Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model.

Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an initial interpretation. However, such a process does not always provide straightforward information to make a complete interpretation. The segmentation process only identifies the region of cardiac septal abnormality, whereas complete interpretation should determine based on the position of defect. In this study, we proposed a stacked residual-dense network model to segment the entire region of cardiac and classifying their defect positions to generate automatic echocardiographic interpretation. We proposed the generalization model with incorporated two modalities: prenatal and postnatal echocardiography. To further evaluate the effectiveness of our model, its performance was verified by five cardiologists. We develop a pipeline process using 1345 echocardiograms for training data and 181 echocardiograms for unseen data from prospective patients acquired during standard clinical practice at Muhammad Hoesin General Hospital in Indonesia. As a result, the proposed model produced of 58.17% intersection over union (IoU), 75.75% dice similarity coefficient (DSC), and 76.36% mean average precision (mAP) for the validation data. Using unseen data, we achieved 42.39% IoU, 55.72% DSC, and 51.04% mAP. Further, the classification of defect positions using unseen data had approximately 92.27% accuracy, 94.33% specificity, and 92.05% sensitivity. Finally, our proposed model is validated with human expert with varying Kappa value. On average, these results hold promise of increasing suitability in clinical practice as a supporting diagnostic tool for establishing the diagnosis.

Transcatheter Closure of Perimembranous Ventricular Septal Defect Using the Lifetech Konar-Multi Functional Occluder: Early to Midterm Results of the Indonesian Multicenter Study.

Background: The alternative device to close perimembranous ventricular septal defect (pmVSD) has been searched for better result, less complications and applicable for infants. However, the ideal device is still unavailable. We aimed to evaluate the effectiveness and outcome of transcatheter pmVSD closure using the KONAR-multi functional occluder (MFO). Methods: Clinical, procedural, follow-up data of pmVSD patients with symptom of heart failure or evidence of significant left to right shunt, growth failure, recurrent respiratory tract infection, and history of endocarditis who underwent transcatheter closure using the MFO were prospectively evaluated. Results: Between January 2016 and December 2017, there were complete records of 132 pmVSD children closed using MFO from eleven centers in Indonesia. The median of age was 4.5 (0.3-17.4) years; weight 14.8 (3.5-57) kg, defect size at the smallest part 3.4 (1.0-8.1) mm, flow ratio 1.6 (1.3-4.9), mean pulmonary artery pressure 18 (7-79) mmHg, fluoroscopy time 18 (3.8-91) and procedural time 75 (26-290) minutes. A retrograde approach was done in 41 (31%) patients. Procedures succeeded in first attempt in 126 (95.4%), failed in three and migration in three patients. Six of eight infants with congestive heart failure were closed successfully. Of 126 patients with successful VSD closure, 12 months follow-up were completed in all patients. The rate of complete occlusion at 1 month, 3 months, 6 months and 12 months after intervention were 95.2%, 97.6%, 99.2%, and 99.2%, respectively. New-onset aortic regurgitation and moderate tricuspid regurgitation developed only in five and three patients. Neither complete atrioventricular block, nor other complications occurred. Conclusion: Transcatheter closure of pmVSD using the MFO is safe, effective, and feasible in infants and children.