RESUMEN
Background: Segmentation of cardiac structures is an important step in evaluation of the heart on imaging. There has been growing interest in how artificial intelligence (AI) methods-particularly deep learning (DL)-can be used to automate this process. Existing AI approaches to cardiac segmentation have mostly focused on cardiac MRI. This systematic review aimed to appraise the performance and quality of supervised DL tools for the segmentation of cardiac structures on CT. Methods: Embase and Medline databases were searched to identify related studies from January 1, 2013 to December 4, 2023. Original research studies published in peer-reviewed journals after January 1, 2013 were eligible for inclusion if they presented supervised DL-based tools for the segmentation of cardiac structures and non-coronary great vessels on CT. The data extracted from eligible studies included information about cardiac structure(s) being segmented, study location, DL architectures and reported performance metrics such as the Dice similarity coefficient (DSC). The quality of the included studies was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: 18 studies published after 2020 were included. The DSC scores median achieved for the most commonly segmented structures were left atrium (0.88, IQR 0.83-0.91), left ventricle (0.91, IQR 0.89-0.94), left ventricle myocardium (0.83, IQR 0.82-0.92), right atrium (0.88, IQR 0.83-0.90), right ventricle (0.91, IQR 0.85-0.92), and pulmonary artery (0.92, IQR 0.87-0.93). Compliance of studies with CLAIM was variable. In particular, only 58% of studies showed compliance with dataset description criteria and most of the studies did not test or validate their models on external data (81%). Conclusion: Supervised DL has been applied to the segmentation of various cardiac structures on CT. Most showed similar performance as measured by DSC values. Existing studies have been limited by the size and nature of the training datasets, inconsistent descriptions of ground truth annotations and lack of testing in external data or clinical settings. Systematic Review Registration: [www.crd.york.ac.uk/prospero/], PROSPERO [CRD42023431113].
RESUMEN
Background: Chronic pulmonary embolism (PE) may result in pulmonary hypertension (CTEPH). Automated CT pulmonary angiography (CTPA) interpretation using artificial intelligence (AI) tools has the potential for improving diagnostic accuracy, reducing delays to diagnosis and yielding novel information of clinical value in CTEPH. This systematic review aimed to identify and appraise existing studies presenting AI tools for CTPA in the context of chronic PE and CTEPH. Methods: MEDLINE and EMBASE databases were searched on 11 September 2023. Journal publications presenting AI tools for CTPA in patients with chronic PE or CTEPH were eligible for inclusion. Information about model design, training and testing was extracted. Study quality was assessed using compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: Five studies were eligible for inclusion, all of which presented deep learning AI models to evaluate PE. First study evaluated the lung parenchymal changes in chronic PE and two studies used an AI model to classify PE, with none directly assessing the pulmonary arteries. In addition, a separate study developed a CNN tool to distinguish chronic PE using 2D maximum intensity projection reconstructions. While another study assessed a novel automated approach to quantify hypoperfusion to help in the severity assessment of CTEPH. While descriptions of model design and training were reliable, descriptions of the datasets used in training and testing were more inconsistent. Conclusion: In contrast to AI tools for evaluation of acute PE, there has been limited investigation of AI-based approaches to characterising chronic PE and CTEPH on CTPA. Existing studies are limited by inconsistent reporting of the data used to train and test their models. This systematic review highlights an area of potential expansion for the field of AI in medical image interpretation.There is limited knowledge of A systematic review of artificial intelligence tools for chronic pulmonary embolism in CT. This systematic review provides an assessment on research that examined deep learning algorithms in detecting CTEPH on CTPA images, the number of studies assessing the utility of deep learning on CTPA in CTEPH was unclear and should be highlighted.
RESUMEN
The diagnostic strategy for chronic thromboembolic pulmonary hypertension (CTEPH) is composed of two components required for a diagnosis of CTEPH: the presence of chronic pulmonary embolism and an elevated pulmonary artery pressure. The current guidelines require that ventilation-perfusion single-photon emission computed tomography (VQ-SPECT) is used for the first step diagnosis of chronic pulmonary embolism. However, VQ-SPECT exposes patients to ionizing radiation in a radiation sensitive population. The prospective, multicenter, comparative phase III diagnostic trial CTEPH diagnosis Europe - MRI (CHANGE-MRI, ClinicalTrials.gov identifier NCT02791282) aims to demonstrate whether functional lung MRI can serve as an equal rights alternative to VQ-SPECT in a diagnostic strategy for patients with suspected CTEPH. Positive findings are verified with catheter pulmonary angiography or computed tomography pulmonary angiography (gold standard). For comparing the imaging methods, a co-primary endpoint is used. (i) the proportion of patients with positive MRI in the group of patients who have a positive SPECT and gold standard diagnosis for chronic pulmonary embolism and (ii) the proportion of patients with positive MRI in the group of patients with negative SPECT and gold standard. The CHANGE-MRI trial will also investigate the performance of functional lung MRI without i.v. contrast agent as an index test and identify cardiac, hemodynamic, and pulmonary MRI-derived parameters to estimate pulmonary artery pressures and predict 6-12 month survival. Ultimately, this study will provide the necessary evidence for the discussion about changes in the recommendations on the diagnostic approach to CTEPH.
RESUMEN
OBJECTIVE: Pulmonary arterial hypertension (PAH) is a life-threatening complication of connective tissue diseases (CTD). Our aim was to compare the diagnostic utility of noninvasive imaging modalities, i.e., magnetic resonance imaging (MRI), computed tomography (CT), and echocardiography, in evaluation of these patients. METHODS: In total, 81 consecutive patients with CTD and suspected PH underwent cardiac MRI, CT, and right heart catheterization (RHC) within 48 hours. Functional cardiac MRI variables [ventricle areas and ratios, delayed myocardial enhancement, position of the interventricular septum, right ventricular mass, ventricular mass index (VMI), and pulmonary artery distensibility] were all evaluated. The pulmonary artery size, pulmonary artery/aortic ratio (PA/Ao), left and right ventricular (RV) diameter ratio, RV wall thickness, and grade of tricuspid regurgitation were measured on CT. Tricuspid gradient (TG) and size of the RV were assessed using echocardiography. RESULTS: In our study of 81 patients with CTD, 55 had PAH, 22 had no PH, and 4 had PH owing to left heart disease. There was good correlation between mean pulmonary artery pressure (mPAP) and pulmonary vascular resistance (PVR) measured by RHC and VMI derived from MRI (mPAP, r = 0.69, p < 0.001; PVR, r = 0.78, p < 0.001) and systolic area ratio (mPAP, r = 0.69, p < 0.001; PVR, r = 0.68, p < 0.001) and TG derived from echocardiography (mPAP, r = 0.84, p < 0.001; PVR, r = 0.76, p < 0.001). In contrast, CT measures showed only moderate correlation. MRI and echocardiography each performed better as a diagnostic test for PAH than CT-derived measures: VMI ≥ 0.45 had a sensitivity of 85% and specificity 82%; and TG ≥ 40 mm Hg had a sensitivity of 86% and specificity 82%. Univariate Cox regression analysis showed the MRI measurements were better at predicting mortality. Patients with RV end diastolic volume < 135 ml had a better prognosis than those with a value > 135 ml, with a 1-year survival of 95% versus 66%, respectively. CONCLUSION: In patients with CTD and suspected PAH, cardiac MRI and echocardiography have greater diagnostic utility than CT in the assessment of patients with suspected PAH, and MRI has prognostic value.