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 falsenegative 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.
Objectives
Due to its high sensitivity, DCE MRI of the breast (MRIb) is increasingly used for both screening and assessment purposes. The Kaiser score (KS) is a clinical decision algorithm, which formalizes and guides diagnosis in breast MRI and is expected to compensate for lesser reader experience. The aim was to evaluate the diagnostic performance of untrained residents using the KS compared to off-site radiologists experienced in breast imaging using only MR BI-RADS.
Methods
Three off-site, board-certified radiologists, experienced in breast imaging, interpreted MRIb according to the MR BI-RADS scale. The same studies were read by three residents in radiology without prior training in breast imaging using the KS. All readers were blinded to clinical information. Histology was used as the gold standard. Statistical analysis was conducted by comparing the AUC of the ROC curves.
Results
A total of 80 women (median age 52 years) with 93 lesions (32 benign, 61 malignant) were included. The individual within-group performance of the three expert readers (AUC 0.723–0.742) as well as the three residents was equal (AUC 0.842–0.928), p > 0.05, respectively. But, the rating of each resident using the KS significantly outperformed the experts’ ratings using the MR BI-RADS scale (p ≤ 0.05).
Conclusion
The KS helped residents to achieve better results in reaching correct diagnoses than experienced radiologists empirically assigning MR BI-RADS categories in a clinical “problem solving MRI” setting. These results support that reporting breast MRI benefits more from using a diagnostic algorithm rather than expert experience.
Key Points
• Reporting breast MRI benefits more from using a diagnostic algorithm rather than expert experience in a clinical “problem solving MRI” setting.
• The Kaiser score, which provides a clinical decision algorithm for structured reporting, helps residents to reach an expert level in breast MRI reporting and to even outperform experienced radiologists using MR BI-RADS without further formal guidance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.