Monitoring Over Time of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Patients Through an Ensemble Vision Transformers-Based Model

IF 2.9 2区医学 Q2 ONCOLOGY

Cancer Medicine Pub Date : 2024-12-18 DOI:10.1002/cam4.70482

Maria Colomba Comes, Annarita Fanizzi, Samantha Bove, Luca Boldrini, Agnese Latorre, Deniz Can Guven, Serena Iacovelli, Tiziana Talienti, Alessandro Rizzo, Francesco Alfredo Zito, Raffaella Massafra

{"title":"Monitoring Over Time of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Patients Through an Ensemble Vision Transformers-Based Model","authors":"Maria Colomba Comes, Annarita Fanizzi, Samantha Bove, Luca Boldrini, Agnese Latorre, Deniz Can Guven, Serena Iacovelli, Tiziana Talienti, Alessandro Rizzo, Francesco Alfredo Zito, Raffaella Massafra","doi":"10.1002/cam4.70482","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Morphological and vascular characteristics of breast cancer can change during neoadjuvant chemotherapy (NAC). Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-acquired pre- and mid-treatment quantitatively capture information about tumor heterogeneity as potential earlier indicators of pathological complete response (pCR) to NAC in breast cancer.</p>\n </section>\n \n <section>\n \n <h3> Aims</h3>\n \n <p>This study aimed to develop an ensemble deep learning-based model, exploiting a Vision Transformer (ViT) architecture, which merges features automatically extracted from five segmented slices of both pre- and mid-treatment exams containing the maximum tumor area, to predict and monitor pCR to NAC.</p>\n </section>\n \n <section>\n \n <h3> Materials and Methods</h3>\n \n <p>Imaging data analyzed in this study referred to a cohort of 86 breast cancer patients, randomly split into training and test sets at a ratio of 8:2, who underwent NAC and for which information regarding the pCR status was available (37.2% of patients achieved pCR). We further validated our model using a subset of 20 patients selected from the publicly available I-SPY2 trial dataset (independent test).</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The performances of the proposed model were assessed using standard evaluation metrics, and promising results were achieved: area under the curve (AUC) value of 91.4%, accuracy value of 82.4%, a specificity value of 80.0%, a sensitivity value of 85.7%, precision value of 75.0%, F-score value of 80.0%, and G-mean value of 82.8%. The results obtained from the independent test show an AUC of 81.3%, an accuracy of 80.0%, a specificity value of 76.9%, a sensitivity of 85.0%, a precision of 66.7%, an F-score of 75.0%, and a G-mean of 81.2%.</p>\n </section>\n \n <section>\n \n <h3> Discussion</h3>\n \n <p>As far as we know, our research is the first proposal using ViTs on DCE-MRI exams to monitor pCR over time during NAC.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>Finally, the changes in DCE-MRI at pre- and mid-treatment could affect the accuracy of pCR prediction to NAC.</p>\n </section>\n </div>","PeriodicalId":139,"journal":{"name":"Cancer Medicine","volume":"13 24","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cam4.70482","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer Medicine","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/cam4.70482","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Morphological and vascular characteristics of breast cancer can change during neoadjuvant chemotherapy (NAC). Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI)-acquired pre- and mid-treatment quantitatively capture information about tumor heterogeneity as potential earlier indicators of pathological complete response (pCR) to NAC in breast cancer.

Aims

This study aimed to develop an ensemble deep learning-based model, exploiting a Vision Transformer (ViT) architecture, which merges features automatically extracted from five segmented slices of both pre- and mid-treatment exams containing the maximum tumor area, to predict and monitor pCR to NAC.

Materials and Methods

Imaging data analyzed in this study referred to a cohort of 86 breast cancer patients, randomly split into training and test sets at a ratio of 8:2, who underwent NAC and for which information regarding the pCR status was available (37.2% of patients achieved pCR). We further validated our model using a subset of 20 patients selected from the publicly available I-SPY2 trial dataset (independent test).

Results

The performances of the proposed model were assessed using standard evaluation metrics, and promising results were achieved: area under the curve (AUC) value of 91.4%, accuracy value of 82.4%, a specificity value of 80.0%, a sensitivity value of 85.7%, precision value of 75.0%, F-score value of 80.0%, and G-mean value of 82.8%. The results obtained from the independent test show an AUC of 81.3%, an accuracy of 80.0%, a specificity value of 76.9%, a sensitivity of 85.0%, a precision of 66.7%, an F-score of 75.0%, and a G-mean of 81.2%.

Discussion

As far as we know, our research is the first proposal using ViTs on DCE-MRI exams to monitor pCR over time during NAC.

Conclusion

Finally, the changes in DCE-MRI at pre- and mid-treatment could affect the accuracy of pCR prediction to NAC.

Abstract Image

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Cancer Medicine ONCOLOGY-

CiteScore

5.50

自引率

2.50%

发文量

907

审稿时长

19 weeks

期刊介绍： Cancer Medicine is a peer-reviewed, open access, interdisciplinary journal providing rapid publication of research from global biomedical researchers across the cancer sciences. The journal will consider submissions from all oncologic specialties, including, but not limited to, the following areas: Clinical Cancer Research Translational research ∙ clinical trials ∙ chemotherapy ∙ radiation therapy ∙ surgical therapy ∙ clinical observations ∙ clinical guidelines ∙ genetic consultation ∙ ethical considerations Cancer Biology: Molecular biology ∙ cellular biology ∙ molecular genetics ∙ genomics ∙ immunology ∙ epigenetics ∙ metabolic studies ∙ proteomics ∙ cytopathology ∙ carcinogenesis ∙ drug discovery and delivery. Cancer Prevention: Behavioral science ∙ psychosocial studies ∙ screening ∙ nutrition ∙ epidemiology and prevention ∙ community outreach. Bioinformatics: Gene expressions profiles ∙ gene regulation networks ∙ genome bioinformatics ∙ pathwayanalysis ∙ prognostic biomarkers. Cancer Medicine publishes original research articles, systematic reviews, meta-analyses, and research methods papers, along with invited editorials and commentaries. Original research papers must report well-conducted research with conclusions supported by the data presented in the paper.