Background: Patients with congenital heart disease (CHD) are at risk for the development of low cardiac output and other physiologic derangements, which could be detected early through continuous stroke volume (SV) measurement. Unfortunately, existing SV measurement methods are limited in the clinic because of their invasiveness (eg, thermodilution), location (eg, cardiac magnetic resonance imaging), or unreliability (eg, bioimpedance). Multimodal wearable sensing, leveraging the seismocardiogram, a sternal vibration signal associated with cardiomechanical activity, offers a means to monitoring SV conveniently, affordably, and continuously. However, it has not been evaluated in a population with significant anatomical and physiological differences (ie, children with CHD) or compared against a true gold standard (ie, cardiac magnetic resonance). Here, we present the feasibility of wearable estimation of SV in a diverse CHD population (N=45 patients). Methods and Results: We used our chest‐worn wearable biosensor to measure baseline ECG and seismocardiogram signals from patients with CHD before and after their routine cardiovascular magnetic resonance imaging, and derived features from the measured signals, predominantly systolic time intervals, to estimate SV using ridge regression. Wearable signal features achieved acceptable SV estimation (28% error with respect to cardiovascular magnetic resonance imaging) in a held‐out test set, per cardiac output measurement guidelines, with a root‐mean‐square error of 11.48 mL and R ² of 0.76. Additionally, we observed that using a combination of electrical and cardiomechanical features surpassed the performance of either modality alone. Conclusions: A convenient wearable biosensor that estimates SV enables remote monitoring of cardiac function and may potentially help identify decompensation in patients with CHD.

Today’s standard of care, in the congenital heart disease (CHD) population, involves performing cardiac catheterization under x-ray fluoroscopy and cardiac magnetic resonance (CMR) imaging separately. The unique ability of CMR to provide real-time functional imaging in multiple views without ionizing radiation exposure has the potential to be a powerful tool for diagnostic and interventional procedures. Limiting fluoroscopic radiation exposure remains a challenge for pediatric interventional cardiologists. This pilot study’s objective is to establish feasibility of right (RHC) and left heart catheterization (LHC) during invasive CMR (iCMR) procedures at our institution in the CHD population. Furthermore, we aim to improve simultaneous visualization of the catheter balloon tip, MR-conditional guidewire, and cardiac/vessel anatomy during iCMR procedures. Subjects with CHD were enrolled in a pilot study for iCMR procedures at 1.5 T with an MR-conditional guidewire. The CMR area is located adjacent to a standard catheterization laboratory. Using the interactive scanning mode for real-time control of the imaging location, a dilute gadolinium-filled balloon-tip catheter was used in combination with an MR-conditional guidewire to obtain cardiac saturations and hemodynamics. A recently developed catheter tracking technique using a real-time single-shot balanced steady-state free precession (bSSFP), flip angle (FA) 35–45°, echo time (TE) 1.3 ms, repetition time (TR) 2.7 ms, 40° partial saturation (pSAT) pre-pulse was used to visualize the gadolinium-filled balloon, MR-conditional guidewire, and cardiac structures simultaneously. MR-conditional guidewire visualization was enabled due to susceptibility artifact created by distal markers. Pre-clinical phantom testing was performed to determine the optimum imaging FA-pSAT combination. The iCMR procedure was successfully performed to completion in 31/34 (91%) subjects between August 1st, 2017 to December 13th, 2018. Median age and weight were 7.7 years and 25.2 kg (range: 3 months – 33 years and 8 – 80 kg). Twenty-one subjects had single ventricle (SV) anatomy: one subject was referred for pre-Glenn evaluation, 11 were pre-Fontan evaluations and 9 post-Fontan evaluations for protein losing enteropathy (PLE) and/or cyanosis. Thirteen subjects had bi-ventricular (BiV) anatomy, 4 were referred for coarctation of the aorta (CoA) evaluations, 3 underwent vaso-reactivity testing with inhaled nitric oxide, 3 investigated RV volume dimensions, two underwent branch PA stenosis evaluation, and the remaining subject was status post heart transplant. No catheter related complications were encountered. Average time taken for first pass RHC, LHC/aortic pull back, and to cross the Fontan fenestration was 5.2, 3.0, and 6.5 min, respectively. Total success rate to obtain required data points to complete Fick principle calculations for all patients was 331/337 (98%). Subjects were transferred to the x-ray fluoroscopy lab if further intervention was required including Fontan fenestration device closure, balloon angioplasty of pulmonary arteries/conduits, CoA stenting, and/or coiling of aortopulmonary (AP) collaterals. Starting with subject #10, an MR-conditional guidewire was used in all subsequent subjects (15 SV and 10 BiV) with a success rate of 96% (24/25). Real-time CMR-guided RHC (25/25 subjects, 100%), retrograde and prograde LHC/aortic pull back (24/25 subjects, 96%), CoA crossing (3/4 subjects, 75%) and Fontan fenestration test occlusion (2/3 subjects, 67%) were successfully performed in the majority of subjects when an MR-conditional guidewire was utilized. Feasibility for detailed diagnostic RHC, LHC, and Fontan fenestration test occlusion iCMR procedures in SV and BiV pediatric subjects with complex CHD is demonstrated with the aid of an MR-conditional guidewire. A novel real-time pSAT GRE sequence with optimized FA-pSAT angle has facilitated simultaneous visualization of the catheter balloon tip, MR-conditional guidewire, and cardiac/vessel anatomy during iCMR procedures.

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.