A Transparent Machine Learning Approach Using Ultrasound Radiomics for Preoperative Distinction Between Granulomatous Lobular Mastitis and Breast Cancer - Summary - MDSpire
Advertisement
A Transparent Machine Learning Approach Using Ultrasound Radiomics for Preoperative Distinction Between Granulomatous Lobular Mastitis and Breast Cancer
To develop an interpretable machine learning model utilizing ultrasound radiomics for distinguishing between granulomatous lobular mastitis and breast cancer.
Key Findings:
Combined model achieved AUC of 0.935 in training cohort and 0.833 in validation cohort.
DCA indicated favorable clinical applicability.
Key radiomic features correlated with predictions include lbp_3D_k_glszm_SmallAreaLowGrayLevelEmphasis and others.
Interpretation:
The combined model effectively differentiates between granulomatous lobular mastitis and breast cancer, enhancing diagnostic precision and clinical decision-making.
Limitations:
Retrospective design may introduce bias.
Single-center study limits generalizability.
Conclusion:
The combined ultrasound radiomics and clinical factors model shows significant efficacy in preoperatively distinguishing granulomatous lobular mastitis from breast cancer.
