Dataset Information

Deep Learning for Classification and Selection of Cine CMR Images to Achieve Fully Automated Quality-Controlled CMR Analysis From Scanner to Report

ABSTRACT: 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.

SUBMITTER: Vergani V

PROVIDER: S-EPMC8551568 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Objectives: Endometrial peristalsis (EP) in non-pregnant uterine can be assessed by visual assessment of transvaginal ultrasound (TVUS). However, visual assessment is subjective, and the outcome depends on the sonographers and video analysts. This study aimed to create a newly developed automatic analysis algorithm for measuring the EP compared to visual assessment. Methods: A retrospective analysis was performed using the datasets from in vitro fertilization and embryo transfer (IVF-ET), who underwent the evaluation of EP by TVUS within 5 days prior to transplantation. 158 cine TVUS images were used to develop the automated analysis algorithm, and 37 cine TVUS images were evaluated by both visual and automated analysis algorithms. The algorithm was developed by applying the optical flow technology and enabled objective analysis of the number, direction, and intensity of EP. Results: The number of peristaltic waves counted by visual assessment was 4.2 ± 2.3 (mean ± standard deviation) and 4.1 ± 2.1 for doctors one and two, respectively. The number of waves counted with the algorithm was 3.6 ± 2.1 at first evaluation and 3.7 ± 2.0 at repeated evaluation. A significant difference was found between the algorithm count and visual assessment (p = 0.001, 0.002, 0.003, 0.008). The ICC values for algorithm versus manuals ranged from 0.84 to 0.96 and 0.87 to 0.96. The numbers of the cervix-to-fundus (CF), fundus-to-cervix (FC), and both cervix-to-fundal and fundus-to-cervix (CF + FC) directions of EP counted by the algorithm were 50, 52, and 32, respectively. The numbers counted by visual assessment were 43, 45, and 46, respectively. The number of EP was the same in 87% of the two algorithm counts. The number was lower between the algorithm and visual analysis (79% with complete agreement). The EP intensity assessed by the algorithm was 2.6 ± 1.1, and the peristalsis velocity was 0.147 (0.07) mm/s. Conclusion: The fully automated analysis algorithm can be used to quantify uterine peristalsis comparable to visual assessment.

Project description:BackgroundMitral 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.MethodsThe 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.ResultsMVnet 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.ConclusionA 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.

Project description:PurposeTo investigate the feasibility of using a deep learning-based approach to detect an anterior cruciate ligament (ACL) tear within the knee joint at MRI by using arthroscopy as the reference standard.Materials and methodsA fully automated deep learning-based diagnosis system was developed by using two deep convolutional neural networks (CNNs) to isolate the ACL on MR images followed by a classification CNN to detect structural abnormalities within the isolated ligament. With institutional review board approval, sagittal proton density-weighted and fat-suppressed T2-weighted fast spin-echo MR images of the knee in 175 subjects with a full-thickness ACL tear (98 male subjects and 77 female subjects; average age, 27.5 years) and 175 subjects with an intact ACL (100 male subjects and 75 female subjects; average age, 39.4 years) were retrospectively analyzed by using the deep learning approach. Sensitivity and specificity of the ACL tear detection system and five clinical radiologists for detecting an ACL tear were determined by using arthroscopic results as the reference standard. Receiver operating characteristic (ROC) analysis and two-sided exact binomial tests were used to further assess diagnostic performance.ResultsThe sensitivity and specificity of the ACL tear detection system at the optimal threshold were 0.96 and 0.96, respectively. In comparison, the sensitivity of the clinical radiologists ranged between 0.96 and 0.98, while the specificity ranged between 0.90 and 0.98. There was no statistically significant difference in diagnostic performance between the ACL tear detection system and clinical radiologists at P < .05. The area under the ROC curve for the ACL tear detection system was 0.98, indicating high overall diagnostic accuracy.ConclusionThere was no significant difference between the diagnostic performance of the ACL tear detection system and clinical radiologists for determining the presence or absence of an ACL tear at MRI.© RSNA, 2019Supplemental material is available for this article.

Dataset Information

Deep Learning for Classification and Selection of Cine CMR Images to Achieve Fully Automated Quality-Controlled CMR Analysis From Scanner to Report

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets