningBreast cancer metastasisSynthetic data generationMulti-modalityMulti Co-Guided Attention (MCGA)<p dir="ltr">The ability to predict breast cancer metastases is essential for making effective clinical decisions and managing patients. Traditional models predominantly rely on structured clinical data, which often lacks essential contextual details, limiting their predictive accuracy. In order to address this limitation, a multi-modal approach is introduced in which structured data is transformed into unstructured text, while contextual richness is preserved. Using this text, synthetic images are generated across three key diagnostic modalities, histopathology, mammography, and ultrasound, to enhance predictive capabilities. Based on converted text data, a pre-trained diffusion model was used to generate synthetic medical images in histopathology, mammography, and ultrasound modalities. The impact of a variety of text description variants on image quality and metastasis prediction was assessed. Comprehensive tumor descriptions or a combination of histological type and differentiation status were the most effective generation strategies. A comparison was conducted between three prediction approaches: a unimodal approach, an early fusion approach based on concatenation, and the Multi Co-Guided Attention (MCGA) approach. Through mutual attention, MCGA enhances feature alignment by addressing inter- and intra-modal heterogeneity and capturing complex relationships. Unimodal and multi-modal methods were evaluated with the application of SMOTE to mitigate the impact of data imbalance. Multi-modal fusion significantly outperforms unimodal methods, especially when class imbalances are mitigated by using SMOTE. When SMOTE was applied, Ultrasound+BERT achieved the highest level of accuracy (0.90), followed by Histopathology+BERT (0.88), and Mammogram+BERT (0.88). As compared to early fusion, MCGA demonstrated better class balance and improved minority class detection. Incorporating unstructured text with synthetic imaging modalities improves the accuracy of metastasis prediction by preserving contextual information. A MCGA fusion is particularly effective in ensuring balanced class performance, particularly for rectifying class imbalances. Through this approach, the complementary strengths of textual and visual data are leveraged to overcome limitations in multi-modality integration. These results demonstrate the potential for advancing the prediction of breast cancer metastasis, offering a more robust and context-aware framework for clinical decision-making.</p><h2>Other Information</h2><p dir="ltr">Published in: Cognitive Computation<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s12559-025-10474-6" target="_blank">https://dx.doi.org/10.1007/s12559-025-10474-6</a></p>2025-06-06T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s12559-025-10474-6https://figshare.com/articles/journal_contribution/Enhancing_the_Prediction_of_Breast_Cancer_Progression_Through_Multi-modal_Data_Transformation/30540857CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/305408572025-06-06T03:00:00Z
spellingShingle Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
Faseela Abdullakutty (22564814)
Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Breast cancer metastasis
Synthetic data generation
Multi-modality
Multi Co-Guided Attention (MCGA)
status_str publishedVersion
title Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
title_full Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
title_fullStr Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
title_full_unstemmed Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
title_short Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
title_sort Enhancing the Prediction of Breast Cancer Progression Through Multi-modal Data Transformation
topic Biomedical and clinical sciences
Oncology and carcinogenesis
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Machine learning
Breast cancer metastasis
Synthetic data generation
Multi-modality
Multi Co-Guided Attention (MCGA)