According to a study published in Radiology a radiomics technique that is based on diffusion weighted imaging with an adapted kurtosis model reduces false-positive results in both malignant and benign breast lesions when compared with x-ray mammography.
This institutional study included 222 women at two study sites (site 1: training set of 95 patients; mean age of 58.6 years; with 61 malignant and 34 benign lesions; and site 2: independent set of 127 patients; mean age, 58.2 years with 61 malignant with 66 benign lesions).
Among all 222 patients, histopathology results confirmed malignant lesions in 122 women (55%); invasive ductal carcinoma was the most common finding, in 90 patients (74%). Benign lesions were found in the remaining 100 women (45%); fibrosis (21 patients, 21%) and fibroadenoma (20 patients, 20%) were the most common abnormalities.
All women presented with findings suspicious for cancer at x-ray mammography (BI-RADS 4 or 5) and an indication for biopsy. Before biopsy, diffusion-weighted MR imaging (b values, 0–1500 sec/mm2) was performed by using 1.5-T imagers from different MR imaging vendors. Lesions were segmented and voxel-based kurtosis fitting adapted to account for fat signal contamination was performed. Conventional interpretations of MR imaging were also assessed for comparison.
The kurtosis radiomics model reduced false-positive results from 66 to 20 (specificity 70.0% [46 of 66]) at the predefined sensitivity of greater than 98.0% [60 of 61] in the independent test set, with BI-RADS 4a and 4b lesions benefiting from the analysis (specificity 74.0%, [37 of 50]; 60.0% [nine of 15]) and BI-RADS 5 lesions showing no added benefit. The model significantly improved specificity compared with the median apparent diffusion coefficient (P < .001) and apparent kurtosis coefficient (P = .02) alone. Conventional reading of dynamic contrast material–enhanced MR imaging provided sensitivity of 91.8% (56 of 61) and a specificity of 74.2% (49 of 66). Accounting for fat signal intensity during fitting significantly improved the area under the curve of the model (P = .001).
The authors concluded the radiomics model based on kurtosis diffusion-weighted imaging allowed for reliable differentiation between malignant and benign breast lesions.
