Automated Classification of Atherosclerotic Radiomics Features in Coronary Computed Tomography Angiography (CCTA)

Abstract

Radiomics is the process of extracting useful quantitative features of high-dimensional data that allows for automated disease classification, including atherosclerotic disease. Hence, this study aimed to quantify and extract the radiomic features from Coronary Computed Tomography Angiography (CCTA) images and to evaluate the performance of automated machine learning (AutoML) model in classifying the atherosclerotic plaques. In total, 202 patients who underwent CCTA examination at Institut Jantung Negara (IJN) between September 2020 and May 2021 were selected as they met the inclusion criteria. Three primary coronary arteries were segmented on axial sectional images, yielding a total of 606 volume of interest (VOI). Subsequently, the first order, second order, and shape order of radiomic characteristics were extracted for each VOI. Model 1, Model 2, Model 3, and Model 4 were constructed using AutoML-based Tree-Pipeline Optimization Tools (TPOT). The heatmap confusion matrix, recall (sensitivity), precision (PPV), F1 score, accuracy, receiver operating characteristic (ROC), and area under the curve (AUC) were analysed. Notably, Model 1 with the first-order features showed superior performance in classifying the normal coronary arteries (F1 score: 0.88; Inverse F1 score: 0.94), as well as in classifying the calcified (F1 score: 0.78; Inverse F1 score: 0.91) and mixed plaques (F1 score: 0.76; Inverse F1 score: 0.86). Moreover, Model 2 consisting of second-order features was proved useful, specifically in classifying the non-calcified plaques (F1 score: 0.63; Inverse F1 score: 0.92) which are a key point for prediction of cardiac events. Nevertheless, Model 3 comprising the shape-based features did not contribute to the classification of atherosclerotic plaques. Overall, TPOT shown promising capabilities in terms of finding the best pipeline and tailoring the model using CCTA-based radiomic datasets.

Reproducibility and Repeatability of Coronary Computed Tomography Angiography (CCTA) Image Segmentation in Detecting Atherosclerosis: A Radiomics Study

“…Yet, these radiomics features will be highly beneficial in supervising various automated machine-learning models, especially in detecting any diseases in medical images particularly at the small area. This result is supported by the previous study [ 15 , 16 , 46 ].…”

“…One-way analysis of variance (ANOVA) was used to obtain the ICC values for intra observer segmentation [ 14 , 15 ]. The equation below defines ICC (C,1): where MS R = mean square for rows, MS W = mean square for residual sources of variance, MS E = mean square error, MS C = mean square for columns, and k and n are the numbers of observers involved and subjects.…”

“…It improves the characterization of plaque-containing blood vessels by using complex and potential algorithms to facilitate the radiologist’s decision regarding prospective patient treatment. The use of texture analysis or the so-called part of artificial intelligence (AI) technology is also a promising alternative quantitative analysis to identify and characterize the lesion by using medical imaging information such as from CCTA images [ 15 , 16 , 17 , 18 , 19 ]. Despite its ability, reproducibility in extracting radiomics features remains a concern.…”

Delta‐radiomics‐based models for toxicity prediction in radiotherapy: A systematic review and meta‐analysis

“…Radiomics refers to a paradigm shift in which medical images are reinterpreted as a quantitative asset in data‐driven precision medicine 37 . Prior research recognizes the critical role played by radiomics‐based models, which have emerged as viable clinical tools for a variety of clinical issues such as drug discovery, clinical diagnosis, 38,39 treatment selection and implementation 40 and prognosis 41,42 . In radiation oncology, efforts mainly focus on radiomics‐based models for the prediction of patients' overall survival and tumour response 43–47 .…”

Stability and Reproducibility of Radiomic Features Based on Various Segmentation Techniques on Cervical Cancer DWI-MRI

“…One of the most significant challenges for radiomics is the accuracy of the tumor segmentation process. Previous research demonstrates that semi-automatic segmentation techniques are selected because they are superior to manual segmentation [ 14 , 15 ]. Manual segmentation is arduous and time consuming compared to semi-automatic segmentation techniques.…”