Mitral Valve Segmentation and Tracking from Transthoracic Echocardiography Using Deep Learning.

OBJECTIVE: Valvular heart diseases (VHDs) pose a significant public health burden, and deciding the best treatment strategy necessitates accurate assessment of heart valve function. Transthoracic echocardiography (TTE) is the key modality to evaluate VHDs, but the lack of standardized quantitative measurements leads to subjective and time-consuming assessments. We aimed to use deep learning to automate the extraction of mitral valve (MV) leaflets and annular hinge points from echocardiograms of the MV, improving standardization and reducing workload in quantitative assessment of MV disease. METHODS: We annotated the MV leaflets and annulus points in 2931 images from 127 patients. We propose an approach for segmenting the annotated features using Attention UNet with deep supervision and weight scheduling of the attention coefficients to enforce saliency surrounding the MV. The derived segmentation masks were used to extract quantitative biomarkers for specific MV leaflet scallops throughout the heart cycle. RESULTS: Evaluation performance was summarized using a Dice score of 0.63 ± 0.14, annulus error of 3.64 ± 2.53 and leaflet angle error of 8.7 ± 8.3°. Leveraging Attention UNet with deep supervision robustness of clinically relevant metrics was improved compared with UNet, reducing standard deviations by 2.7° (angle error) and 0.73 mm (annulus error). We correctly identified cases of MV prolapse, cases of stenosis and healthy references from a clinical material using the derived biomarkers. CONCLUSION: Robust deep learning segmentation and tracking of MV morphology and motion is possible by leveraging attention gates and deep supervision, and holds promise for enhancing VHD diagnosis and treatment monitoring.

The Zanzibar Heart Survey: A special report from a humanitarian cardiology program at the Mnazi Mmoja referral hospital, Zanzibar, United Republic of Tanzania by Haukeland University Hospital in Bergen, Norway.

A Norwegian cardiology delegation comprised of Cardiologists and Researchers travelled voluntarily to Zanzibar to undertake 4 humanitarian missions in 2022. The principal aims of this were to: 1) Train local cardiologists in transthoracic echocardiography and perform echocardiographic screening in patients with cardiac symptoms who had not undergone any prior cardiac imaging, 2) Conduct a hypertension survey to improve awareness, treatment and control of hypertension and 3) Implant permanent pacemakers in patients with significant bradyarrhythmias for the first time in the Archipelago. The current report details our experience at the Mnazi Mmoja Referral Hospital. We describe the challenges in managing common cardiovascular conditions such as hypertension, cardiomyopathies, coronary artery disease and rhythm disturbances. Furthermore, we propose that improvement to care may be achieved by implementing systematic access to echocardiography and hypertension services to the island. In our survey, we found that hypertension and hypertension-mediated target organ damage were highly prevalent and hypertension was poorly controlled in Zanzibar. The common reasons for poor BP control were reported to be partly the issue of cost, affordability and availability of antihypertensive medications, and partly due to lack of awareness. Women were on average 10 years younger than men and were more likely to be obese, while men had higher burden of established cardiovascular disease (CAD, stroke, chronic kidney disease, and atrial fibrillation). Humanitarian healthcare missions by Western countries provide invaluable contributions to the healthcare of patients elsewhere in the world. Although their impact can be felt immediately, there is the propensity for these benefits to dissipate rapidly following the departure of visiting delegations. There is a need for more sustainable solutions whereby local healthcare systems are empowered to develop their own local capacities and initiate a system whereby local training can occur, the utilisation of facilities can be maximised and new skills can be transferred to health care practitioners to ensure universal access to diagnostics and treatments of cardiovascular diseases in Zanzibar. Our report indicates that measurable changes can be achieved in a relatively short time frame. These may in turn translate to improvements in access and quality of healthcare to the local population.

Short-term outcome after open-heart surgery for severe chronic rheumatic heart disease in a low-income country, with comparison with an historical control group: an observational study.

OBJECTIVES: Rheumatic heart disease (RHD) is a major burden in low-income and middle-income countries (LMICs). Cardiac surgery is the only curative treatment. Little is known about patients with severe chronic RHD operated in LMICs, and challenges regarding postoperative follow-up are an important issue. At Tikur Anbessa Specialised Hospital, Addis Ababa, Ethiopia, we aimed to evaluate the course and 12-month outcome of patients with severe chronic RHD who received open-heart surgery, as compared with the natural course of controls waiting for surgery and undergoing only medical treatment. METHODS: Clinical data and outcome measures were registered in 46 patients operated during five missions from March 2016 to November 2019, and compared with the first-year course in a cohort of 49 controls from the same hospital's waiting list for surgery. Adverse events were death or complications such as stroke, other thromboembolic events, bleeding, hospitalisation for heart failure and infectious endocarditis. RESULTS: Survival at 12 months was 89% and survival free from complications was 80% in the surgical group. Despite undergoing open-heart surgery, with its inherent risks, outcome measures of the surgical group were non-inferior to the natural course of the control group in the first year after inclusion on the waiting list (p≥0.45). All except six surgical patients were in New York Heart Association class I after 12 months and 84% had resumed working. CONCLUSIONS: Cardiac surgery for severe chronic RHD is feasible in LMICs if the service is structured and planned. Rates of survival and survival free from complications were similar to those of controls at 12 months. Functional level and resumption of work were high in the surgical group. Whether the patients who underwent cardiac surgery will have better long-term prognosis, in line with what is known in high-income countries, needs to be evaluated in future studies.