Angelman and Prader-Willi Syndromes: Sister Imprinting Disorders With High Complication Rates Following Spinal Deformity Surgery.

We sought to examine the modern surgical treatment of spinal deformity associated with sister imprinting disorders, Prader-Willi syndrome (PWS) and Angelman syndrome (AS), with emphasis on the specific complications encountered in these patient populations. Fifteen patients with PWS and 5 patients with AS who underwent surgical intervention for spinal deformity between 2000 and 2018 were identified. Postoperative complications were classified using the modified Clavien-Dindo-Sink (CDS) system and further categorized into specific subtypes including excessive drainage, dehiscence, implant failure, infection, and delayed wound healing. Perioperative and final follow-up radiographic data were analyzed. Mean age at surgery was 12.9 years (range, 4-21 years) with mean follow-up of 46.1 months (range, 1-145 months). There were postoperative complications in 17 patients (85%). Ten major complications (CDS ≥ 3) occurred in 9 patients (45%). These included 5 infections requiring reoperation, 1 seroma requiring drainage, 2 severe cervical-thoracic deformities requiring reoperation, 1 implant failure requiring reoperation, and 1 death secondary to fungal sepsis and thromboembolic disease. Eight additional patients (40%) had minor complications (CDS 1 or 2). Eight intraoperative complications occurred in 5 patients (25%), including loss of neuromonitoring signals and cerebrospinal fluid leaks. Surgical intervention for scoliosis in PWS and AS continues to have high complication rates secondary to medical and behavioral comorbidities found in these patient populations. The exact etiology of the high complication rates encountered cannot be definitively stated, but both syndromes frequently present with a number of unique features that may predispose patients to develop surgical complications. [Orthopedics. 2023;46(4):e223-e229.].

Retraining Convolutional Neural Networks for Specialized Cardiovascular Imaging Tasks: Lessons from Tetralogy of Fallot.

Ventricular contouring of cardiac magnetic resonance imaging is the gold standard for volumetric analysis for repaired tetralogy of Fallot (rTOF), but can be time-consuming and subject to variability. A convolutional neural network (CNN) ventricular contouring algorithm was developed to generate contours for mostly structural normal hearts. We aimed to improve this algorithm for use in rTOF and propose a more comprehensive method of evaluating algorithm performance. We evaluated the performance of a ventricular contouring CNN, that was trained on mostly structurally normal hearts, on rTOF patients. We then created an updated CNN by adding rTOF training cases and evaluated the new algorithm's performance generating contours for both the left and right ventricles (LV and RV) on new testing data. Algorithm performance was evaluated with spatial metrics (Dice Similarity Coefficient (DSC), Hausdorff distance, and average Hausdorff distance) and volumetric comparisons (e.g., differences in RV volumes). The original Mostly Structurally Normal (MSN) algorithm was better at contouring the LV than the RV in patients with rTOF. After retraining the algorithm, the new MSN + rTOF algorithm showed improvements for LV epicardial and RV endocardial contours on testing data to which it was naïve (N = 30; e.g., DSC 0.883 vs. 0.905 for LV epicardium at end diastole, p < 0.0001) and improvements in RV end-diastolic volumetrics (median %error 8.1 vs 11.4, p = 0.0022). Even with a small number of cases, CNN-based contouring for rTOF can be improved. This work should be extended to other forms of congenital heart disease with more extreme structural abnormalities. Aspects of this work have already been implemented in clinical practice, representing rapid clinical translation. The combined use of both spatial and volumetric comparisons yielded insights into algorithm errors.