EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features

Giulio Del Corso, Danila Germanese, Claudia Caudai iD, Giada Anastasi, Paolo Belli, Alessia Formica, Alberto Nicolucci, Simone Palma, Maria Antonietta Pascali, Stefania Pieroni, Charlotte Trombadori, Sara Colantonio und 2 weitere

Journal of Imaging Informatics in Medicine · 2024

DOI: 10.1007/s10278-024-01064-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2024. Verfasst von Giulio Del Corso und 13 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Science and Technologies "A. Faedo" (ISTI), National Research Council of Italy (CNR), Pisa, Italy. giulio.delcorso@isti.cnr.…. Hauptthemen laut MEDLINE: Breast Neoplasms, Machine Learning, Mammography. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Consiglio Nazionale Delle Ricerche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer holds the highest diagnosis rate among female tumors and is the leading cause of death among women. Quantitative analysis of radiological images shows the potential to address several medical challenges, including the early detection and classification of breast tumors. In the P.I.N.K study, 66 women were enrolled. Their paired Automated Breast Volume Scanner (ABVS) and Digital Breast Tomosynthesis (DBT) images, annotated with cancerous lesions, populated the first ABVS+DBT dataset. This enabled not only a radiomic analysis for the malignant vs. benign breast cancer classification, but also the comparison of the two modalities. For this purpose, the models were trained using a leave-one-out nested cross-validation strategy combined with a proper threshold selection approach. This approach provides statistically significant results even with medium-sized data sets. Additionally it provides distributional variables of importance, thus identifying the most informative radiomic features. The analysis proved the predictive capacity of radiomic models even using a reduced number of features. Indeed, from tomography we achieved AUC-ROC $$89.9\%$$ 89.9 % using 19 features and $$92.1\%$$ 92.1 % using 7 of them; while from ABVS we attained an AUC-ROC of $$72.3\%$$ 72.3 % using 22 features and $$85.8\%$$ 85.8 % using only 3 features. Although the predictive power of DBT outperforms ABVS, when comparing the predictions at the patient level, only 8.7% of lesions are misclassified by both methods, suggesting a partial complementarity. Notably, promising results (AUC-ROC ABVS-DBT $$71.8\%$$ 71.8 % - $$74.1\%$$ 74.1 % ) were achieved using non-geometric features, thus opening the way to the integration of virtual biopsy in medical routine.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsMachine LearningMammographyHumansFemaleMiddle AgedAgedAdultBreastRadiographic Image Interpretation, Computer-AssistedRadiomics

Stichwörter der Autor:innen

Adaptive feature selectionBreast cancerModel reductionRadiomic

Autor:innen und Institutionen

  • Institute of Information Science and Technologies "A. Faedo" (ISTI), National Research Council of Italy (CNR), Pisa, Italy. giulio.delcorso@isti.cnr.it.
  • Institute of Information Science and Technologies "A. Faedo" (ISTI), National Research Council of Italy (CNR), Pisa, Italy.
  • Institute of Clinical Physiology (IFC), National Research Council of Italy (CNR), Pisa, Italy.
  • Department of Computer Science, University of Pisa, Pisa, Italy.
  • Policlinico Gemelli IRCCS, Rome, Italy.
  • Università Cattolica del Sacro Cuore, Rome, Italy.

ORCID-Profile: Claudia Caudai

Förderung

  • Consiglio Nazionale Delle Ricerche

Zitieren

APA

Del Corso, G., Germanese, D., Caudai, C., Anastasi, G., Belli, P., Formica, A., Nicolucci, A., Palma, S., Pascali, M. A., Pieroni, S., Trombadori, C., Colantonio, S., Franchini, M., & Molinaro, S. (2024). Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01064-3

Vancouver

Del Corso G, Germanese D, Caudai C, Anastasi G, Belli P, Formica A, et al. Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features. Journal of Imaging Informatics in Medicine. 2024. doi:10.1007/s10278-024-01064-3

BibTeX
@article{DelCorso2024,
  author = {Del Corso, Giulio and Germanese, Danila and Caudai, Claudia and Anastasi, Giada and Belli, Paolo and Formica, Alessia and Nicolucci, Alberto and Palma, Simone and Pascali, Maria Antonietta and Pieroni, Stefania and Trombadori, Charlotte and Colantonio, Sara and Franchini, Michela and Molinaro, Sabrina},
  title = {Adaptive Machine Learning Approach for Importance Evaluation of Multimodal Breast Cancer Radiomic Features},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2024},
  doi = {10.1007/s10278-024-01064-3}
}
Kostenlos starten →