Co-attention spatial transformer network for unsupervised motion tracking and cardiac strain analysis in 3D echocardiography.

Myocardial ischemia/infarction causes wall-motion abnormalities in the left ventricle. Therefore, reliable motion estimation and strain analysis using 3D+time echocardiography for localization and characterization of myocardial injury is valuable for early detection and targeted interventions. Previous unsupervised cardiac motion tracking methods rely on heavily-weighted regularization functions to smooth out the noisy displacement fields in echocardiography. In this work, we present a Co-Attention Spatial Transformer Network (STN) for improved motion tracking and strain analysis in 3D echocardiography. Co-Attention STN aims to extract inter-frame dependent features between frames to improve the motion tracking in otherwise noisy 3D echocardiography images. We also propose a novel temporal constraint to further regularize the motion field to produce smooth and realistic cardiac displacement paths over time without prior assumptions on cardiac motion. Our experimental results on both synthetic and in vivo 3D echocardiography datasets demonstrate that our Co-Attention STN provides superior performance compared to existing methods. Strain analysis from Co-Attention STNs also correspond well with the matched SPECT perfusion maps, demonstrating the clinical utility for using 3D echocardiography for infarct localization.

The incidence and mortality of acute thoracic aortic dissection: results from a whole nation study.

OBJECTIVES: Acute thoracic aortic dissection (ATAD) is a devastating condition associated with a high mortality rate. Recent reports suggest that its incidence is rising. Utilizing nationwide data comprising the whole Icelandic population, we aimed to determine the incidence, mortality rate and time-dependent mortality risk of ATAD. METHODS: Data were retrospectively collected using centralized hospital discharge registries, autopsy records and Cause of Death Registry in Iceland from 1992 to 2013. RESULTS: Age- and gender-adjusted incidence of ATAD was 2.53/100 000/year, and no significant change in incidence was observed during the study period. The mean age was 66.9 ± 13.6 years and 66.0% (101/153) were Stanford type A. Of the whole group, 17.6% (27/153) died prior to hospital arrival, whereas the risk of death for patients who arrived alive to a hospital was 21.4% (27/126) within 24 h and 45.2% (57/126) at 30 days. During the course of the study, patients with type A dissection were more likely to undergo an operation and the management of type B dissection changed from open to endovascular repair. The 30-day mortality rate declined every year and the 5-year survival rate improved in the last third of the study. CONCLUSIONS: The incidence of ATAD was 2.53/100 000/year and remained constant throughout the study, contradicting recent perceptions of a rising incidence. ATAD, type A in particular, remains a highly lethal condition: Over half of all patients die within 30 days of the index event. A reduced 30-day mortality rate and an increased long-term survival rate indicate improved overall outcomes in patients with this complex condition.