Click here to

Session: Breast Imaging [Return to Session]

Case-Based Repeatability of AI Classification On Multi-Modality Imaging of Breast Lesions Using DCE-MRI and FFDM

H Whitney1,2*, K Drukker1, H Li1, A Edwards1, L Lan1, H Abe1, M Giger1, (1) University of Chicago, Chicago, IL, (2) Wheaton College, Wheaton, IL

Presentations

MO-E115-IePD-F8-5 (Monday, 7/11/2022) 1:15 PM - 1:45 PM [Eastern Time (GMT-4)]

Exhibit Hall | Forum 8

Purpose: Characterization of case-based repeatability can complement CADx performance metrics. We investigated case-based repeatability of classification of breast lesions as malignant or benign using multi-modality human-engineered radiomic features extracted from both dynamic contrast-enhanced magnetic resonance (DCE-MR) and full field digital mammography (FFDM) images.

Methods: The database was comprised of 78 lesions (8 benign, 70 malignant) for which both DCE-MR and FFDM images were available, one lesion per case. Twenty-eight DCE-MR features describing shape, morphology, texture, and kinetics of contrast enhancement and 32 FFDM features describing size, shape, margin, and texture were extracted after the lesions had been segmented using previously established methods. FFDM features for each lesion were averaged across all views available. Case-based repeatability was investigated for three scenarios: (1) DCE-MR features alone, (2) FFDM features alone, and (3) all features (i.e., multi-modality). The case-based repeatability profile for each scenario was developed by separating features into training and test folds by case using a 0.632 bootstrap with 200 iterations. A random forest classifier from each training fold was applied to each test fold, resulting in the posterior probability of malignancy for each case, called the case-based output (CBO). The CBO was scaled to 50% prevalence. The median CBO and the width of its 95% CI (95CI(CBO)) was determined for each case across bootstrap folds. 95CI(CBO) was also reviewed for each pairwise comparison of features used for classification, assessed using the coefficient of determination (R²).

Results: Using multi-modality features somewhat modified the case-based repeatability profile for the lesions. It also increased the repeatability of some cases but decreased it for others. The 95CI(CBO) of individual cases demonstrated little correlation between modalities (R² = 0.004).

Conclusion: This pilot study demonstrates that classification of breast lesions using multi-modality human-engineered radiomic features may change case-based repeatability, and further studies are warranted.

Funding Support, Disclosures, and Conflict of Interest: NIH NCI Grant U01 CA195564 and Grant R15 CA227948, NIH Grant S10 OD025081. MLG is a stockholder in R2 Technology/Hologic, was a cofounder/equity holder in Quantitative Insights (now Qlarity Imaging), and receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi, and Toshiba. KD receives royalties from Hologic.

Keywords

CAD, Statistical Analysis, Quantitative Imaging

Taxonomy

IM- Dataset Analysis/Biomathematics: Machine learning

Contact Email

Share: