Dataset Information

MVnet: automated time-resolved tracking of the mitral valve plane in CMR long-axis cine images with residual neural networks: a multi-center, multi-vendor study.

ABSTRACT:

Background

Mitral annular plane systolic excursion (MAPSE) and left ventricular (LV) early diastolic velocity (e') are key metrics of systolic and diastolic function, but not often measured by cardiovascular magnetic resonance (CMR). Its derivation is possible with manual, precise annotation of the mitral valve (MV) insertion points along the cardiac cycle in both two and four-chamber long-axis cines, but this process is highly time-consuming, laborious, and prone to errors. A fully automated, consistent, fast, and accurate method for MV plane tracking is lacking. In this study, we propose MVnet, a deep learning approach for MV point localization and tracking capable of deriving such clinical metrics comparable to human expert-level performance, and validated it in a multi-vendor, multi-center clinical population.

Methods

The proposed pipeline first performs a coarse MV point annotation in a given cine accurately enough to apply an automated linear transformation task, which standardizes the size, cropping, resolution, and heart orientation, and second, tracks the MV points with high accuracy. The model was trained and evaluated on 38,854 cine images from 703 patients with diverse cardiovascular conditions, scanned on equipment from 3 main vendors, 16 centers, and 7 countries, and manually annotated by 10 observers. Agreement was assessed by the intra-class correlation coefficient (ICC) for both clinical metrics and by the distance error in the MV plane displacement. For inter-observer variability analysis, an additional pair of observers performed manual annotations in a randomly chosen set of 50 patients.

Results

MVnet achieved a fast segmentation (<1 s/cine) with excellent ICCs of 0.94 (MAPSE) and 0.93 (LV e') and a MV plane tracking error of -0.10 ± 0.97 mm. In a similar manner, the inter-observer variability analysis yielded ICCs of 0.95 and 0.89 and a tracking error of -0.15 ± 1.18 mm, respectively.

Conclusion

A dual-stage deep learning approach for automated annotation of MV points for systolic and diastolic evaluation in CMR long-axis cine images was developed. The method is able to carefully track these points with high accuracy and in a timely manner. This will improve the feasibility of CMR methods which rely on valve tracking and increase their utility in a clinical setting.

SUBMITTER: Gonzales RA

PROVIDER: S-EPMC8638514 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Introduction: Deep learning demonstrates great promise for automated analysis of CMR. However, existing limitations, such as insufficient quality control and selection of target acquisitions from the full CMR exam, are holding back the introduction of deep learning tools in the clinical environment. This study aimed to develop a framework for automated detection and quality-controlled selection of standard cine sequences images from clinical CMR exams, prior to analysis of cardiac function. Materials and Methods: Retrospective study of 3,827 subjects that underwent CMR imaging. We used a total of 119,285 CMR acquisitions, acquired with scanners of different magnetic field strengths and from different vendors (1.5T Siemens and 1.5T and 3.0T Phillips). We developed a framework to select one good acquisition for each conventional cine class. The framework consisted of a first pre-processing step to exclude still acquisitions; two sequential convolutional neural networks (CNN), the first (CNNclass) to classify acquisitions in standard cine views (2/3/4-chamber and short axis), the second (CNNQC) to classify acquisitions according to image quality and orientation; a final algorithm to select one good acquisition of each class. For each CNN component, 7 state-of-the-art architectures were trained for 200 epochs, with cross entropy loss and data augmentation. Data were divided into 80% for training, 10% for validation, and 10% for testing. Results: CNNclass selected cine CMR acquisitions with accuracy ranging from 0.989 to 0.998. Accuracy of CNNQC reached 0.861 for 2-chamber, 0.806 for 3-chamber, and 0.859 for 4-chamber. The complete framework was presented with 379 new full CMR studies, not used for CNN training/validation/testing, and selected one good 2-, 3-, and 4-chamber acquisition from each study with sensitivity to detect erroneous cases of 89.7, 93.2, and 93.9%, respectively. Conclusions: We developed an accurate quality-controlled framework for automated selection of cine acquisitions prior to image analysis. This framework is robust and generalizable as it was developed on multivendor data and could be used at the beginning of a pipeline for automated cine CMR analysis to obtain full automatization from scanner to report.

Project description:Cardiac magnetic resonance (CMR) is a key tool for cardiac work-up. However, arrhythmia can be responsible for arrhythmia-related artifacts (ARA) and increased scan time using segmented sequences. The aim of this study is to evaluate the effect of cardiac arrhythmia on image quality in a comparison of a compressed sensing real-time (CSrt) cine sequence with the reference prospectively gated segmented balanced steady-state free precession (Cineref) technique regarding ARA. A total of 71 consecutive adult patients (41 males; mean age = 59.5 ± 20.1 years (95% CI: 54.7-64.2 years)) referred for CMR examination with concomitant irregular heart rate (defined by an RR interval coefficient of variation >10%) during scanning were prospectively enrolled. For each patient, two cine sequences were systematically acquired: first, the reference prospectively triggered multi-breath-hold Cineref sequence including a short-axis stack, one four-chamber slice, and a couple of two-chamber slices; second, an additional single breath-hold CSrt sequence providing the same slices as the reference technique. Two radiologists independently assessed ARA and image quality (overall, acquisition, and edge sharpness) for both techniques. The mean heart rate was 71.8 ± 19.0 (SD) beat per minute (bpm) (95% CI: 67.4-76.3 bpm) and its coefficient of variation was 25.0 ± 9.4 (SD) % (95% CI: 22.8-27.2%). Acquisition was significantly faster with CSrt than with Cineref (Cineref: 556.7 ± 145.4 (SD) s (95% CI: 496.7-616.7 s); CSrt: 23.9 ± 7.9 (SD) s (95% CI: 20.6-27.1 s); p < 0.0001). A total of 599 pairs of cine slices were evaluated (median: 8 (range: 6-14) slices per patient). The mean proportion of ARA-impaired slices per patient was 85.9 ± 22.7 (SD) % using Cineref, but this was figure was zero using CSrt (p < 0.0001). The European CMR registry artifact score was lower with CSrt (median: 1 (range: 0-5)) than with Cineref (median: 3 (range: 0-3); p < 0.0001). Subjective image quality was higher in CSrt than in Cineref (median: 3 (range: 1-3) versus 2 (range: 1-4), respectively; p < 0.0001). In line, edge sharpness was higher on CSrt cine than on Cineref images (0.054 ± 0.016 pixel-1 (95% CI: 0.050-0.057 pixel-1) versus 0.042 ± 0.022 pixel-1 (95% CI: 0.037-0.047 pixel-1), respectively; p = 0.0001). Compressed sensing real-time cine drastically reduces arrhythmia-related artifacts and thus improves cine image quality in patients with arrhythmia.