Automated Breast Density Assessment in MRI Using Deep Learning and Radiomics: Strategies for Reducing Inter‐Observer Variability

Abstract

BackgroundAccurate breast density evaluation allows for more precise risk estimation but suffers from high inter‐observer variability.PurposeTo evaluate the feasibility of reducing inter‐observer variability of breast density assessment through artificial intelligence (AI) assisted interpretation.Study TypeRetrospective.PopulationSix hundred and twenty‐one patients without breast prosthesis or reconstructions were randomly divided into training (N = 377), validation (N = 98), and independent test (N = 146) datasets.Field Strength/Sequence1.5 T and 3.0 T; T1‐weighted spectral attenuated inversion recovery.AssessmentFive radiologists independently assessed each scan in the independent test set to establish the inter‐observer variability baseline and to reach a reference standard. Deep learning and three radiomics models were developed for three classification tasks: (i) four Breast Imaging‐Reporting and Data System (BI‐RADS) breast composition categories (A–D), (ii) dense (categories C, D) vs. non‐dense (categories A, B), and (iii) extremely dense (category D) vs. moderately dense (categories A–C). The models were tested against the reference standard on the independent test set. AI‐assisted interpretation was performed by majority voting between the models and each radiologist's assessment.Statistical TestsInter‐observer variability was assessed using linear‐weighted kappa (κ) statistics. Kappa statistics, accuracy, and area under the receiver operating characteristic curve (AUC) were used to assess models against reference standard.ResultsIn the independent test set, five readers showed an overall substantial agreement on tasks (i) and (ii), but moderate agreement for task (iii). The best‐performing model showed substantial agreement with reference standard for tasks (i) and (ii), but moderate agreement for task (iii). With the assistance of the AI models, almost perfect inter‐observer variability was obtained for tasks (i) (mean κ = 0.86), (ii) (mean κ = 0.94), and (iii) (mean κ = 0.94).Data ConclusionDeep learning and radiomics models have the potential to help reduce inter‐observer variability of breast density assessment.Level of Evidence3Technical EfficacyStage 1

Editorial for “Automated Breast Density Assessment in MRI Using Deep Learning and Radiomics: Strategies for Reducing Inter‐Observer Variability”

“…In the most recent issue of JMRI, Jing et al 7 present an innovative approach to address the intricacies involved in breast density assessment of magnetic resonance imaging (MRI) images by leveraging AI techniques. Their retrospective study encompasses a cohort of 621 patients, where a DL model was constructed based on the 3D convolutional neural network of EfficientNet 8 architecture.…”

“…By harnessing the potential of AI technology and fostering interdisciplinary collaboration, we can pave the way for more accurate and personalized breast cancer diagnosis and management, ultimately leading to improved patient outcomes. While the full integration of AI-assisted interpretation into clinical practice is yet to be determined, the publication by Jing et al 7 serves as an important step in that direction. The integration of AI into clinical imaging practice has the potential to revolutionize breast cancer care by providing more accurate risk estimation and guiding personalized screening and treatment strategies.…”