CMMCSegNet: Cross-Modality Multicascade Indirect LGE Segmentation on Multimodal Cardiac MR

Since Late-Gadolinium Enhancement (LGE) of cardiac magnetic resonance (CMR) visualizes myocardial infarction, and the balanced-Steady State Free Precession (bSSFP) cine sequence can capture cardiac motions and present clear boundaries; multimodal CMR segmentation has played an important role in the assessment of myocardial viability and clinical diagnosis, while automatic and accurate CMR segmentation still remains challenging due to a very small amount of labeled LGE data and the relatively low contrasts of LGE. The main purpose of our work is to learn the real/fake bSSFP modality with ground truths to indirectly segment the LGE modality of cardiac MR by using a proposed cross-modality multicascade framework: cross-modality translation network and automatic segmentation network, respectively. In the segmentation stage, a novel multicascade pix2pix network is designed to segment the fake bSSFP sequence obtained from a cross-modality translation network. Moreover, we propose perceptual loss measuring features between ground truth and prediction, which are extracted from the pretrained vgg network in the segmentation stage. We evaluate the performance of the proposed method on the multimodal CMR dataset and verify its superiority over other state-of-the-art approaches under different network structures and different types of adversarial losses in terms of dice accuracy in testing. Therefore, the proposed network is promising for Indirect Cardiac LGE Segmentation in clinical applications.

Feasibility of non-gated dynamic fetal cardiac MRI for identification of fetal cardiovascular anatomy

Funding Acknowledgements Type of funding sources: None. Purpose We sought to retrospectively evaluate the feasibility of identifying the fetal cardiac and thoracic vascular structures with non-gated dynamic balanced steady-state free precession MRI sequences. Methods We retrospectively assessed the visibility of cardiovascular anatomy in 66 fetuses without suspicion of congenital heart defect (mean gestational age 27+/- 4, range 21-38 weeks). Non-gated dynamic balanced steady-state free precession (SSFP) sequences were acquired in three planes (axial, coronal and sagittal) of the fetal thorax (slice thickness 4-5mm, FOV 400, FA 60°, matrix 256x256). The images were analysed following a segmental approach in consensus reading by an experienced paediatric cardiologist and radiologist. An imaging score was defined by giving one point to each visualized structure. Basic diagnostic structures included the atria, ventricles, systemic veins, right and left ventricular outflow tracts (RVOT/LVOT), aortic arch, descending aorta (DAO), ductus arteriosus and thymus (12 points); advanced diagnostic features included the atrioventricular (AV) valves, pulmonary arteries and veins, supraaortic arteries and trachea, yielding a maximum score of 21 points. Image quality was rated from 0 (poor) to 2 (good). The influence of gestational age (GA), field strength, placenta position, and maternal panniculus on image quality and imaging score were tested. Results 34 scans were performed at 1.5 T, 32 at 3 T. Heart position, atria and ventricles could be seen in all 66 fetuses. Basic diagnosis (>12 points) was achieved in 60 (90%) cases, with visualization of the IVC and SVC in 65 (98%) and 63 (95%), RVOT in 62 (94%), LVOT in 61 (92%), aortic arch in 60 (91%), DAO in 64 (97%), ductus arteriosus in 59 (89%) and thymus in 50 (76%) fetuses. The AV valves were recognised in 55 (83%), the pulmonary arteries in 35 (53%), at least one pulmonary vein in 46 (70%), the supraaortic arteries in 42 (64%), and the trachea in 59 (89%) fetuses. The mean imaging score was 16.8 +/- 3.7. Maternal panniculus (r -0.3; p 0.01) and gestational age (r 0.6; p < 0.001) correlated with imaging score. Field strength influenced image quality, with 1.5 T being better than 3T images (p 0.04), but not the total imaging score. Imaging score or quality were independent from placenta position. Conclusions Fetal heart MRI with a non-gated SSFP sequence in multiple planes enables recognition of basic cardiovascular anatomy. Advanced diagnostics may be limited by thick maternal panniculus, lower GA and higher field strength.

Retrospective assessment of at-risk myocardium in reperfused acute myocardial infarction patients using contrast‐enhanced balanced steady‐state free‐precession cardiovascular magnetic resonance at 3T with SPECT validation

Background Contrast-enhanced (CE) steady-state free precession (SSFP) CMR at 1.5T has been shown to be a valuable alternative to T2-based methods for the detection and quantifications of area-at-risk (AAR) in acute myocardial infarction (AMI) patients. However, CE-SSFP’s capacity for assessment of AAR at 3T has not been investigated. We examined the clinical utility of CE-SSFP and T2-STIR for the retrospective assessment of AAR at 3T with single-photon-emission-computed tomography (SPECT) validation. Materials and methods A total of 60 AMI patients (ST-elevation AMI, n = 44; non-ST-elevation AMI, n = 16) were recruited into the CMR study between 3 and 7 days post revascularization. All patients underwent T2-STIR, CE-bSSFP and late-gadolinium-enhancement CMR. For validation, SPECT images were acquired in a subgroup of patients (n = 30). Results In 53 of 60 patients (88 %), T2-STIR was of diagnostic quality compared with 54 of 60 (90 %) with CE-SSFP. In a head-to-head per-slice comparison (n = 365), there was no difference in AAR quantified using T2-STIR and CE-SSFP (R2 = 0.92, p < 0.001; bias:-0.4 ± 0.8 cm2, p = 0.46). On a per-patient basis, there was good agreement between CE-SSFP (n = 29) and SPECT (R2 = 0.86, p < 0.001; bias: − 1.3 ± 7.8 %LV, p = 0.39) for AAR determination. T2-STIR also showed good agreement with SPECT for AAR measurement (R2 = 0.81, p < 0.001, bias: 0.5 ± 11.1 %LV, p = 0.81). There was also a strong agreement between CE-SSFP and T2-STIR with respect to the assessment of AAR on per-patient analysis (R2 = 0.84, p < 0.001, bias: − 2.1 ± 10.1 %LV, p = 0.31). Conclusions At 3T, both CE-SSFP and T2-STIR can retrospectively quantify the at-risk myocardium with high accuracy.

Lymphatic pathway evaluation in congenital heart disease using 3D whole-heart balanced steady state free precession and T2-weighted cardiovascular magnetic resonance

Background Due to passive blood flow in palliated single ventricle, central venous pressure increases chronically, ultimately impeding lymphatic drainage. Early visualization and treatment of these malformations is essential to reduce morbidity and mortality. Cardiovascular magnetic resonance (CMR) T2-weighted lymphangiography (T2w) is used for lymphatic assessment, but its low signal-to-noise ratio may result in incomplete visualization of thoracic duct pathway. 3D-balanced steady state free precession (3D-bSSFP) is commonly used to assess congenital cardiac disease anatomy. Here, we aimed to improve diagnostic imaging of thoracic duct pathway using 3D-bSSFP. Methods Patients underwent CMR during single ventricle or central lymphatic system assessment using T2w and 3D-bSSFP. T2w parameters included 3D-turbo spin echo (TSE), TE/TR = 600/2500 ms, resolution = 1 × 1 × 1.8 mm, respiratory triggering with bellows. 3D-bSSFP parameters included electrocardiogram triggering and diaphragm navigator, 1.6 mm isotropic resolution, TE/TR = 1.8/3.6 ms. Thoracic duct was identified independently in T2w and 3D-bSSFP images, tracked completely from cisterna chyli to its drainage site, and classified based on severity of lymphatic abnormalities. Results Forty-eight patients underwent CMR, 46 of whom were included in the study. Forty-five had congenital heart disease with single ventricle physiology. Median age at CMR was 4.3 year (range 0.9–35.1 year, IQR 2.4 year), and median weight was 14.4 kg (range, 7.9–112.9 kg, IQR 5.2 kg). Single ventricle with right dominant ventricle was noted in 31 patients. Thirty-eight patients (84%) were status post bidirectional Glenn and 7 (16%) were status post Fontan anastomosis. Thoracic duct visualization was achieved in 45 patients by T2w and 3D-bSSFP. Complete tracking to drainage site was attained in 11 patients (24%) by T2w vs 25 (54%) by 3D-bSSFP and in 28 (61%) by both. Classification of lymphatics was performed in 31 patients. Conclusion Thoracic duct pathway can be visualized by 3D-bSSFP combined with T2w lymphangiography. Cardiac triggering and respiratory navigation likely help retain lymphatic signal in the retrocardiac area by 3D-bSSFP. Visualizing lymphatic system leaks is challenging on 3D-bSSFP images alone, but 3D-bSSFP offers good visualization of duct anatomy and landmark structures to help plan interventions. Together, these sequences can define abnormal lymphatic pathway following single ventricle palliative surgery, thus guiding lymphatic interventional procedures.