Combined Use of Texture Features and Morphological Classification Based on Dynamic Contrast-enhanced MR Imaging: Differentiating Benign and Malignant Breast Masses with High Negative Predictive Value

Abstract

We evaluated the diagnostic performance of the texture features of dynamic contrast-enhanced (DCE) MRI for breast cancer diagnosis in which the discriminator was optimized, so that the specificity was maximized via the restriction of the negative predictive value (NPV) to greater than 98%.Methods: Histologically proven benign and malignant mass lesions of DCE MRI were enrolled retrospectively. Training and testing sets consist of 166 masses (49 benign, 117 malignant) and 50 masses (15 benign, 35 malignant), respectively. Lesions were classified via MRI review by a radiologist into 4 shape types: smooth (S-type, 34 masses in training set and 8 masses in testing set), irregular without rim-enhancement (I-type, 60 in training and 14 in testing), irregular with rim-enhancement (R-type, 56 in training and 22 in testing), and spicula (16 in training and 6 in testing). Spicula were immediately classified as malignant. For the remaining masses, 298 texture features were calculated using a parametric map of DCE MRI in 3D mass regions. Masses were classified into malignant or benign using two thresholds on a feature pair. On the training set, several feature pairs and their thresholds were selected and optimized for each mass shape type to maximize specificity with the restriction of NPV > 98%. NPV and specificity were computed using the testing set by comparison with histopathologic results and averaged on the selected feature pairs. Results:In the training set, 27, 12, and 15 texture feature pairs are selected for S-type, I-type, and R-type masses, respectively, and thresholds are determined. In the testing set, average NPV and specificity using the selected texture features were 99.0% and 45.2%, respectively, compared to the NPV (85.7%) and specificity (40.0%) in visually assessed MRI category-based diagnosis. Conclusion:We, therefore, suggest that the NPV of our texture-based features method described performs similarly to or greater than the NPV of the MRI category-based diagnosis.

Multiparametric MRI

“…75 Radiomics has become one of the most popular analytical methods of multiparametric MRI, which is based on the extraction of potentially innumerable numbers of quantitative imaging metrics, or "radiomic features," which are difficult to be captured by the human eye. 76 Radiomic features are collectively used for the prediction of diagnosis, [77][78][79][80] classification, 37 prognostication, 81 assessment of treatment effects, 82 and gene expression profiling, among others. Focal lesions (eg, tumors) or other areas of concern are segmented to be used as regions of interest for extracting radiomic features.…”

Considerations for artificial intelligence clinical impact in oncologic imaging: an AI4HI position paper

“…There might be several clinical and legal issues in such a situation, such as (1) the patient died of the undiagnosed condition, (2) the disease progressed without being detected, (3) the disease progressed due to late detection, or (4) the disease failed to be treated due to the late detection. These aspects require elaboration while the AI algorithms become more precise and sensitive, such as the tool capable of predicting future breast cancer based on subtle image features [ 43 ]. These clinical issues concern physicians and their obligation to deliver the best possible care for their patients.…”