Texture analysis and machine learning of non-contrast T1-weighted MR images in patients with hypertrophic cardiomyopathy-Preliminary results

Test-retest repeatability of myocardial radiomic features from quantitative cardiac magnetic resonance T1 and T2 mapping

Radiomics of cardiac magnetic resonance (MR) imaging has proved to be potentially useful in the study of various myocardial diseases. Therefore, assessing the repeatability degree in radiomic features measurement is of fundamental importance. The aim of this study was to assess test-retest repeatability of myocardial radiomic features extracted from quantitative T1 and T2 maps. A representative group of 24 subjects (mean age 54 ± 18 years) referred for clinical cardiac MR imaging were enrolled in the study. For each subject, T1 and T2 mapping through MOLLI and T2-prepared TrueFISP acquisition sequences, respectively, were performed at 1.5 T. Then, 98 radiomic features of different classes (shape, first-order, second-order) were extracted from a region of interest encompassing the whole left ventricle myocardium in a short axis slice. The repeatability was assessed performing different and complementary analyses: intraclass correlation coefficient (ICC) and limits of agreement (LOA) (i.e., the interval within which 95% of the percentage differences between two repeated measures are expected to lie). Radiomic features were characterized by a relatively wide range of repeatability degree in terms of both ICC and LOA. Overall, 44.9% and 38.8% of radiomic features showed ICC values > 0.75 for T1 and T2 maps, respectively, while 25.5% and 23.4% of radiomic features showed LOA between ±10%. A subset of radiomic features for T1 (Mean, Median, 10Percentile, 90Percentile, RootMeanSquared, Imc2, RunLengthNonUniformityNormalized, RunPercentage and ShortRunEmphasis) and T2 (MaximumDiameter, RunLengthNonUniformityNormalized, RunPercentage, ShortRunEmphasis) maps presented both ICC > 0.75 and LOA between ±5%. Overall, radiomic features extracted from T1 maps showed better repeatability performance than those extracted from T2 maps, with shape features characterized by better repeatability than first-order and textural features. Moreover, only a limited subset of 9 and 4 radiomic features for T1 and T2 maps, respectively, showed high repeatability degree in terms of both ICC and LOA. These results confirm the importance of assessing test-retest repeatability degree in radiomic feature estimation and might be useful for a more effective/reliable use of myocardial T1 and T2 mapping radiomics in clinical or research studies.

The role of artificial intelligence in cardiovascular magnetic resonance imaging

Cardiovascular magnetic resonance (CMR) imaging is the gold standard test for myocardial tissue characterization and chamber volumetric and functional evaluation. However, manual CMR analysis can be time-consuming and is subject to intra- and inter-observer variability. Artificial intelligence (AI) is a field that permits automated task performance through the identification of high-level and complex data relationships. In this review, we review the rapidly growing role of AI in CMR, including image acquisition, sequence prescription, artifact detection, reconstruction, segmentation, and data reporting and analysis including quantification of volumes, function, myocardial infarction (MI) and scar detection, and prediction of outcomes. We conclude with a discussion of the emerging challenges to widespread adoption and solutions that will allow for successful, broader uptake of this powerful technology.

Perfect Match: Radiomics and Artificial Intelligence in Cardiac Imaging

Cardiovascular diseases remain a significant health burden, with imaging modalities like echocardiography, cardiac computed tomography, and cardiac magnetic resonance imaging playing a crucial role in diagnosis and prognosis. However, the inherent heterogeneity of these diseases poses challenges, necessitating advanced analytical methods like radiomics and artificial intelligence. Radiomics extracts quantitative features from medical images, capturing intricate patterns and subtle variations that may elude visual inspection. Artificial intelligence techniques, including deep learning, can analyze these features to generate knowledge, define novel imaging biomarkers, and support diagnostic decision-making and outcome prediction. Radiomics and artificial intelligence thus hold promise for significantly enhancing diagnostic and prognostic capabilities in cardiac imaging, paving the way for more personalized and effective patient care. This review explores the synergies between radiomics and artificial intelligence in cardiac imaging, following the radiomics workflow and introducing concepts from both domains. Potential clinical applications, challenges, and limitations are discussed, along with solutions to overcome them.

A deep learning-based radiomics model for predicting lymph node status from lung adenocarcinoma

OBJECTIVES

At present, there are many limitations in the evaluation of lymph node metastasis of lung adenocarcinoma. Currently, there is a demand for a safe and accurate method to predict lymph node metastasis of lung cancer. In this study, radiomics was used to accurately predict the lymph node status of lung adenocarcinoma patients based on contrast-enhanced CT.

METHODS

A total of 503 cases that fulfilled the analysis requirements were gathered from two distinct hospitals. Among these, 287 patients exhibited lymph node metastasis (LNM +) while 216 patients were confirmed to be without lymph node metastasis (LNM-). Using both traditional and deep learning methods, 22,318 features were extracted from the segmented images of each patient's enhanced CT. Then, the spearman test and the least absolute shrinkage and selection operator were used to effectively reduce the dimension of the feature data, enabling us to focus on the most pertinent features and enhance the overall analysis. Finally, the classification model of lung adenocarcinoma lymph node metastasis was constructed by machine learning algorithm. The Accuracy, AUC, Specificity, Precision, Recall and F1 were used to evaluate the efficiency of the model.

RESULTS

By incorporating a comprehensively selected set of features, the extreme gradient boosting method (XGBoost) effectively distinguished the status of lymph nodes in patients with lung adenocarcinoma. The Accuracy, AUC, Specificity, Precision, Recall and F1 of the prediction model performance on the external test set were 0.765, 0.845, 0.705, 0.784, 0.811 and 0.797, respectively. Moreover, the decision curve analysis, calibration curve and confusion matrix of the model on the external test set all indicated the stability and accuracy of the model.

CONCLUSIONS

Leveraging enhanced CT images, our study introduces a noninvasive classification prediction model based on the extreme gradient boosting method. This approach exhibits remarkable precision in identifying the lymph node status of lung adenocarcinoma patients, offering a safe and accurate alternative to invasive procedures. By providing clinicians with a reliable tool for diagnosing and assessing disease progression, our method holds the potential to significantly improve patient outcomes and enhance the overall quality of clinical practice.

Contrast-enhanced CT-based radiomics differentiate anterior mediastinum lymphoma from thymoma without myasthenia gravis and calcification

AIM

To explore the value of a radiomics model based on enhanced computed tomography (CT) in differentiating anterior mediastinal lymphoma (AML) and thymoma without myasthenia gravis (MG) and calcification.

MATERIALS AND METHODS

The present study analysed patients who were diagnosed histologically with AML and thymoma in three independent institutions. All pre-treatment patients underwent enhanced CT. In the training group of patients from institutions 1 (the First Affiliated Hospital of Kunming Medical University) and 3 (the Yunnan Cancer Hospital), two radiologists independently analysed the enhanced CT images and performed manual segmentation of each tumour. Radiomics features were screened using interobserver interclass coefficient (ICC) analysis, feature correlation analysis, and L1 regularisation. The discriminative efficacy of the logistic regression model was evaluated using receiver operating characteristic (ROC) analysis. Validation group of patients from institution 2 (the Second Affiliated Hospital of Zhejiang University School of Medicine) was used to validate the proposed models.

RESULTS

A total of 114 patients were enrolled in this study and 1,743 radiomics features were extracted from the enhanced CT images. After feature screening, the remaining 37 robust radiomics features were used to construct the model. In the training group, the AUC of the model was 0.987 (95% confidence interval [CI]: 0.976-0.999), the sensitivity, specificity, and accuracy were 0.912, 0.946, and 0.924, respectively. In the validation group, the AUC of the model was 0.798 (95% CI: 0.683-0.913), the sensitivity, specificity, and accuracy were 0.760, 0.700, and 0.743, respectively.

CONCLUSION

The radiomics model created provided effective information to assist in the selection of clinical strategies, thus reducing unnecessary procedures in patients with AML and guiding direct surgery in patients with thymoma to avoid biopsy.

Assessing heterogeneity on cardiovascular magnetic resonance imaging: a novel approach to diagnosis and risk stratification in cardiac diseases

Cardiac disease affects the heart non-uniformly. Examples include focal septal or apical hypertrophy with reduced strain in hypertrophic cardiomyopathy, replacement fibrosis with akinesia in an infarct-related coronary artery territory, and a pattern of scarring in dilated cardiomyopathy. The detail and versatility of cardiovascular magnetic resonance (CMR) imaging mean it contains a wealth of information imperceptible to the naked eye and not captured by standard global measures. CMR-derived heterogeneity biomarkers could facilitate early diagnosis, better risk stratification, and a more comprehensive prediction of treatment response. Small cohort and case-control studies demonstrate the feasibility of proof-of-concept structural and functional heterogeneity measures. Detailed radiomic analyses of different CMR sequences using open-source software delineate unique voxel patterns as hallmarks of histopathological changes. Meanwhile, measures of dispersion applied to emerging CMR strain sequences describe variable longitudinal, circumferential, and radial function across the myocardium. Two of the most promising heterogeneity measures are the mean absolute deviation of regional standard deviations on native T1 and T2 and the standard deviation of time to maximum regional radial wall motion, termed the tissue synchronization index in a 16-segment left ventricle model. Real-world limitations include the non-standardization of CMR imaging protocols across different centres and the testing of large numbers of radiomic features in small, inadequately powered patient samples. We, therefore, propose a three-step roadmap to benchmark novel heterogeneity biomarkers, including defining normal reference ranges, statistical modelling against diagnosis and outcomes in large epidemiological studies, and finally, comprehensive internal and external validations.

Cine-cardiac magnetic resonance to distinguish between ischemic and non-ischemic cardiomyopathies: a machine learning approach

OBJECTIVE

This work aimed to derive a machine learning (ML) model for the differentiation between ischemic cardiomyopathy (ICM) and non-ischemic cardiomyopathy (NICM) on non-contrast cardiovascular magnetic resonance (CMR).

METHODS

This retrospective study evaluated CMR scans of 107 consecutive patients (49 ICM, 58 NICM), including atrial and ventricular strain parameters. We used these data to compare an explainable tree-based gradient boosting additive model with four traditional ML models for the differentiation of ICM and NICM. The models were trained and internally validated with repeated cross-validation according to discrimination and calibration. Furthermore, we examined important variables for distinguishing between ICM and NICM.

RESULTS

A total of 107 patients and 38 variables were available for the analysis. Of those, 49 were ICM (34 males, mean age 60 ± 9 years) and 58 patients were NICM (38 males, mean age 56 ± 19 years). After 10 repetitions of the tenfold cross-validation, the proposed model achieved the highest area under curve (0.82, 95% CI [0.47-1.00]) and lowest Brier score (0.19, 95% CI [0.13-0.27]), showing competitive diagnostic accuracy and calibration. At the Youden's index, sensitivity was 0.72 (95% CI [0.68-0.76]), the highest of all. Analysis of predictions revealed that both atrial and ventricular strain CMR parameters were important for the identification of ICM patients.

CONCLUSION

The current study demonstrated that using a ML model, multi chamber myocardial strain, and function on non-contrast CMR parameters enables the discrimination between ICM and NICM with competitive diagnostic accuracy.

CLINICAL RELEVANCE STATEMENT

A machine learning model based on non-contrast cardiovascular magnetic resonance parameters may discriminate between ischemic and non-ischemic cardiomyopathy enabling wider access to cardiovascular magnetic resonance examinations with lower costs and faster imaging acquisition.

KEY POINTS

• The exponential growth in cardiovascular magnetic resonance examinations may require faster and more cost-effective protocols. • Artificial intelligence models can be utilized to distinguish between ischemic and non-ischemic etiologies. • Machine learning using non-contrast CMR parameters can effectively distinguish between ischemic and non-ischemic cardiomyopathies.

Deep Learning for Discrimination of Hypertrophic Cardiomyopathy and Hypertensive Heart Disease on MRI Native T1 Maps

BACKGROUND

Native T1 and radiomics were used for hypertrophic cardiomyopathy (HCM) and hypertensive heart disease (HHD) differentiation previously. The current problem is that global native T1 remains modest discrimination performance and radiomics requires feature extraction beforehand. Deep learning (DL) is a promising technique in differential diagnosis. However, its feasibility for discriminating HCM and HHD has not been investigated.

PURPOSE

To examine the feasibility of DL in differentiating HCM and HHD based on T1 images and compare its diagnostic performance with other methods.

STUDY TYPE

Retrospective.

POPULATION

128 HCM patients (men, 75; age, 50 years ± 16) and 59 HHD patients (men, 40; age, 45 years ± 17).

FIELD STRENGTH/SEQUENCE

3.0T; Balanced steady-state free precession, phase-sensitive inversion recovery (PSIR) and multislice native T1 mapping.

ASSESSMENT

Compare HCM and HHD patients baseline data. Myocardial T1 values were extracted from native T1 images. Radiomics was implemented through feature extraction and Extra Trees Classifier. The DL network is ResNet32. Different input including myocardial ring (DL-myo), myocardial ring bounding box (DL-box) and the surrounding tissue without myocardial ring (DL-nomyo) were tested. We evaluate diagnostic performance through AUC of ROC curve.

STATISTICAL TESTS

Accuracy, sensitivity, specificity, ROC, and AUC were calculated. Independent t test, Mann-Whitney U-test and Chi-square test were adopted for HCM and HHD comparison. P < 0.05 was considered statistically significant.

RESULTS

DL-myo, DL-box, and DL-nomyo models showed an AUC (95% confidential interval) of 0.830 (0.702-0.959), 0.766 (0.617-0.915), 0.795 (0.654-0.936) in the testing set. AUC of native T1 and radiomics were 0.545 (0.352-0.738) and 0.800 (0.655-0.944) in the testing set.

DATA CONCLUSION

The DL method based on T1 mapping seems capable of discriminating HCM and HHD. Considering diagnostic performance, the DL network outperformed the native T1 method. Compared with radiomics, DL won an advantage for its high specificity and automated working mode.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 2.

Editorial for "Left Ventricular Vertical Run-Length Nonuniformity MRI Adds Prognostic Value to MACE in Patients with End-Stage Renal Disease"

Level of Evidence

2

Technical Efficacy Stage

2

Left Ventricular Vertical Run-Length Nonuniformity MRI Adds Prognostic Value to MACE in Patients with End-Stage Renal Disease

BACKGROUND

Vertical run-length nonuniformity (VRLN) is a texture feature representing heterogeneity within native T1 images and reflects the extent of cardiac fibrosis. In uremic cardiomyopathy, interstitial fibrosis was the major histological alteration. The prognostic value of VRLN in patients with end-stage renal disease (ESRD) remains unclear.

PURPOSE

To evaluate the prognostic value of VRLN MRI in patients with ESRD.

STUDY TYPE

Prospective.

POPULATION

A total of 127 ESRD patients (30 participants in the major adverse cardiac events, MACE group).

FIELD STRENGTH/SEQUENCE

3.0 T/steady-state free precession sequence, modified Look-Locker imaging.

ASSESSMENT

MRI image qualities were assessed by three independent radiologists. VRLN values were measured in the myocardium on the mid-ventricular short-axis slice of T1 mapping. Left ventricular (LV) mass, LV end-diastolic and end-systolic volume, as well as LV global strain cardiac parameters were measured.

STATISTICAL TESTS

The primary endpoint was the incident of MACE from enrollment time to January 2023. MACE is a composite endpoint consisting of all-cause mortality, acute myocardial infarction, stroke, heart failure hospitalization, and life-threatening arrhythmia. Cox proportional-hazards regression was performed to test whether VRLN independently correlated with MACE. The intraclass correlation coefficients of VRLN were calculated to evaluate intraobserver and interobserver reproducibility. The C-index was computed to examine the prognostic value of VRLN. P-value <0.05 were considered statistically significant.

RESULTS

Participants were followed for a median of 26 months. VRLN, age, LV end-systolic volume index, and global longitudinal strain remained significantly associated with MACE in the multivariable model. Adding VRLN to a baseline model containing clinical and conventional cardiac MRI parameters significantly improved the accuracy of the predictive model (C-index of the baseline model: 0.781 vs. the model added VRLN: 0.814).

DATA CONCLUSION

VRLN is a novel marker for risk stratification toward MACE in patients with ESRD, superior to native T1 mapping and LV ejection fraction.

EVIDENCE LEVEL

2 TECHNICAL EFFICACY STAGE: 2.

Artificial Intelligence in the Differential Diagnosis of Cardiomyopathy Phenotypes

Artificial intelligence (AI) is rapidly being applied to the medical field, especially in the cardiovascular domain. AI approaches have demonstrated their applicability in the detection, diagnosis, and management of several cardiovascular diseases, enhancing disease stratification and typing. Cardiomyopathies are a leading cause of heart failure and life-threatening ventricular arrhythmias. Identifying the etiologies is fundamental for the management and diagnostic pathway of these heart muscle diseases, requiring the integration of various data, including personal and family history, clinical examination, electrocardiography, and laboratory investigations, as well as multimodality imaging, making the clinical diagnosis challenging. In this scenario, AI has demonstrated its capability to capture subtle connections from a multitude of multiparametric datasets, enabling the discovery of hidden relationships in data and handling more complex tasks than traditional methods. This review aims to present a comprehensive overview of the main concepts related to AI and its subset. Additionally, we review the existing literature on AI-based models in the differential diagnosis of cardiomyopathy phenotypes, and we finally examine the advantages and limitations of these AI approaches.

Left Ventricular Myocardial Dysfunction Evaluation in Thalassemia Patients Using Echocardiographic Radiomic Features and Machine Learning Algorithms

Heart failure caused by iron deposits in the myocardium is the primary cause of mortality in beta-thalassemia major patients. Cardiac magnetic resonance imaging (CMRI) T2* is the primary screening technique used to detect myocardial iron overload, but inherently bears some limitations. In this study, we aimed to differentiate beta-thalassemia major patients with myocardial iron overload from those without myocardial iron overload (detected by T2*CMRI) based on radiomic features extracted from echocardiography images and machine learning (ML) in patients with normal left ventricular ejection fraction (LVEF > 55%) in echocardiography. Out of 91 cases, 44 patients with thalassemia major with normal LVEF (> 55%) and T2* ≤ 20 ms and 47 people with LVEF > 55% and T2* > 20 ms as the control group were included in the study. Radiomic features were extracted for each end-systolic (ES) and end-diastolic (ED) image. Then, three feature selection (FS) methods and six different classifiers were used. The models were evaluated using various metrics, including the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Maximum relevance-minimum redundancy-eXtreme gradient boosting (MRMR-XGB) (AUC = 0.73, ACC = 0.73, SPE = 0.73, SEN = 0.73), ANOVA-MLP (AUC = 0.69, ACC = 0.69, SPE = 0.56, SEN = 0.83), and recursive feature elimination-K-nearest neighbors (RFE-KNN) (AUC = 0.65, ACC = 0.65, SPE = 0.64, SEN = 0.65) were the best models in ED, ES, and ED&ES datasets. Using radiomic features extracted from echocardiographic images and ML, it is feasible to predict cardiac problems caused by iron overload.

Coronary computed tomography angiography imaging features combined with computed tomography-fractional flow reserve, pericoronary fat attenuation index, and radiomics for the prediction of myocardial ischemia

BACKGROUND

This study aimed to predict myocardial ischemia (MIS) by constructing models with imaging features, CT-fractional flow reserve (CT-FFR), pericoronary fat attenuation index (pFAI), and radiomics based on coronary computed tomography angiography (CCTA).

METHODS AND RESULTS

This study included 96 patients who underwent CCTA and single photon emission computed tomography-myocardial perfusion imaging (SPECT-MPI). According to SPECT-MPI results, there were 72 vessels with MIS in corresponding supply area and 105 vessels with no-MIS. The conventional model [lesion length (LL), MDS (maximum stenosis diameter × 100% / reference vessel diameter), MAS (maximum stenosis area × 100% / reference vessel area) and CT value], radiomics model (radiomics features), and multi-faceted model (all features) were constructed using support vector machine. Conventional and radiomics models showed similar predictive efficacy [AUC: 0.76, CI 0.62-0.90 vs. 0.74, CI 0.61-0.88; p > 0.05]. Adding pFAI to the conventional model showed better predictive efficacy than adding CT-FFR (AUC: 0.88, CI 0.79-0.97 vs. 0.80, CI 0.68-0.92; p < 0.05). Compared with conventional and radiomics model, the multi-faceted model showed the highest predictive efficacy (AUC: 0.92, CI 0.82-0.98, p < 0.05).

CONCLUSION

pFAI is more effective for predicting MIS than CT-FFR. A multi-faceted model combining imaging features, CT-FFR, pFAI, and radiomics is a potential diagnostic tool for MIS.

Non-Contrast Cine Cardiac Magnetic Resonance Derived-Radiomics for the Prediction of Left Ventricular Adverse Remodeling in Patients With ST-Segment Elevation Myocardial Infarction

OBJECTIVE

To investigate the predictive value of radiomics features based on cardiac magnetic resonance (CMR) cine images for left ventricular adverse remodeling (LVAR) after acute ST-segment elevation myocardial infarction (STEMI).

MATERIALS AND METHODS

We conducted a retrospective, single-center, cohort study involving 244 patients (random-split into 170 and 74 for training and testing, respectively) having an acute STEMI (88.5% males, 57.0 ± 10.3 years of age) who underwent CMR examination at one week and six months after percutaneous coronary intervention. LVAR was defined as a 20% increase in left ventricular end-diastolic volume 6 months after acute STEMI. Radiomics features were extracted from the one-week CMR cine images using the least absolute shrinkage and selection operator regression (LASSO) analysis. The predictive performance of the selected features was evaluated using receiver operating characteristic curve analysis and the area under the curve (AUC).

RESULTS

Nine radiomics features with non-zero coefficients were included in the LASSO regression of the radiomics score (RAD score). Infarct size (odds ratio [OR]: 1.04 (1.00-1.07); P = 0.031) and RAD score (OR: 3.43 (2.34-5.28); P < 0.001) were independent predictors of LVAR. The RAD score predicted LVAR, with an AUC (95% confidence interval [CI]) of 0.82 (0.75-0.89) in the training set and 0.75 (0.62-0.89) in the testing set. Combining the RAD score with infarct size yielded favorable performance in predicting LVAR, with an AUC of 0.84 (0.72-0.95). Moreover, the addition of the RAD score to the left ventricular ejection fraction (LVEF) significantly increased the AUC from 0.68 (0.52-0.84) to 0.82 (0.70-0.93) (P = 0.018), which was also comparable to the prediction provided by the combined microvascular obstruction, infarct size, and LVEF with an AUC of 0.79 (0.65-0.94) (P = 0.727).

CONCLUSION

Radiomics analysis using non-contrast cine CMR can predict LVAR after STEMI independently and incrementally to LVEF and may provide an alternative to traditional CMR parameters.

Radiomics applications in cardiac imaging: a comprehensive review

Radiomics is a new emerging field that includes extraction of metrics and quantification of so-called radiomic features from medical images. The growing importance of radiomics applied to oncology in improving diagnosis, cancer staging and grading, and improved personalized treatment, has been well established; yet, this new analysis technique has still few applications in cardiovascular imaging. Several studies have shown promising results describing how radiomics principles could improve the diagnostic accuracy of coronary computed tomography angiography (CCTA) and magnetic resonance imaging (MRI) in diagnosis, risk stratification, and follow-up of patients with coronary heart disease (CAD), ischemic heart disease (IHD), hypertrophic cardiomyopathy (HCM), hypertensive heart disease (HHD), and many other cardiovascular diseases. Such quantitative approach could be useful to overcome the main limitations of CCTA and MRI in the evaluation of cardiovascular diseases, such as readers' subjectiveness and lack of repeatability. Moreover, this new discipline could potentially overcome some technical problems, namely the need of contrast administration or invasive examinations. Despite such advantages, radiomics is still not applied in clinical routine, due to lack of standardized parameters acquisition, inconsistent radiomic methods, lack of external validation, and different knowledge and experience among the readers. The purpose of this manuscript is to provide a recent update on the status of radiomics clinical applications in cardiovascular imaging.

Artificial Intelligence Applications in Cardiovascular Magnetic Resonance Imaging: Are We on the Path to Avoiding the Administration of Contrast Media?

In recent years, cardiovascular imaging examinations have experienced exponential growth due to technological innovation, and this trend is consistent with the most recent chest pain guidelines. Contrast media have a crucial role in cardiovascular magnetic resonance (CMR) imaging, allowing for more precise characterization of different cardiovascular diseases. However, contrast media have contraindications and side effects that limit their clinical application in determinant patients. The application of artificial intelligence (AI)-based techniques to CMR imaging has led to the development of non-contrast models. These AI models utilize non-contrast imaging data, either independently or in combination with clinical and demographic data, as input to generate diagnostic or prognostic algorithms. In this review, we provide an overview of the main concepts pertaining to AI, review the existing literature on non-contrast AI models in CMR, and finally, discuss the strengths and limitations of these AI models and their possible future development.

Prediction of incident cardiovascular events using machine learning and CMR radiomics

OBJECTIVES

Evaluation of the feasibility of using cardiovascular magnetic resonance (CMR) radiomics in the prediction of incident atrial fibrillation (AF), heart failure (HF), myocardial infarction (MI), and stroke using machine learning techniques.

METHODS

We identified participants from the UK Biobank who experienced incident AF, HF, MI, or stroke during the continuous longitudinal follow-up. The CMR indices and the vascular risk factors (VRFs) as well as the CMR images were obtained for each participant. Three-segmented regions of interest (ROIs) were computed: right ventricle cavity, left ventricle (LV) cavity, and LV myocardium in end-systole and end-diastole phases. Radiomics features were extracted from the 3D volumes of the ROIs. Seven integrative models were built for each incident cardiovascular disease (CVD) as an outcome. Each model was built with VRF, CMR indices, and radiomics features and a combination of them. Support vector machine was used for classification. To assess the model performance, the accuracy, sensitivity, specificity, and AUC were reported.

RESULTS

AF prediction model using the VRF+CMR+Rad model (accuracy: 0.71, AUC 0.76) obtained the best result. However, the AUC was similar to the VRF+Rad model. HF showed the most significant improvement with the inclusion of CMR metrics (VRF+CMR+Rad: 0.79, AUC 0.84). Moreover, adding only the radiomics features to the VRF reached an almost similarly good performance (VRF+Rad: accuracy 0.77, AUC 0.83). Prediction models looking into incident MI and stroke reached slightly smaller improvement.

CONCLUSIONS

Radiomics features may provide incremental predictive value over VRF and CMR indices in the prediction of incident CVDs.

KEY POINTS

• Prediction of incident atrial fibrillation, heart failure, stroke, and myocardial infarction using machine learning techniques. • CMR radiomics, vascular risk factors, and standard CMR indices will be considered in the machine learning models. • The experiments show that radiomics features can provide incremental predictive value over VRF and CMR indices in the prediction of incident cardiovascular diseases.

Machine learning approach in diagnosing Takotsubo cardiomyopathy: The role of the combined evaluation of atrial and ventricular strain, and parametric mapping

BACKGROUND

Cardiac magnetic resonance (CMR) with late gadolinium enhancement (LGE) is a key diagnostic tool in the differential diagnosis between non-ischemic cause of cardiac chest pain. Some patients are not eligible for a gadolinium contrast-enhanced CMR; in this scenario, the diagnosis remains challenging without invasive examination. Our purpose was to derive a machine learning model integrating some non-contrast CMR parameters and demographic factors to identify Takotsubo cardiomyopathy (TTC) in subjects with cardiac chest pain.

MATERIAL AND METHODS

Three groups of patients were retrospectively studied: TTC, acute myocarditis, and healthy controls. Global and regional left ventricular longitudinal, circumferential, and radial strain (RS) analysis included were assessed. Reservoir, conduit, and booster bi-atrial functions were evaluated by tissue-tracking. Parametric mapping values were also assessed in all the patients. Five different tree-based ensemble learning algorithms were tested concerning their ability in recognizing TTC in a fully cross-validated framework.

RESULTS

The CMR-based machine learning (ML) ensemble model, by using the Extremely Randomized Trees algorithm with Elastic Net feature selection, showed a sensitivity of 92% (95% CI 78-100), specificity of 86% (95% CI 80-92) and area under the ROC of 0.94 (95% CI 0.90-0.99) in diagnosing TTC. Among non-contrast CMR parameters, the Shapley additive explanations analysis revealed that left atrial (LA) strain and strain rate were the top imaging markers in identifying TTC patients.

CONCLUSIONS

Our study demonstrated that using a tree-based ensemble learning algorithm on non-contrast CMR parameters and demographic factors enables the identification of subjects with TTC with good diagnostic accuracy.

TRANSLATIONAL OUTLOOK

Our results suggest that non-contrast CMR features can be implemented in a ML model to accurately identify TTC subjects. This model could be a valuable tool for aiding in the diagnosis of subjects with a contraindication to the contrast media. Furthermore, the left atrial conduit strain and strain rate were imaging markers that had a strong impact on TTC identification. Further prospective and longitudinal studies are needed to validate these findings and assess predictive performance in different cohorts, such as those with different ethnicities, and social backgrounds and undergoing different treatments.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Prediction of myocardial ischemia in coronary heart disease patients using a CCTA-Based radiomic nomogram

Objective

The present study aimed to predict myocardial ischemia in coronary heart disease (CHD) patients based on the radiologic features of coronary computed tomography angiography (CCTA) combined with clinical factors.

Methods

The imaging and clinical data of 110 patients who underwent CCTA scan before DSA or FFR examination in Changzhou Second People's Hospital, Nanjing Medical University (90 patients), and The First Affiliated Hospital of Soochow University (20 patients) from March 2018 to January 2022 were retrospectively analyzed. According to the digital subtraction angiography (DSA) and fractional flow reserve (FFR) results, all patients were assigned to myocardial ischemia (n = 58) and normal myocardial blood supply (n = 52) groups. All patients were further categorized into training (n = 64) and internal validation (n = 26) sets at a ratio of 7:3, and the patients from second site were used as external validation. Clinical indicators of patients were collected, the left ventricular myocardium were segmented from CCTA images using CQK software, and the radiomics features were extracted using pyradiomics software. Independent prediction models and combined prediction models were established. The predictive performance of the model was assessed by calibration curve analysis, receiver operating characteristic (ROC) curve and decision curve analysis.

Results

The combined model consisted of one important clinical factor and eight selected radiomic features. The area under the ROC curve (AUC) of radiomic model was 0.826 in training set, and 0.744 in the internal validation set. For the combined model, the AUCs were 0.873, 0.810, 0.800 in the training, internal validation, and external validation sets, respectively. The calibration curves demonstrated that the probability of myocardial ischemia predicted by the combined model was in good agreement with the observed values in both training and validation sets. The decision curve was within the threshold range of 0.1-1, and the clinical value of nomogram was higher than that of clinical model.

Conclusion

The radiomic characteristics of CCTA combined with clinical factors have a good clinical value in predicting myocardial ischemia in CHD patients.

Clinician's guide to trustworthy and responsible artificial intelligence in cardiovascular imaging

A growing number of artificial intelligence (AI)-based systems are being proposed and developed in cardiology, driven by the increasing need to deal with the vast amount of clinical and imaging data with the ultimate aim of advancing patient care, diagnosis and prognostication. However, there is a critical gap between the development and clinical deployment of AI tools. A key consideration for implementing AI tools into real-life clinical practice is their "trustworthiness" by end-users. Namely, we must ensure that AI systems can be trusted and adopted by all parties involved, including clinicians and patients. Here we provide a summary of the concepts involved in developing a "trustworthy AI system." We describe the main risks of AI applications and potential mitigation techniques for the wider application of these promising techniques in the context of cardiovascular imaging. Finally, we show why trustworthy AI concepts are important governing forces of AI development.

Differentiating between cardiac amyloidosis and hypertrophic cardiomyopathy on non-contrast cine-magnetic resonance images using machine learning-based radiomics

Objectives

This study aimed to determine whether texture analysis (TA) and machine learning-based classifications can be applied in differential diagnosis of cardiac amyloidosis (CA) and hypertrophic cardiomyopathy (HCM) using non-contrast cine cardiac magnetic resonance (CMR) images.

Methods

In this institutional review board-approved study, we consecutively enrolled 167 patients with CA (n = 85), HCM (n = 82), and 84 patients with normal CMR served as controls. All cases were randomized into training [119 patients (70%)] and validation [48 patients (30%)] groups. A total of 275 texture features were extracted from cine images. Based on regression analysis with the least absolute shrinkage and selection operator (LASSO), nine machine learning models were established and their diagnostic performance determined.

Results

Nineteen radiomics texture features derived from cine images were used to differentiate CA and HCM. In the validation cohort, the support vector machine (SVM), which had an accuracy of 0.85, showed the best performance (MCC = 0.637). Gray level non-uniformity (GLevNonU) was the single most effective feature. The combined model of radiomics texture features and conventional MR metrics had superior discriminatory performance (AUC = 0.89) over conventional MR metrics model (AUC = 0.79). Moreover, results showed that GLevNonU levels in HCM patients were significantly higher compared with levels in CA patients and control groups (P < 0.001). A cut-off of GLevNonU ≥ 25 was shown to differentiate between CA and HCM patients, with an area under the curve (AUC) of 0.86 (CI:0.804–0.920). Multiple comparisons tests showed that GLevNonU was significantly greater in LGE+, relative to LGE-patient groups (CA+ vs. CA- and HCM+ vs. HCM-, P = 0.01, 0.001, respectively).

Conclusion

Machine learning-based classifiers can accurately differentiate between CA and HCM on non-contrast cine images. The radiomics-MR combined model can be used to improve the discriminatory performance. TA may be used to assess myocardial microstructure changes that occur during different stages of cardiomyopathies.

Artificial intelligence in cardiac magnetic resonance fingerprinting

Magnetic resonance fingerprinting (MRF) is a fast MRI-based technique that allows for multiparametric quantitative characterization of the tissues of interest in a single acquisition. In particular, it has gained attention in the field of cardiac imaging due to its ability to provide simultaneous and co-registered myocardial T₁ and T₂ mapping in a single breath-held cardiac MRF scan, in addition to other parameters. Initial results in small healthy subject groups and clinical studies have demonstrated the feasibility and potential of MRF imaging. Ongoing research is being conducted to improve the accuracy, efficiency, and robustness of cardiac MRF. However, these improvements usually increase the complexity of image reconstruction and dictionary generation and introduce the need for sequence optimization. Each of these steps increase the computational demand and processing time of MRF. The latest advances in artificial intelligence (AI), including progress in deep learning and the development of neural networks for MRI, now present an opportunity to efficiently address these issues. Artificial intelligence can be used to optimize candidate sequences and reduce the memory demand and computational time required for reconstruction and post-processing. Recently, proposed machine learning-based approaches have been shown to reduce dictionary generation and reconstruction times by several orders of magnitude. Such applications of AI should help to remove these bottlenecks and speed up cardiac MRF, improving its practical utility and allowing for its potential inclusion in clinical routine. This review aims to summarize the latest developments in artificial intelligence applied to cardiac MRF. Particularly, we focus on the application of machine learning at different steps of the MRF process, such as sequence optimization, dictionary generation and image reconstruction.

Myocardial Function Prediction After Coronary Artery Bypass Grafting Using MRI Radiomic Features and Machine Learning Algorithms

The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images in patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 patients who had visible scars on short-axis LGE-CMR images and were candidates for CABG surgery were selected and enrolled in this study. MR imaging was performed preoperatively using a 1.5-T MRI scanner. All images were segmented by two expert radiologists (in consensus). Prior to extraction of radiomics features, all MR images were resampled to an isotropic voxel size of 1.8 × 1.8 × 1.8 mm³. Subsequently, intensities were quantized to 64 discretized gray levels and a total of 93 features were extracted. The applied algorithms included a smoothly clipped absolute deviation (SCAD)-penalized support vector machine (SVM) and the recursive partitioning (RP) algorithm as a robust classifier for binary classification in this high-dimensional and non-sparse data. All models were validated with repeated fivefold cross-validation and 10,000 bootstrapping resamples. Ten and seven features were selected with SCAD-penalized SVM and RP algorithm, respectively, for CABG responder/non-responder classification. Considering univariate analysis, the GLSZM gray-level non-uniformity-normalized feature achieved the best performance (AUC: 0.62, 95% CI: 0.53-0.76) with SCAD-penalized SVM. Regarding multivariable modeling, SCAD-penalized SVM obtained an AUC of 0.784 (95% CI: 0.64-0.92), whereas the RP algorithm achieved an AUC of 0.654 (95% CI: 0.50-0.82). In conclusion, different radiomics texture features alone or combined in multivariate analysis using machine learning algorithms provide prognostic information regarding myocardial function in patients after CABG.

Predicting post-contrast information from contrast agent free cardiac MRI using machine learning: Challenges and methods

Objectives

Currently, administering contrast agents is necessary for accurately visualizing and quantifying presence, location, and extent of myocardial infarction (MI) with cardiac magnetic resonance (CMR). In this study, our objective is to investigate and analyze pre- and post-contrast CMR images with the goal of predicting post-contrast information using pre-contrast information only. We propose methods and identify challenges.

Methods

The study population consists of 272 retrospectively selected CMR studies with diagnoses of MI (n = 108) and healthy controls (n = 164). We describe a pipeline for pre-processing this dataset for analysis. After data feature engineering, 722 cine short-axis (SAX) images and segmentation mask pairs were used for experimentation. This constitutes 506, 108, and 108 pairs for the training, validation, and testing sets, respectively. We use deep learning (DL) segmentation (UNet) and classification (ResNet50) models to discover the extent and location of the scar and classify between the ischemic cases and healthy cases (i.e., cases with no regional myocardial scar) from the pre-contrast cine SAX image frames, respectively. We then capture complex data patterns that represent subtle signal and functional changes in the cine SAX images due to MI using optical flow, rate of change of myocardial area, and radiomics data. We apply this dataset to explore two supervised learning methods, namely, the support vector machines (SVM) and the decision tree (DT) methods, to develop predictive models for classifying pre-contrast cine SAX images as being a case of MI or healthy.

Results

Overall, for the UNet segmentation model, the performance based on the mean Dice score for the test set (n = 108) is 0.75 (±0.20) for the endocardium, 0.51 (±0.21) for the epicardium and 0.20 (±0.17) for the scar. For the classification task, the accuracy, F1 and precision scores of 0.68, 0.69, and 0.64, respectively, were achieved with the SVM model, and of 0.62, 0.63, and 0.72, respectively, with the DT model.

Conclusion

We have presented some promising approaches involving DL, SVM, and DT methods in an attempt to accurately predict contrast information from non-contrast images. While our initial results are modest for this challenging task, this area of research still poses several open problems.

Image resampling and discretization effect on the estimate of myocardial radiomic features from T1 and T2 mapping in hypertrophic cardiomyopathy

Radiomics is emerging as a promising and useful tool in cardiac magnetic resonance (CMR) imaging applications. Accordingly, the purpose of this study was to investigate, for the first time, the effect of image resampling/discretization and filtering on radiomic features estimation from quantitative CMR T1 and T2 mapping. Specifically, T1 and T2 maps of 26 patients with hypertrophic cardiomyopathy (HCM) were used to estimate 98 radiomic features for 7 different resampling voxel sizes (at fixed bin width), 9 different bin widths (at fixed resampling voxel size), and 7 different spatial filters (at fixed resampling voxel size/bin width). While we found a remarkable dependence of myocardial radiomic features from T1 and T2 mapping on image filters, many radiomic features showed a limited sensitivity to resampling voxel size/bin width, in terms of intraclass correlation coefficient (> 0.75) and coefficient of variation (< 30%). The estimate of most textural radiomic features showed a linear significant (p < 0.05) correlation with resampling voxel size/bin width. Overall, radiomic features from T2 maps have proven to be less sensitive to image preprocessing than those from T1 maps, especially when varying bin width. Our results might corroborate the potential of radiomics from T1/T2 mapping in HCM and hopefully in other myocardial diseases.

Diffusion-Weighted Imaging Prior to Percutaneous Sclerotherapy of Venous Malformations—Proof of Concept Study for Prediction of Clinical Outcome

Prediction of response to percutaneous sclerotherapy in patients with venous malformations (VM) is currently not possible with baseline clinical or imaging characteristics. This prospective single-center study aimed to predict treatment outcome of percutaneous sclerotherapy as measured by quality of life (QoL) by using radiomic analysis of diffusion-weighted (dw) magnetic resonance imaging (MRI) before and after first percutaneous sclerotherapy. In all patients (n = 16) pre-interventional (PRE-) and delta (DELTA-) radiomic features (RF) were extracted from dw-MRI before and after first percutaneous sclerotherapy with ethanol gel or polidocanol foam, while QoL was assessed using the Toronto Extremity Salvage Score (TESS) and the 36-Item Short Form Survey (SF-36) health questionnaire. For selecting features that allow differentiation of clinical response, a stepwise dimension reduction was performed. Logistic regression models were fitted and selected PRE-/DELTA-RF were tested for their predictive value. QoL improved significantly after percutaneous sclerotherapy. While no common baseline patient characteristics were able to predict response to percutaneous sclerotherapy, the radiomics signature of VMs (independent PRE/DELTA-RF) revealed high potential for the prediction of clinical response after percutaneous sclerotherapy. This proof-of-concept study provides first evidence on the potential predictive value of (delta) radiomic analysis from diffusion-weighted MRI for Quality-of-Life outcome after percutaneous sclerotherapy in patients with venous malformations.

Texture Analysis Based on Vascular Ultrasound to Identify the Vulnerable Carotid Plaques

Vulnerable carotid plaques are closely related to the occurrence of ischemic stroke. Therefore, accurate and rapid identification of the nature of carotid plaques is essential. This study aimed to determine whether texture analysis based on a vascular ultrasound can be applied to identify vulnerable plaques. Data from a total of 150 patients diagnosed with atherosclerotic plaque (AP) by carotid ultrasound (CDU) and high-resolution magnetic resonance imaging (HRMRI) were collected. HRMRI is the in vivo reference to assess the nature of AP. MaZda software was used to delineate the region of interest and extract 303 texture features from ultrasonic images of plaques. Following regression analysis using the least absolute shrinkage and selection operator (LASSO) algorithm, the overall cohort was randomized 7:3 into the training (n = 105) and testing (n = 45) sets. In the training set, the conventional ultrasound model, the texture feature model, and the conventional ultrasound-texture feature combined model were constructed. The testing set was used to validate the model’s effectiveness by calculating the area under the curve (AUC), accuracy, sensitivity, and specificity. Based on the combined model, a nomogram risk prediction model was established, and the consistency index (C-index) and the calibration curve were obtained. In the training and testing sets, the AUC of the prediction performance of the conventional ultrasonic-texture feature combined model was higher than that of the conventional ultrasonic model and the texture feature model. In the training set, the AUC of the combined model was 0.88, while in the testing set, AUC was 0.87. In addition, the C-index results were also favorable (0.89 in the training set and 0.84 in the testing set). Furthermore, the calibration curve was close to the ideal curve, indicating the accuracy of the nomogram. This study proves the performance of vascular ultrasound-based texture analysis in identifying the vulnerable carotid plaques. Texture feature extraction combined with CDU sonogram features can accurately predict the vulnerability of AP.

CT-based radiomics signature for differentiation between cardiac tumors and a thrombi: a retrospective, multicenter study

The study aimed to develop and validate whether the computed tomography (CT) radiomics analysis is effective in differentiating cardiac tumors and thrombi. For this retrospective study, a radiomics model was developed on the basis of a training dataset of 192 patients (61.9 ± 13.3 years, 90 men) with cardiac masses detected in cardiac CT from January 2010 to September 2019. We constructed three models for discriminating between a cardiac tumor and a thrombus: a radiomics model, a clinical model, which included clinical and conventional CT variables, and a model that combined clinical and radiomics models. In the training dataset, the radiomics model and the combined model yielded significantly higher differentiation performance between cardiac tumors and cardiac thrombi than the clinical model (AUC 0.973 vs 0.870, p < 0.001 and AUC 0.983 vs 0.870, p < 0.001, respectively). In the external validation dataset with 63 patients (59.8 ± 13.2 years, 26 men), the combined model yielded a larger AUC compared to the clinical model (AUC 0.911 vs 0.802, p = 0.037). CT radiomics analysis is effective in differentiating cardiac tumors and thrombi. In conclusion, the combination of clinical, conventional CT, and radiomics features demonstrated an additional benefit in differentiating between cardiac tumor and thrombi compared to clinical data and conventional CT features alone.

Radiomics Feature Analysis Using Native T1 Mapping for Discriminating Between Cardiac Tumors and Thrombi

RATIONALE AND OBJECTIVES

Accurate differential diagnosis is essential because cardiac tumors and thrombi have different prognoses and therapeutic approaches. Native T1 map provides an objective T1 time quantifications of cardiac mass without the need for a contrast agent. We examined the diagnostic performance of radiomics features for differentiating cardiac tumors from thrombi using cardiac magnetic resonance imaging T1 mapping technique compared to that of late gadolinium enhancement (LGE) imaging.

MATERIALS AND METHODS

This retrospective study included 22 cardiac tumors and 21 thrombi of 41 patients who underwent cardiac magnetic resonance imaging from December 2013 to May 2018. Fifty-six radiomics features were extracted from native T1 images. The least absolute shrinkage and selection operator method was used for feature selection and rad score extraction. The diagnostic performance of the rad score was compared to that of the native T1 value (mean T1) and LGE ratio.

RESULTS

The area under the receiver operating characteristic curve of the rad score was higher than that of the mean T1 and LGE ratio (0.98 vs. 0.86 vs. 0.82, p = 0.001). With the optimal cut-off value, the rad score showed sensitivity, specificity, and accuracy of 95.4%, 95.2%, and 95.2%, respectively. Combination of the rad score and mean T1 showed a significantly higher diagnostic performance than mean T1 (p = 0.019) or LGE ratio (p = 0.022).

CONCLUSION

The rad score derived from native T1 maps can differentiate thrombi from tumors better than the mean T1 or LGE ratio. This is valuable for determining a treatment strategy for cardiac lesions in patients who cannot tolerate contrast agents.

Diagnosis of Cardiac Amyloidosis Using a Radiomics Approach Applied to Late Gadolinium-Enhanced Cardiac Magnetic Resonance Images: A Retrospective, Multicohort, Diagnostic Study

Objectives

To assess the potential of a radiomics approach of late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) in the diagnosis of cardiac amyloidosis (CA).

Materials and Methods

This retrospective study included 200 patients with biopsy-proven light-chain (AL) amyloidosis. CA was diagnosed on the basis of systemic amyloidosis confirmed with evidence of cardiac involvement by imaging and clinical biomarkers. A total of 139 patients [54 ± 8 years, 75 (54%) men] in our institution were divided into training cohort [n = 97, mean age of 53 ± 8 years, 54 (56%) men] and internal validation cohort [n = 42, mean age: 56 ± 8 years, 21 (50%) men] with a ratio of 7:3, while 61 patients [mean age: 60 ± 9 years, 42 (69%) men] from the other two institutions were enrolled for external validation. Radiomics features were extracted from global (all short-axis images from base-to-apex) left ventricular (LV) myocardium and three different segments (basal, midventricular, and apex) on short-axis LGE images using the phase-sensitive reconstruction (PSIR) sequence. The Boruta algorithm was used to select the radiomics features. This model was built using the XGBoost algorithm. The two readers performed qualitative and semiquantitative assessment of the LGE images based on the visual LGE patterns, while the quantitative assessment was measured using a dedicated semi-automatic CMR software. The diagnostic performance of the radiomics and other qualitative and quantitative parameters were compared by a receiver operating characteristic (ROC) curve analysis. A correlation between radiomics and the degree of myocardial involvement by amyloidosis was tested.

Results

A total of 1,906 radiomics features were extracted for each LV section. No statistical significance was indicated between any two slices for diagnosing CA, and the highest area under the curve (AUC) was found in basal section {0.92 [95% confidence interval (CI), 0.86–0.97] in the LGE images in the training set, 0.89 (95% CI, 0.79–1.00) in the internal validation set, and 0.92 (95% CI, 0.85–0.99) in the external validation set}, which was superior to the visual assessment and quantitative LGE parameters. Moderate correlations between global or basal radiomics scores (Rad-scores) and Mayo stage in all patients were reported (Spearman’s Rho = 0.61, 0.62; all p < 0.01).

Conclusion

A radiomics analysis of the LGE images provides incremental information compared with the visual assessment and quantitative parameters on CMR to diagnose CA. Radiomics was moderately correlated with the severity of CA. Further studies are needed to assess the prognostic significance of radiomics in patients with CA.

Quality of science and reporting for radiomics in cardiac magnetic resonance imaging studies: a systematic review

OBJECTIVES

To evaluate the quality of radiomics studies using cardiac magnetic resonance imaging (CMR) according to the radiomics quality score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines, and the standards defined by the Image Biomarker Standardization Initiative (IBSI) and identify areas needing improvement.

MATERIALS AND METHODS

PubMed and Embase were searched to identify radiomics studies using CMR until March 10, 2021. Of the 259 identified articles, 32 relevant original research articles were included. Studies were scored according to the RQS, TRIPOD guidelines, and IBSI standards by two cardiac radiologists.

RESULTS

The mean RQS was 14.3% of the maximum (5.16 out of 36). RQS were low for the demonstration of validation (-60.6%), calibration statistics (1.6%), potential clinical utility (3.1%), and open science (3.1%) items. No study conducted a phantom study or cost-effectiveness analysis. The adherence to TRIPOD guidelines was 55.9%. Studies were deficient in reporting title (3.1%), stating objective in abstract and introduction (6.3% and 9.4%), missing data (0%), discrimination/calibration (3.1%), and how to use the prediction model (3.1%). According to the IBSI standards, non-uniformity correction, image interpolation, grey-level discretization, and signal intensity normalization were performed in two (6.3%), four (12.5%), six (18.8%), and twelve (37.5%) studies, respectively.

CONCLUSION

The quality of radiomics studies using CMR is suboptimal. Improvements are needed in the areas of validation, calibration, clinical utility, and open science. Complete reporting of study objectives, missing data, discrimination/calibration, how to use the prediction model, and preprocessing steps are necessary.

KEY POINTS

• The quality of science in radiomics studies using CMR is currently inadequate. • RQS were low for validation, calibration, clinical utility, and open science; no study conducted a phantom study or cost-effectiveness analysis. • In stating the study objective, missing data, discrimination/calibration, how to use the prediction model, and preprocessing steps, improvements are needed.

Evaluation of the dependence of radiomic features on the machine learning model

Background

In radiomic studies, several models are often trained with different combinations of feature selection methods and classifiers. The features of the best model are usually considered relevant to the problem, and they represent potential biomarkers. Features selected from statistically similarly performing models are generally not studied. To understand the degree to which the selected features of these statistically similar models differ, 14 publicly available datasets, 8 feature selection methods, and 8 classifiers were used in this retrospective study. For each combination of feature selection and classifier, a model was trained, and its performance was measured with AUC-ROC. The best-performing model was compared to other models using a DeLong test. Models that were statistically similar were compared in terms of their selected features.

Results

Approximately 57% of all models analyzed were statistically similar to the best-performing model. Feature selection methods were, in general, relatively unstable (0.58; range 0.35–0.84). The features selected by different models varied largely (0.19; range 0.02–0.42), although the selected features themselves were highly correlated (0.71; range 0.4–0.92).

Conclusions

Feature relevance in radiomics strongly depends on the model used, and statistically similar models will generally identify different features as relevant. Considering features selected by a single model is misleading, and it is often not possible to directly determine whether such features are candidate biomarkers.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-022-01170-2.

Predicting Chronic Myocardial Ischemia Using CCTA-Based Radiomics Machine Learning Nomogram

BACKGROUND

Coronary computed tomography angiography (CCTA) is a well-established non-invasive diagnostic test for the assessment of coronary artery diseases (CAD). CCTA not only provides information on luminal stenosis but also permits non-invasive assessment and quantitative measurement of stenosis based on radiomics.

PURPOSE

This study is aimed to develop and validate a CT-based radiomics machine learning for predicting chronic myocardial ischemia (MIS).

METHODS

CCTA and SPECT-myocardial perfusion imaging (MPI) of 154 patients with CAD were retrospectively analyzed and 94 patients were diagnosed with MIS. The patients were randomly divided into two sets: training (n = 107) and test (n = 47). Features were extracted for each CCTA cross-sectional image to identify myocardial segments. Multivariate logistic regression was used to establish a radiomics signature after feature dimension reduction. Finally, the radiomics nomogram was built based on a predictive model of MIS which in turn was constructed by machine learning combined with the clinically related factors. We then validated the model using data from 49 CAD patients and included 18 MIS patients from another medical center. The receiver operating characteristic curve evaluated the diagnostic accuracy of the nomogram based on the training set and was validated by the test and validation set. Decision curve analysis (DCA) was used to validate the clinical practicability of the nomogram.

RESULTS

The accuracy of the nomogram for the prediction of MIS in the training, test and validation sets was 0.839, 0.832, and 0.816, respectively. The diagnosis accuracy of the nomogram, signature, and vascular stenosis were 0.824, 0.736 and 0.708, respectively. A significant difference in the number of patients with MIS between the high and low-risk groups was identified based on the nomogram (P < .05). The DCA curve demonstrated that the nomogram was clinically feasible.

CONCLUSION

The radiomics nomogram constructed based on the image of CCTA act as a non-invasive tool for predicting MIS that helps to identify high-risk patients with coronary artery disease.

Radiomics in Cardiovascular Disease Imaging: from Pixels to the Heart of the Problem

Purpose of Review

This review of the literature aims to present potential applications of radiomics in cardiovascular radiology and, in particular, in cardiac imaging.

Recent Findings

Radiomics and machine learning represent a technological innovation which may be used to extract and analyze quantitative features from medical images. They aid in detecting hidden pattern in medical data, possibly leading to new insights in pathophysiology of different medical conditions. In the recent literature, radiomics and machine learning have been investigated for numerous potential applications in cardiovascular imaging. They have been proposed to improve image acquisition and reconstruction, for anatomical structure automated segmentation or automated characterization of cardiologic diseases.

Summary

The number of applications for radiomics and machine learning is continuing to rise, even though methodological and implementation issues still limit their use in daily practice. In the long term, they may have a positive impact in patient management.

CNN-KCL: Automatic myocarditis diagnosis using convolutional neural network combined with k-means clustering

Myocarditis is the form of an inflammation of the middle layer of the heart wall which is caused by a viral infection and can affect the heart muscle and its electrical system. It has remained one of the most challenging diagnoses in cardiology. Myocardial is the prime cause of unexpected death in approximately 20% of adults less than 40 years of age. Cardiac MRI (CMR) has been considered a noninvasive and golden standard diagnostic tool for suspected myocarditis and plays an indispensable role in diagnosing various cardiac diseases. However, the performance of CMR depends heavily on the clinical presentation and features such as chest pain, arrhythmia, and heart failure. Besides, other imaging factors like artifacts, technical errors, pulse sequence, acquisition parameters, contrast agent dose, and more importantly qualitatively visual interpretation can affect the result of the diagnosis. This paper introduces a new deep learning-based model called Convolutional Neural Network-Clustering (CNN-KCL) to diagnose Myocarditis. In this study, we used 47 subjects with a total number of 98,898 images to diagnose myocarditis disease. Our results demonstrate that the proposed method achieves an accuracy of 97.41% based on 10 fold-cross validation technique with 4 clusters for diagnosis of Myocarditis. To the best of our knowledge, this research is the first to use deep learning algorithms for the diagnosis of myocarditis.

Radiomics Analysis Derived From LGE-MRI Predict Sudden Cardiac Death in Participants With Hypertrophic Cardiomyopathy

Objectives: To identify significant radiomics features derived from late gadolinium enhancement (LGE) images in participants with hypertrophic cardiomyopathy (HCM) and assess their prognostic value in predicting sudden cardiac death (SCD) endpoint.

Method: The 157 radiomic features of 379 sequential participants with HCM who underwent cardiovascular magnetic resonance imaging (MRI) were extracted. CoxNet (Least Absolute Shrinkage and Selection Operator (LASSO) and Elastic Net) and Random Forest models were applied to optimize feature selection for the SCD risk prediction and cross-validation was performed.

Results: During a median follow-up of 29 months (interquartile range, 20–42 months), 27 participants with HCM experienced SCD events. Cox analysis revealed that two selected features, local binary patterns (LBP) (19) (hazard ratio (HR), 1.028, 95% CI: 1.032–1.134; P = 0.001) and Moment (1) (HR, 1.212, 95%CI: 1.032–1.423; P = 0.02) provided significant prognostic value to predict the SCD endpoints after adjustment for the clinical risk predictors and late gadolinium enhancement. Furthermore, the univariately significant risk predictor was improved by the addition of the selected radiomics features, LBP (19) and Moment (1), to predict SCD events (P < 0.05).

Conclusion: The radiomics features of LBP (19) and Moment (1) extracted from LGE images, reflecting scar heterogeneity, have independent prognostic value in identifying high SCD risk patients with HCM.

Cardiac Magnetic Resonance Radiomics Reveal Differential Impact of Sex, Age, and Vascular Risk Factors on Cardiac Structure and Myocardial Tissue

Background: Cardiovascular magnetic resonance (CMR) radiomics analysis provides multiple quantifiers of ventricular shape and myocardial texture, which may be used for detailed cardiovascular phenotyping. Objectives: We studied variation in CMR radiomics phenotypes by age and sex in healthy UK Biobank participants. Then, we examined independent associations of classical vascular risk factors (VRFs: smoking, diabetes, hypertension, high cholesterol) with CMR radiomics features, considering potential sex and age differential relationships. Design: Image acquisition was with 1.5 Tesla scanners (MAGNETOM Aera, Siemens). Three regions of interest were segmented from short axis stack images using an automated pipeline: right ventricle, left ventricle, myocardium. We extracted 237 radiomics features from each study using Pyradiomics. In a healthy subset of participants (n = 14,902) without cardiovascular disease or VRFs, we estimated independent associations of age and sex with each radiomics feature using linear regression models adjusted for body size. We then created a sample comprising individuals with at least one VRF matched to an equal number of healthy participants (n = 27,400). We linearly modelled each radiomics feature against age, sex, body size, and all the VRFs. Bonferroni adjustment for multiple testing was applied to all p-values. To aid interpretation, we organised the results into six feature clusters. Results: Amongst the healthy subset, men had larger ventricles with dimmer and less texturally complex myocardium than women. Increasing age was associated with smaller ventricles and greater variation in myocardial intensities. Broadly, all the VRFs were associated with dimmer, less varied signal intensities, greater uniformity of local intensity levels, and greater relative presence of low signal intensity areas within the myocardium. Diabetes and high cholesterol were also associated with smaller ventricular size, this association was of greater magnitude in men than women. The pattern of alteration of radiomics features with the VRFs was broadly consistent in men and women. However, the associations between intensity based radiomics features with both diabetes and hypertension were more prominent in women than men. Conclusions: We demonstrate novel independent associations of sex, age, and major VRFs with CMR radiomics phenotypes. Further studies into the nature and clinical significance of these phenotypes are needed.

Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis

Objectives

To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG).

Methods

Patients with histologically confirmed TET in the years 2000–2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance.

Results

105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22–82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3–94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9–93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8–79.5).

Conclusions

CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.

Texture analysis imaging "what a clinical radiologist needs to know"

Texture analysis has arisen as a tool to explore the amount of data contained in images that cannot be explored by humans visually. Radiomics is a method that extracts a large number of features from radiographic medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover disease characteristics. The goal of both radiomics and texture analysis is to go beyond size or human-eye based semantic descriptors, to enable the non-invasive extraction of quantitative radiological data to correlate them with clinical outcomes or pathological characteristics. In the latest years there has been a flourishing sub-field of radiology where texture analysis and radiomics have been used in many settings. It is difficult for the clinical radiologist to cope with such amount of data in all the different radiological sub-fields and to identify the most significant papers. The aim of this review is to provide a tool to better understand the basic principles underlining texture analysis and radiological data mining and a summary of the most significant papers of the latest years.

New Imaging Signatures of Cardiac Alterations in Ischaemic Heart Disease and Cerebrovascular Disease Using CMR Radiomics

Background: Ischaemic heart disease (IHD) and cerebrovascular disease are two closely inter-related clinical entities. Cardiovascular magnetic resonance (CMR) radiomics may capture subtle cardiac changes associated with these two diseases providing new insights into the brain-heart interactions. Objective: To define the CMR radiomics signatures for IHD and cerebrovascular disease and study their incremental value for disease discrimination over conventional CMR indices. Methods: We analysed CMR images of UK Biobank's subjects with pre-existing IHD, ischaemic cerebrovascular disease, myocardial infarction (MI), and ischaemic stroke (IS) (n = 779, 267, 525, and 107, respectively). Each disease group was compared with an equal number of healthy controls. We extracted 446 shape, first-order, and texture radiomics features from three regions of interest (right ventricle, left ventricle, and left ventricular myocardium) in end-diastole and end-systole defined from segmentation of short-axis cine images. Systematic feature selection combined with machine learning (ML) algorithms (support vector machine and random forest) and 10-fold cross-validation tests were used to build the radiomics signature for each condition. We compared the discriminatory power achieved by the radiomics signature with conventional indices for each disease group, using the area under the curve (AUC), receiver operating characteristic (ROC) analysis, and paired t-test for statistical significance. A third model combining both radiomics and conventional indices was also evaluated. Results: In all the study groups, radiomics signatures provided a significantly better disease discrimination than conventional indices, as suggested by AUC (IHD:0.82 vs. 0.75; cerebrovascular disease: 0.79 vs. 0.77; MI: 0.87 vs. 0.79, and IS: 0.81 vs. 0.72). Similar results were observed with the combined models. In IHD and MI, LV shape radiomics were dominant. However, in IS and cerebrovascular disease, the combination of shape and intensity-based features improved the disease discrimination. A notable overlap of the radiomics signatures of IHD and cerebrovascular disease was also found. Conclusions: This study demonstrates the potential value of CMR radiomics over conventional indices in detecting subtle cardiac changes associated with chronic ischaemic processes involving the brain and heart, even in the presence of more heterogeneous clinical pictures. Radiomics analysis might also improve our understanding of the complex mechanisms behind the brain-heart interactions during ischaemia.

Automatic machine learning based on native T1 mapping can identify myocardial fibrosis in patients with hypertrophic cardiomyopathy

OBJECTIVES

To investigate the feasibility of automatic machine learning (autoML) based on native T1 mapping to predict late gadolinium enhancement (LGE) status in hypertrophic cardiomyopathy (HCM).

METHODS

Ninety-one HCM patients and 44 healthy controls who underwent cardiovascular MRI were enrolled. The native T1 maps of HCM patients were classified as LGE ( +) or LGE (-) based on location-matched LGE images. An autoML pipeline was implemented using the tree-based pipeline optimization tool (TPOT) for 3 binary classifications: LGE ( +) and LGE (-), LGE (-) and control, and HCM and control. TPOT modeling was repeated 10 times to obtain the optimal model for each classification. The diagnostic performance of the best models by slice and by case was evaluated using sensitivity, specificity, accuracy, and microaveraged area under the curve (AUC).

RESULTS

Ten prediction models were generated by TPOT for each of the 3 binary classifications. The diagnostic accuracy obtained with the best pipeline in detecting LGE status in the testing cohort of HCM patients was 0.80 by slice and 0.79 by case. In addition, the TPOT model also showed discriminability between LGE (-) patients and control (accuracy: 0.77 by slice; 0.78 by case) and for all HCM patients and controls (accuracy: 0.88 for both).

CONCLUSIONS

Native T1 map analysis based on autoML correlates with LGE ( +) or (-) status. The TPOT machine learning algorithm could be a promising method for predicting myocardial fibrosis, as reflected by the presence of LGE in HCM patients without the need for late contrast-enhanced MRI sequences.

KEY POINTS

• The tree-based pipeline optimization tool (TPOT) is a machine learning algorithm that could help predict late gadolinium enhancement (LGE) status in patients with hypertrophic cardiomyopathy. • The TPOT could serve as an adjuvant method to detect LGE by using information from native T1 maps, thus avoiding the need for contrast agent. • The TPOT also detects native T1 map alterations in LGE-negative patients with hypertrophic cardiomyopathy.

Emerging Techniques in Cardiac Magnetic Resonance Imaging

Cardiovascular disease is the leading cause of death and a significant contributor of health care costs. Noninvasive imaging plays an essential role in the management of patients with cardiovascular disease. Cardiac magnetic resonance (MR) can noninvasively assess heart and vascular abnormalities, including biventricular structure/function, blood hemodynamics, myocardial tissue composition, microstructure, perfusion, metabolism, coronary microvascular function, and aortic distensibility/stiffness. Its ability to characterize myocardial tissue composition is unique among alternative imaging modalities in cardiovascular disease. Significant growth in cardiac MR utilization, particularly in Europe in the last decade, has laid the necessary clinical groundwork to position cardiac MR as an important imaging modality in the workup of patients with cardiovascular disease. Although lack of availability, limited training, physician hesitation, and reimbursement issues have hampered widespread clinical adoption of cardiac MR in the United States, growing clinical evidence will ultimately overcome these challenges. Advances in cardiac MR techniques, particularly faster image acquisition, quantitative myocardial tissue characterization, and image analysis have been critical to its growth. In this review article, we discuss recent advances in established and emerging cardiac MR techniques that are expected to strengthen its capability in managing patients with cardiovascular disease. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

Evaluation of 68Ga-PSMA-11 PET-MRI in Patients with Advanced Prostate Cancer Receiving 177Lu-PSMA-617 Therapy: A Radiomics Analysis

¹⁷⁷Lutetium PSMA-617 (Lu-PSMA) therapy in patients with metastatic castration resistant prostate cancer (mCRPC) has gained visibility through the ongoing phase III trial. The data on prediction of therapy outcome and survival out of pretherapeutic imaging parameters is still sparse. In this study, the predictive and prognostic value of radiomic features from ⁶⁸Ga-PSMA-11 PET-MRI are analyzed. In total, 21 patients with mCRPC underwent ⁶⁸Ga-PSMA-11 PET-MRI before Lu-PSMA therapy. The PET-positive tumor volume was defined and transferred to whole-body T2-, T1- and contrast-enhanced T1-weighted MRI-sequences. The radiomic features from PET and MRI sequences were extracted by using a freely available software package. For selecting features that allow differentiation of biochemical response (PSA decrease > 50%), a stepwise dimension reduction was performed. Logistic regression models were fitted, and selected features were tested for their prognostic value (overall survival) in all patients. Eight patients achieved biochemical response after Lu-PSMA therapy. Ten independent radiomic features differentiated well between responders and non-responders. The logistic regression model, including the feature interquartile range from T2-weighted images, revealed the highest accuracy (AUC = 0.83) for the prediction of biochemical response after Lu-PSMA therapy. Within the final model, patients with a biochemical response (p = 0.003) and higher T2 interquartile range values in pre-therapeutic imaging (p = 0.038) survived significantly longer. This proof-of-concept study provides first evidence on a potential predictive and prognostic value of radiomic analysis of pretherapeutic ⁶⁸Ga-PSMA-11 PET-MRI before Lu-PSMA therapy.

Myocardial area at risk and salvage in reperfused acute MI measured by texture analysis of cardiac T2 mapping and its prediction value of functional recovery in the convalescent stage

OBJECTIVES

We sought to distinguish area at risk from salvage myocardial zone and to predict left ventricle functional recovery in the convalescent stage by Texture Analysis (TA) of T2-Mapping.

METHODS

One hundred and six patients diagnosed with AMI and treated with percutaneous coronary intervention (PCI) underwent acute cardiac magnetic resonance imaging (CMR) and 45 of whom had a subsequent CMR scan following recovery. Cine imaging, T2-Mapping, T2-weighted STIR imaging, and LGE imaging were performed. In the texture analysis, regions of interest (infarcted, salvageable, and remote) were drawn by two blinded, independent readers.

RESULTS

Seven independent texture features on T2-Mapping were selected: Perc.50%, S(2,2)InvDfMom, S(2.-2)AngScMom, S(4,0)Entropy, 45dgrLngREmph, 45dgr_Fraction and 135dr_GLevNonU. Among them, the average value of 135dr_GLevNonU in the infarct zone, AAR zone, and the remote zone was: 61.96±26.03, 31.811±18.933 and 99.839±26.231, respectively. Additionally, 135dr_GLevNonU provided the highest area under the curve (AUC) from the receiver operating characteristic curve (ROC curve) for distinguishing AAR from the infarct zone in each subgroup (all patients, patients with MVO and)were 0.845 ± 0.052 0.855 ± 0.083 and 0.845 ± 0.066, respectively, and were more promise than T2-Mapping mean (p<0.001). The AUC for differentiating AAR from the remote zone is 0.942±0.041. Texture features are not associated with convalescent decreased strain, ejection fraction (EF) or left ventricle remodeling (LVR) in analysis (p>0.05).

CONCLUSION

TA of T2-mapping can distinguish AAR from both the infarct zone and the remote myocardial zone without LGE imaging in reperfused AMI. However, these features are not able to predict patients' functional recovery in the convalescent stage.

Cardiac magnetic resonance radiomics: basic principles and clinical perspectives

Radiomics is a novel image analysis technique, whereby voxel-level information is extracted from digital images and used to derive multiple numerical quantifiers of shape and tissue character. Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function. Conventional analysis of CMR scans is mostly reliant on qualitative image analysis and basic geometric quantifiers. Small proof-of-concept studies have demonstrated the feasibility and superior diagnostic accuracy of CMR radiomics analysis over conventional reporting. CMR radiomics has the potential to transform our approach to defining image phenotypes and, through this, improve diagnostic accuracy, treatment selection, and prognostication. The purpose of this article is to provide an overview of radiomics concepts for clinicians, with particular consideration of application to CMR. We will also review existing literature on CMR radiomics, discuss challenges, and consider directions for future work.

Machine learning and network medicine: a novel approach for precision medicine and personalized therapy in cardiomyopathies

The early identification of pathogenic mechanisms is essential to predict the incidence and progression of cardiomyopathies and to plan appropriate preventive interventions. Noninvasive cardiac imaging such as cardiac computed tomography, cardiac magnetic resonance, and nuclear imaging plays an important role in diagnosis and management of cardiomyopathies and provides useful prognostic information. Most molecular factors exert their functions by interacting with other cellular components, thus many diseases reflect perturbations of intracellular networks. Indeed, complex diseases and traits such as cardiomyopathies are caused by perturbations of biological networks. The network medicine approach, by integrating systems biology, aims to identify pathological interacting genes and proteins, revolutionizing the way to know cardiomyopathies and shifting the understanding of their pathogenic phenomena from a reductionist to a holistic approach. In addition, artificial intelligence tools, applied to morphological and functional imaging, could allow imaging scans to be automatically analyzed to extract new parameters and features for cardiomyopathy evaluation. The aim of this review is to discuss the tools of network medicine in cardiomyopathies that could reveal new candidate genes and artificial intelligence imaging-based features with the aim to translate into clinical practice as diagnostic, prognostic, and predictive biomarkers and shed new light on the clinical setting of cardiomyopathies. The integration and elaboration of clinical habits, molecular big data, and imaging into machine learning models could provide better disease phenotyping, outcome prediction, and novel drug targets, thus opening a new scenario for the implementation of precision medicine for cardiomyopathies.

A radiomic approach to predict myocardial fibrosis on coronary CT angiography in hypertrophic cardiomyopathy

BACKGROUND

Late gadolinium enhancement (LGE) derived from cardiac magnetic resonance (CMR) represents myocardial fibrosis (MF) and is associated with prognosis in hypertrophic cardiomyopathy (HCM). However, it cannot be evaluated when CMR is unavailable. Hence, we aimed to investigate the ability of radiomic features derived from coronary computed tomography angiography (CCTA) to detect the presence and extent of MF in HCM, with LGE as references.

METHODS

161 patients with HCM who underwent CCTA and CMR were retrospectively enrolled and randomly divided into training (107 patients, 1712 segments) and testing cohorts (54 patients, 864 segments). Segments were obtained according to AHA 17-segment method. Radiomic features were extracted from per-segment and entire myocardium regions, and multiple machine-learning algorithms were used for radiomic signatures (Rad-sig) generation and model building. Four models were established by multivariable logistic regression using Rad-sig (R-model), clinical characteristic (C-model), echocardiography parameters (E-model), and all features integrated (Integ-model) to identify LGE/left ventricular mass ≥ 15%.

RESULTS

The model achieved good diagnostic accuracy in both training (area under the curve [AUC]:0.81, 95% confidence interval [CI]: 0.78-0.83) and testing cohort (AUC: 0.78, 95%CI: 0.75-0.81) on a per-segment basis for the presence of MF. The Integ-model owned the highest discriminative ability for patients with LGE/left ventricular mass ≥ 15% in both training and testing cohorts with AUC of 0.94 (95%CI: 0.89-0.98) and 0.92 (95%CI: 0.85-0.99), respectively.

CONCLUSIONS

Our radiomic models were considered as useful and complementary biomarkers for the evaluation of the presence and extent of MF on CCTA, facilitating clinical decision-making and risk stratification in HCM patients.