Computer-aided diagnosis of contrast-enhanced spectral mammography: A feasibility study. Issue 98 (January 2018)

• Record Type: Journal Article
• Authors: Patel, Bhavika K.; Ranjbar, Sara; Wu, Teresa; Pockaj, Barbara A.; Li, Jing; Zhang, Nan; Lobbes, Mark; Zhang, Bin; Mitchell, J. Ross
• Is Part Of: European journal of radiology. Issue 98(2018)
• Page Start: 207
• Page End: 213
• Publication Date: 2018-01
• Subjects: BIRADS Breast Imaging Reporting and Data Systems -- CAD computer aided diagnosis -- CC craniocaudal -- CEDM contrast-enhanced digital mammography -- CESM contrast-enhanced spectral mammography -- DICOM Digital Imaging and Communications in Medicine -- DOST discrete orthonormal Stockwell transform -- DE dual-energy -- FFDM full-field digital mammography -- GFB Gabor filter bank -- GLCM gray level co-occurrence matrices -- IRB institutional review board -- LBP local binary patterns -- LoGHist Laplacian-of-Gaussian histogram -- LOOCV leave-one-out–cross-validation -- MLO mediolateral oblique -- PASH pseudoangiomatous stromal hyperplasia -- PC principal component -- PCA principal component analysis -- ROC receiver operating characteristic -- ROI region of interest -- SFFS sequential forward feature selection -- SVM support vector machine; Breast cancer -- Computer-aided diagnosis -- Contrast-enhanced digital mammography -- Contrast-enhanced spectral mammography -- Quantitative image analysis; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2017.11.024
• Languages: English
• ISSNs: 0720-048X

Abstract

Abstract: Objective: To evaluate whether the use of a computer-aided diagnosis–contrast-enhanced spectral mammography (CAD-CESM) tool can further increase the diagnostic performance of CESM compared with that of experienced radiologists. Materials and methods: This IRB-approved retrospective study analyzed 50 lesions described on CESM from August 2014 to December 2015. Histopathologic analyses, used as the criterion standard, revealed 24 benign and 26 malignant lesions. An expert breast radiologist manually outlined lesion boundaries on the different views. A set of morphologic and textural features were then extracted from the low-energy and recombined images. Machine-learning algorithms with feature selection were used along with statistical analysis to reduce, select, and combine features. Selected features were then used to construct a predictive model using a support vector machine (SVM) classification method in a leave-one-out–cross-validation approach. The classification performance was compared against the diagnostic predictions of 2 breast radiologists with access to the same CESM cases. Results: Based on the SVM classification, CAD-CESM correctly identified 45 of 50 lesions in the cohort, resulting in an overall accuracy of 90%. The detection rate for the malignant group was 88% (3 false-negative cases) and 92% for the benign group (2 false-positive cases). Compared with the model, radiologist 1 had an overall accuracy of 78% and a detection rate of 92% (2 false-negative cases) for the malignant group and 62% (10 false-positive cases) for the benign group. Radiologist 2 had an overall accuracy of 86% and a detection rate of 100% for the malignant group and 71% (8 false-positive cases) for the benign group. Conclusions: The results of our feasibility study suggest that a CAD-CESM tool can provide complementary information to radiologists, mainly by reducing the number of false-positive findings.