Deep learning-based breast lesion classification using treatment response assessment maps with uncertainty quantification.

Published in Journal of medical imaging (Bellingham, Wash.). Abstract: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is widely used for breast cancer diagnosis due to its high sensitivity; however, limited specificity often leads to false positives and unnecessary biopsies. Treatment response assessment maps (TRAMs), derived from delayed contrast-enhanced imaging, characterize contrast accumulation and clearance and may improve diagnostic specificity. We utilized the Advanced MRI Breast Lesions dataset from The Cancer Imaging Archive to develop deep learning-based models for breast lesion classification using both multiphase DCE-MRI and TRAM images. A 3D convolutional residual network (ResNet18) was employed for feature extraction, followed by a fully connected classifier. To assess prediction reliability, test-time augmentation was used to estimate aleatoric uncertainty. Radiomics-based models were also implemented for comparison. The TRAM-based deep learning model achieved numerically higher area under the receiver operating characteristic curve (0.870 versus 0.835), sensitivity (0.848 versus 0.818), and specificity (0.823 versus 0.759) compared with DCE-MRI. Radiomics analysis showed similar trends. Uncertainty stratification demonstrated improved performance in low-uncertainty predictions for both modalities, where high-uncertainty DCE-MRI predictions showed a marked performance decline compared with TRAM. These results suggest that TRAM-based deep learning models may provide a promising complementary imaging approach for br...

5 Key Takeaways

1. TRAM-based deep learning models achieved higher AUC, sensitivity, and specificity than DCE-MRI models.
2. Uncertainty stratification improved performance in low-uncertainty predictions for both modalities.
3. Integration of uncertainty quantification could enhance reliability of TRAM-based models.

OpenRounds transcript synthesis · Verify against the source