Automated left atrial time-resolved segmentation in MRI long-axis cine images using active contours

Abstract

Background Segmentation of the left atrium (LA) is required to evaluate atrial size and function, which are important imaging biomarkers for a wide range of cardiovascular conditions, such as atrial fibrillation, stroke, and diastolic dysfunction. LA segmentations are currently being performed manually, which is time-consuming and observer-dependent. Methods This study presents an automated image processing algorithm for time-resolved LA segmentation in cardiac magnetic resonance imaging (MRI) long-axis cine images of the 2-chamber (2ch) and 4-chamber (4ch) views using active contours. The proposed algorithm combines mitral valve tracking, automated threshold calculation, edge detection on a radially resampled image, edge tracking based on Dijkstra’s algorithm, and post-processing involving smoothing and interpolation. The algorithm was evaluated in 37 patients diagnosed mainly with paroxysmal atrial fibrillation. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC) and Hausdorff distance (HD), with manual segmentations in all time frames as the reference standard. For inter-observer variability analysis, a second observer performed manual segmentations at end-diastole and end-systole on all subjects. Results The proposed automated method achieved high performance in segmenting the LA in long-axis cine sequences, with a DSC of 0.96 for 2ch and 0.95 for 4ch, and an HD of 5.5 mm for 2ch and 6.4 mm for 4ch. The manual inter-observer variability analysis had an average DSC of 0.95 and an average HD of 4.9 mm. Conclusion The proposed automated method achieved performance on par with human experts analyzing MRI images for evaluation of atrial size and function.

TVnet: Automated Time-Resolved Tracking of the Tricuspid Valve Plane in MRI Long-Axis Cine Images with a Dual-Stage Deep Learning Pipeline

“…Four chamber data had an average spatial resolution of 2 × 2 mm 2 , slice thickness of 8 mm, and mostly 30 temporal frames per cardiac cycle were reconstructed. The final dataset comprised a total of 4170 images (140 sets of time-resolved images) analyzed in previous studies [12][13][14].…”

Semi-Supervised Unpaired Medical Image Segmentation Through Task-Affinity Consistency

“…As each specific type of region largely shares the same key information across different images (e.g. the atrium always has a thicker wall, a similar texture and a variable shape across subjects [9]), we hypothesize class-specific information should be similar across the regions of the same interest in the feature maps regardless whether it is labelled or not. Therefore, to make use of this class-specific information, we design a module called task-affinity module (as shown in Fig.…”

Automated Measurements of Mitral and Tricuspid Annular Dimensions in Cardiovascular Magnetic Resonance

“…The automated diameters were evaluated in 55 subjects [8,9,10] with varied cardiovascular diseases, and compared against manual diameters annotated in Segment [11] by an observer with 5 years of CMR experience. Test sets comprised of 32 subjects (13 females, 57 ± 15 years old) with 943 2Ch and 943 4Ch images, and 28 subjects (12 females, 54 ± 15 years old) with 840 4Ch images, for MVnet Yale and TVnet, respectively.…”