Efficacy of Mammographic Artificial Intelligence-Based Computer-Aided Detection in Predicting Pathologic Complete...

Area of Science:

• Oncology
• Radiology
• Artificial Intelligence in Medicine

Background:

• Neoadjuvant chemotherapy (NAC) is a standard treatment for breast cancer.
• Accurate prediction of pathologic complete response (pCR) after NAC is crucial for treatment planning.
• Digital mammography plays a role in monitoring treatment response.

Purpose of the Study:

• To evaluate the potential of an AI-based computer-aided detection (AI-CAD) system in digital mammography for predicting pCR in breast cancer patients post-NAC.
• To compare the performance of AI-CAD with conventional CAD and other imaging modalities in predicting pCR.

Main Methods:

• Retrospective analysis of 132 breast cancer patients who received NAC.
• Analysis of pre- and post-NAC digital mammograms using conventional CAD and AI-CAD.
• Review of mammography, ultrasound, MRI, and diffusion-weighted imaging (DWI) by radiologists.
• Assessment of diagnostic performance, including concordance rates and AUC.

Main Results:

• AI-CAD showed high pre-NAC concordance (97%) and comparable post-NAC concordance (89.4%) to conventional CAD.
• MRI demonstrated the highest diagnostic performance for pCR prediction.
• AI-CAD was identified as a significant predictor of pCR in univariate analysis.

Conclusions:

• AI-CAD in digital mammography shows promise for evaluating pCR in breast cancer patients after NAC.
• While MRI remains a strong predictor, AI-CAD offers a valuable tool for assessing treatment response.
• Further research can explore the integration of AI-CAD into routine clinical practice for breast cancer management.