Exploring the Efficacy of Artificial Intelligence-Based Computer-Aided Detection for Breast Cancer Detection on...

Area of Science:

• Radiology
• Medical Imaging
• Artificial Intelligence in Medicine

Background:

• Mammography is a key tool for breast cancer screening.
• Early and accurate detection of breast cancer improves patient outcomes.
• Computer-aided detection (CAD) systems aim to enhance radiologist performance.

Purpose of the Study:

• To evaluate the efficacy of artificial intelligence-based computer-aided detection (AI-CAD) for identifying breast cancer in mammograms.
• To assess the concordance of AI-CAD findings with expert radiologists' assessments.
• To determine AI-CAD's performance in detecting mammographically occult breast cancers.

Main Methods:

• Retrospective analysis of mammograms from 269 women diagnosed with breast cancer.
• Radiologist consensus review for cancer visibility, mammographic findings, and BI-RADS categories.
• Evaluation of AI-CAD performance, including detection rates and concordance with radiologists.
• Analysis of AI-CAD detection rates based on lesion characteristics and cancer stage.

Main Results:

• AI-CAD detected 81.4% of all breast cancers.
• Higher detection rates were observed for larger lesions, high histologic grades, lymph node involvement, and advanced stages.
• Concordance between AI-CAD and radiologists was 88.5%; AI-CAD identified 19.4% of mammographically occult cancers.

Conclusions:

• AI-CAD demonstrates significant efficacy in detecting breast cancer on mammograms.
• The system shows substantial agreement with expert radiologists' interpretations.
• AI-CAD has the potential to improve the detection of subtle or occult breast cancers.