Exploration of the efficacy of radiomics applied to left ventricular tomograms obtained from D-SPECT MPI for the auxiliary diagnosis of myocardial ischemia in CAD

• Published in: The International Journal of Cardiovascular Imaging 2022-02, Vol.38 (2), p.465-472
• Main Authors: Wang, Junpeng, Fan, Xin, Qin, ShanShan, Shi, Kuangyu, Zhang, Han, Yu, Fei
• Format: Article
• Language: English
• Subjects: Annotations; Cardiac Imaging; Cardiology; Cardiovascular disease; Classification; Coronary Angiography - methods; Coronary artery; Coronary artery disease; Coronary Artery Disease - diagnostic imaging; Coronary Artery Disease - therapy; Desensitization; Diagnosis; Evaluation; Heart; Heart diseases; Humans; Image classification; Image segmentation; Imaging; Information processing; Ischemia; Likelihood ratio; Medical imaging; Medicine; Medicine & Public Health; Metric space; Myocardial ischemia; Myocardial Ischemia - diagnostic imaging; Myocardial Perfusion Imaging - methods; Original Paper; Perfusion; Predictive Value of Tests; Radiology; Radiomics; Retrospective Studies; Single photon emission computed tomography; Tomography, Emission-Computed, Single-Photon - methods; Training; Ventricle
• ISSN: 1569-5794; 1573-0743; 1875-8312
• DOI: 10.1007/s10554-021-02413-x

To explore the feasibility and efficacy of radiomics with left ventricular tomograms obtained from D-SPECT myocardial perfusion imaging (MPI) for auxiliary diagnosis of myocardial ischemia in coronary artery disease (CAD). The images of 103 patients with CAD myocardial ischemia between September 2020 and April 2021 were retrospectively selected. After information desensitization processing, format conversion, annotation using the Labelme tool on an open-source platform, lesion classification, and establishment of a database, the images were cropped for analysis. The ResNet18 model was used to automate two steps (classification and segmentation) with five randomization, training and validation steps. The sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, positive predictive value, negative predictive value, Youden’s index, agreement rate, and kappa value were calculated as evaluation indexes of the classification results for each training-validation step; then, receiver operating characteristics (ROC) curves were drawn, and the areas under the curve (AUCs) were calculated. The Dice coefficient, intersection over union, and Hausdorff distance were calculated as evaluation indexes of the segmentation results for each training-validation step; then, the predicted images were exported. Under the existing conditions, the radiomics model used in this study had an AUC above 0.95 in identifying the presence or absence of myocardial ischemia; in the prediction of the extent of myocardial ischemia, its evaluation index distribution is also close to that of the gold standard. Radiomics can be feasibly applied to left ventricular tomograms obtained from D-SPECT MPI for auxiliary diagnosis. With more in-depth research and the development of technology, adding this method to the existing auxiliary diagnosis will likely further improve the diagnostic accuracy and efficiency, and patients will therefore benefit.