Search

BACKGROUND: Coronary artery segmentation is a prerequisite in computer-aided diagnosis of Coronary Artery Disease (CAD). However, segmentation of coronary arteries in Coronary Computed Tomography Angiography (CCTA) images faces several challenges. The current segmentation approaches are unable to effectively address these challenges and existing problems such as the need for manual interaction or low segmentation accuracy. OBJECTIVE: A Multi-scale Feature Learning and Rectification (MFLR) network is proposed to tackle the challenges and achieve automatic and accurate segmentation of coronary arteries. METHODS: The MFLR network introduces a multi-scale feature extraction module in the encoder to effectively capture contextual information under different receptive fields. In the decoder, a feature correction and fusion module is proposed, which employs high-level features containing multi-scale information to correct and guide low-level features, achieving fusion between the two-level features to further improve segmentation performance. RESULTS: The MFLR network achieved the best performance on the dice similarity coefficient, Jaccard index, Recall, F1-score, and 95% Hausdorff distance, for both in-house and public datasets. CONCLUSION: Experimental results demonstrate the superiority and good generalization ability of the MFLR approach. This study contributes to the accurate diagnosis and treatment of CAD, and it also informs other segmentation applications in medicine. [ABSTRACT FROM AUTHOR]

Background: Papillary muscle (PM) infarction (PMI) detected by cardiac magnetic resonance imaging (CMR) is associated with poor outcomes. Whether PM parameters provide more value for mitral regurgitation (MR) management currently remains unclear. Therefore, we examined the prognostic value of PMI using CMR in patients with MR. Methods: Between March 2018 and July 2023, we retrospectively enrolled 397 patients with MR undergoing CMR. CMR was used to detect PMI qualitatively and quantitively. We also collected baseline clinical, echocardiography, and follow‐up data. Results: Of the 397 patients with MR (52.4 ± 13.9 years), 117 (29.5%) were assigned to the PMI group, with 280 (70.5%) in the non‐PMI group. PMI was demonstrated more in the posteromedial PM (PM‐PM, 98/117) than in the anterolateral PM (AL‐PM, 45/117). Compared with patients without PMI, patients with PMI had a decreased AL‐PM (41.5 ± 5.4 vs. 45.6 ± 5.3)/PM‐PM diastolic length (35.0 ± 5.2 vs. 37.9 ± 4.0), PM‐longitudinal strain (LS, 20.4 ± 6.1 vs. 24.9 ± 4.6), AL‐PM‐LS (19.7 ± 6.8 vs. 24.7 ± 5.6)/PM‐PM‐LS (21.2 ± 7.9 vs. 25.2 ± 6.0), and increased inter‐PM distance (25.7 ± 8.0 vs. 22.7 ± 6.2, all p < 0.001). Multiple logistic regression analyses identified male sex (odds ratio [OR] = 3.65, 95% confidence interval = 1.881−7.081, p < 0.001) diabetes mellitus (OR/95% CI/p = 2.534/1.13–5.68/0.024), AL‐PM diastolic length (OR/95% CI/p = 0.841/0.77–0.92/< 0.001), PM‐PM diastolic length (OR/95% CI/p = 0.873/0.79–0.964/0.007), inter‐PM distance (OR/95% CI/p = 1.087/1.028–1.15/0.003), AL‐PM‐LS (OR/95% CI/p = 0.892/0.843–0.94/< 0.001), and PM‐PM‐LS (OR/95% CI/p = 0.95/0.9–0.992/0.021) as independently associated with PMI. Over a 769 ± 367‐day follow‐up, 100 (25.2%) patients had arrhythmia. Cox regression analyses indicated that PMI (hazard ratio [HR]/95% CI/p = 1.644/1.062–2.547/0.026), AL‐PM‐LS (HR/95% CI/p = 0.937/0.903–0.973/0.001), and PM‐PM‐LS (HR/95% CI/p = 0.933/0.902–0.965/< 0.001) remained independently associated with MR. Conclusions: The CMR‐derived PMI and LS parameters improve the evaluation of PM dysfunction, indicating a high risk for arrhythmia, and provide additive risk stratification for patients with MR. [ABSTRACT FROM AUTHOR]

Background: The curved planar reformation (CPR) technique is one of the most commonly used methods in clinical practice to locate coronary arteries in medical images. Purpose: The artery centerline is the cornerstone for the generation of the CPR image. Here, we describe the development of a new fully automatic artery centerline tracker with the aim of increasing the efficiency and accuracy of the process. Methods: We propose a COronary artery Centerline Tracker (COACT) framework which consists of an ostium point finder (OPFinder) model, an intersection point detector (IPDetector) model and a set of centerline tracking strategies. The output of OPFinder is the ostium points. The function of the IPDetector is to predict the intersections of a sample sphere and the centerlines. The centerline tracking process starts from two ostium points detected by the OPFinder, and combines the results of the IPDetector with a series of strategies to gradually reconstruct the coronary artery centerline tree. Results: Two coronary CT angiography (CCTA) datasets were used to validate the models. Dataset1 contains 160 cases (32 for test and 128 for training) and dataset2 contains 70 cases (20 for test and 50 for training). The results show that the average distance between the ostium points predicted by the OPFinder and the manually annotated ostium points was 0.88 mm, which is similar to the differences between the results obtained by two observers (0.85 mm). For the IPDetector, the average overlap of the predicted and ground truth intersection points was 97.82% and this is also close to the inter‐observer agreement of 98.50%. For the entire coronary centerline tree, the overlap between the results obtained by COACT and the gold standard was 94.33%, which is slightly lower than the inter‐observer agreement, 98.39%. Conclusions: We have developed a fully automatic centerline tracking method for CCTA scans and achieved a satisfactory result. The proposed algorithms are also incorporated in the medical image analysis platform TIMESlice (https://slice‐doc.netlify.app) for further studies. [ABSTRACT FROM AUTHOR]