EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Classification of BI-RADS 4 and BI-RADS 5 Microcalcifications in Mammography Combined with DCE-MRI for Malignant–Benign Discrimination

Sevgi Ünal iD, Enes Açıkgözoğlu iD

Tomography · 17.06.2026 · 12 (6) · 88

DOI: 10.3390/tomography12060088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tomography, online erschienen am 17.06.2026. Verfasst von Sevgi Ünal und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Izmir Katip Celebi University Ataturk Training and Research Hospital, Izmir 35360, Turkey. Hauptthemen laut MEDLINE: Calcinosis, Mammography, Machine Learning, Breast Neoplasms. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide. Early and accurate characterization of suspicious mammographic microcalcifications is essential for improving diagnostic decision-making and reducing unnecessary invasive procedures. Microcalcifications classified as BI-RADS 4 and BI-RADS 5 are clinically important radiological findings; however, differentiating benign from malignant lesions remains challenging because of overlapping morphological and distribution patterns. This study aimed to develop a structured feature-based machine learning model for predicting the pathological diagnosis of breast microcalcifications by integrating mammographic descriptors, patient age, and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) contrast enhancement findings.

Methods

The dataset included 53 biopsy-confirmed cases and consisted of clinical and radiological variables, including patient age, calcification morphology, calcification size, distribution pattern, DCE-MRI contrast enhancement status, and histopathological outcome. Several conventional machine learning algorithms were evaluated, including Logistic Regression, Support Vector Machine with radial basis function kernel, K-Nearest Neighbors, Decision Tree, Random Forest, Extra Trees, Gradient Boosting, AdaBoost, and CatBoost. Hyperparameter optimization was performed using grid search with five-fold cross-validation. Model performance was assessed using accuracy, precision, recall, F1-score, ROC-AUC, and log loss.

Results

Logistic Regression achieved the highest overall performance, with an accuracy of 0.909 and an F1-score of 0.889, while AdaBoost achieved a recall of 1.000 in the internal evaluation. However, given the limited sample size and lack of external validation, these findings should be interpreted as preliminary.

Conclusions

The results suggest that structured radiological descriptors combined with DCE-MRI enhancement information may support malignancy risk stratification of BI-RADS 4–5 microcalcifications, although larger multicenter studies are required before clinical implementation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CalcinosisMammographyMachine LearningBreast NeoplasmsHumansFemaleDynamic Contrast Enhanced Magnetic Resonance ImagingMiddle AgedDiagnosis, DifferentialClassification AlgorithmsAgedAdultBoosting Machine Learning AlgorithmsPredictive Learning ModelsRandom ForestMagnetic Resonance ImagingBreast

Stichwörter der Autor:innen

BI-RADS classificationbreast cancercomputer-aided diagnosismachine learningmammographymedical image analysismicrocalcifications

Autor:innen und Institutionen

  • Department of Radiology, Izmir Katip Celebi University Ataturk Training and Research Hospital, Izmir 35360, Turkey.
  • Cloud Computing Operators, Isparta School of Information Technologies, Isparta University of Applied Sciences, Isparta 32200, Turkey.

ORCID-Profile: Sevgi Ünal, Enes Açıkgözoğlu

Zitieren

APA

Ünal, S., & Açıkgözoğlu, E. (2026). Machine Learning-Based Classification of BI-RADS 4 and BI-RADS 5 Microcalcifications in Mammography Combined with DCE-MRI for Malignant–Benign Discrimination. Tomography, 12(6), 88. https://doi.org/10.3390/tomography12060088

Vancouver

Ünal S, Açıkgözoğlu E. Machine Learning-Based Classification of BI-RADS 4 and BI-RADS 5 Microcalcifications in Mammography Combined with DCE-MRI for Malignant–Benign Discrimination. Tomography. 2026;12(6):88. doi:10.3390/tomography12060088

BibTeX
@article{nal2026,
  author = {Ünal, Sevgi and Açıkgözoğlu, Enes},
  title = {Machine Learning-Based Classification of BI-RADS 4 and BI-RADS 5 Microcalcifications in Mammography Combined with DCE-MRI for Malignant–Benign Discrimination},
  journal = {Tomography},
  year = {2026},
  volume = {12},
  number = {6},
  pages = {88},
  doi = {10.3390/tomography12060088}
}
Kostenlos starten →