What type of study is this?

September 17, 2025

Machine Learning-Based Automating Breast Cancer Detection and Classification using DWI

Key Points

Significant diagnostic performance was achieved through machine learning approaches, indicating effective automation in breast cancer detection.
The whole-slice method provided an AUC of 0.90 with sensitivity and specificity of 84.4% and 84.0%, respectively.
Utilizing YOLO v5 and a 2D CNN for malignancy assessment, the analysis was conducted on data from 601 patients.
Findings highlight the potential of AI integration to enhance screening efficiency and reduce false positives in breast cancer diagnostics.

Abstract

Motivation: Breast MRI's subotimal specificity and labor-intensive DWI interpretation call for automated diagnostic solutions. Goal(s): Investigate effectiveness of AI integration for breast tumor detection and characterization in DWI. Approach: Retrospective analysis of 601 patients. Fine-tuned YOLO v5 for tumor identification and 2D CNN for malignancy assessment, utilizing whole-slice and bounding box techniques. Results: Strong diagnostic performance observed. Whole-slice method: AUC 0.90, sensitivity 84.4%, specificity 84.0%. Bounding box method: AUC 0.87, sensitivity 87.5%, specificity 80.0%. Impact: Potential to boost screening efficiency, minimize false positives, and improve patient care via more precise, swift diagnoses.

Bookmark

Machine Learning-Based Automating Breast Cancer Detection and Classification using DWI

Key Points

Abstract

Cite This Study

Also Consider

Also Consider