摘要
Objective： To develop and validate a radiomic nomogram based on an apparent diffusion coefficient （ADC） mapfor differentiating benign and malignant lesions in suspicious breast findings classified as Breast Imaging Reportingand Data System （BI-RADS） category 4 on breast magnetic resonance imaging （MR2）.Methods： Eighty-eight patients diagnosed with BI-RADS 4 findings on breast MRI in the First AffiliatedHospital of China Medical University from December 2014 to December 2015 were retrospectively analyzed inthis study. Sixty-three were randomized electronically to establish forecasting models, and the other 25 were usedfor validation. Radiomic features based on the ADC map were generated automatically by Artificial Intelligence Kitsoftware （A.K. software; GE Healthcare, China）. Feature reduction was conducted using the Mann-Whitney testand Spearman correlation after pre-treatment. A prediction model of ADC radiomics was established by logisticlinear regression and cross-validation. A nomogram was established based on ADC radiomic features,pharmacokinetics and clinical features, including the morphology and ADC value for breast BI-RADS 4 lesionson MRI.Results： A total of 396 radiomic features were extracted automatically by the A.K. software. Five features wereselected after pre-processing, Mann-Whitney tests and Spearman correlation analysis. The area under the ROCcurve of the prediction model comprising ADC radiomie features was 0.79 when the cutoffvalue was 0.45, and theaccuracy, sensitivity and specificity were 80.0%, 0.813 and 0.778, respectively. A visualized differential nomogrambased on the radiomic score, pharmacokinetics and clinical features was established. The decision curve showedgood consistency.Conclusions： ADC radiomie features could provide an important reference for differential diagnosis betweenbenign and malignant lesions in suspicious BI-RADS 4 lesions. The visualized nomogram based on ADC radiomicfeatures, pharmaeokinetics and clinical features may have good prospects for clinical application.
Objective： To develop and validate a radiomic nomogram based on an apparent diffusion coefficient （ADC） mapfor differentiating benign and malignant lesions in suspicious breast findings classified as Breast Imaging Reportingand Data System （BI-RADS） category 4 on breast magnetic resonance imaging （MR2）.Methods： Eighty-eight patients diagnosed with BI-RADS 4 findings on breast MRI in the First AffiliatedHospital of China Medical University from December 2014 to December 2015 were retrospectively analyzed inthis study. Sixty-three were randomized electronically to establish forecasting models, and the other 25 were usedfor validation. Radiomic features based on the ADC map were generated automatically by Artificial Intelligence Kitsoftware （A.K. software; GE Healthcare, China）. Feature reduction was conducted using the Mann-Whitney testand Spearman correlation after pre-treatment. A prediction model of ADC radiomics was established by logisticlinear regression and cross-validation. A nomogram was established based on ADC radiomic features,pharmacokinetics and clinical features, including the morphology and ADC value for breast BI-RADS 4 lesionson MRI.Results： A total of 396 radiomic features were extracted automatically by the A.K. software. Five features wereselected after pre-processing, Mann-Whitney tests and Spearman correlation analysis. The area under the ROCcurve of the prediction model comprising ADC radiomie features was 0.79 when the cutoffvalue was 0.45, and theaccuracy, sensitivity and specificity were 80.0%, 0.813 and 0.778, respectively. A visualized differential nomogrambased on the radiomic score, pharmacokinetics and clinical features was established. The decision curve showedgood consistency.Conclusions： ADC radiomie features could provide an important reference for differential diagnosis betweenbenign and malignant lesions in suspicious BI-RADS 4 lesions. The visualized nomogram based on ADC radiomicfeatures, pharmaeokinetics and clinical features may have good prospects for clinical application.
基金
supported by Liaoning Science and Technology Office Project (No. 2012225013)
Youth Foundation of Natural Science Project (No. 81301222)
Special Project of Public Health Research (No.201402013)
