Combined texture analysis and machine learning in suspicious calcifications detected by mammography: Potential to avoid unnecessary stereotactical biopsies. Issue 132 (November 2020)

• Record Type: Journal Article
• Authors: Stelzer, P.D.; Steding, O.; Raudner, M.W.; Euller, G.; Clauser, P.; Baltzer, P.A.T.
• Is Part Of: European journal of radiology. Issue 132(2020)
• Publication Date: 2020-11
• Subjects: Breast neoplasms -- Mammography -- Calcifications -- Image-guided biopsy -- Machine-learning -- Texture analysis; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2020.109309
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: Combined texture analysis and machine-learning can diagnose malignancy in mammographic BI-RADS 4 calcifications. The machine-learning classifier demonstrated the potential to avoid more than one third of unnecessary biopsies. A rule-out criterion to exclude malignancy with high certainty was identified and successfully tested. Abstract: Objectives: To investigate whether combined texture analysis and machine learning can distinguish malignant from benign suspicious mammographic calcifications, to find an exploratory rule-out criterion to potentially avoid unnecessary benign biopsies. Methods: Magnification views of 235 patients which underwent vacuum-assisted biopsy of suspicious calcifications (BI-RADS 4) during a two-year period were retrospectively analyzed using the texture analysis tool MaZda (Version 4.6). Microcalcifications were manually segmented and analyzed by two readers, resulting in 249 image features from gray-value histogram, gray-level co-occurrence and run-length matrices. After feature reduction with principal component analysis (PCA), a multilayer perceptron (MLP) artificial neural network was trained using histological results as the reference standard. For training and testing of this model, the dataset was split into 70 % and 30 %. ROC analysis was used to calculate diagnostic performance indices. Results: 226 patients (150 benign, 76 malignant) were included in the final analysis due to missing data in 9 cases. Feature selection yielded nine image features for MLP training. Area under the ROC-curve in the testing dataset (n = 54) was 0.82 (95 %-CI: 0.70−0.94) and 0.832 (95 %-CI 0.72−0.94) for both readers, respectively. A high sensitivity threshold criterion was identified in the training dataset and successfully applied to the testing dataset, demonstrating the potential to avoid 37.1–45.7 % of unnecessary biopsies at the cost of one false-negative for each reader. Conclusion: Combined texture analysis and machine learning could be used for risk stratification in suspicious mammographic calcifications. At low costs in terms of false-negatives, unnecessary biopsies could be avoided.