Deep Learning for Automated Measurement of Total Cardiac Volume for Heart Transplantation Size Matching.

Total Cardiac Volume (TCV)-based size matching using Computed Tomography (CT) is a novel technique to compare donor and recipient heart size in pediatric heart transplant that may increase overall utilization of available grafts. TCV requires manual segmentation, which limits its widespread use due to time and specialized software and training needed for segmentation. This study aims to determine the accuracy of a Deep Learning (DL) approach using 3-dimensional Convolutional Neural Networks (3D-CNN) to calculate TCV, with the clinical aim of enabling fast and accurate TCV use at all transplant centers. Ground truth TCV was segmented on CT scans of subjects aged 0-30 years, identified retrospectively. Ground truth segmentation masks were used to train and test a custom 3D-CNN model consisting of a DenseNet architecture in combination with residual blocks of ResNet architecture. The model was trained on a cohort of 270 subjects and a validation cohort of 44 subjects (36 normal, 8 heart disease retained for model testing). The average Dice similarity coefficient of the validation cohort was 0.94 ± 0.03 (range 0.84-0.97). The mean absolute percent error of TCV estimation was 5.5%. There is no significant association between model accuracy and subject age, weight, or height. DL-TCV was on average more accurate for normal hearts than those listed for transplant (mean absolute percent error 4.5 ± 3.9 vs. 10.5 ± 8.5, p = 0.08). A deep learning-based 3D-CNN model can provide accurate automatic measurement of TCV from CT images. This initial study is limited as a single-center study, though future multicenter studies may enable generalizable and more accurate TCV measurement by inclusion of more diverse cardiac pathology and increasing the training data.

Impact of Size Matching on Survival Post Heart Transplant in Infants: Estimated Total Cardiac Volume Ratio Outperforms Donor-Recipient Weight Ratio.

PURPOSE: Cardiac volume-based estimation offers an alternative to donor-recipient weight ratio (DRWR) in pediatric heart transplantation (HT), but has not been correlated to post-transplant outcomes We sought to determine whether estimated Total Cardiac Volume (eTCV) ratio is associated with HT survival in infants. METHODS: The UNOS database was used to identify infants (age:<1year) who received HT in 1987-2020. Donor and recipient eTCV were calculated from weight using previously published data. Patient cohort was divided according to the significant range of eTCV ratio; characteristics and survival were compared. RESULTS: 2845 infants were identified. Hazard ratio with cubic spline showed prognostic relationship of eTCV ratio and DRWR with the overall survival. The cut-point method determined an optimal eTCV ratio range predictive of infant survival was 1.05-1.85 whereas no range for DRWR was predictive. 75.6% patients had an optimal TCV ratio, while 18.1% were in the lower (LR) and 6.3% in the higher (HR) group. Kaplan-Meier analysis showed better survival for patients within the optimal vs LR (p=0.0017), and a similar significantly better survival when compared to HR (p=0.0053). The optimal eTCV ratio group (n=2151) had DRWR ranging from 1.09-5; 34.3% had DRWR 2-3, and 5.0% DRWR>3. CONCLUSION: Currently, an upper DRWR limit has not been established in infants. Therefore, determining the optimal eTCV range is important to identifying an upper limit that significantly predicts survival benefit. This finding suggests a potential increase in donor pool for infant recipients since over 40% of donors in the optimal eTCV range includes DRWR values>2 that are traditionally not considered for candidate listing.

Echocardiography Provides a Reliable Estimate of Total Cardiac Volume for Pediatric Heart Transplantation.

BACKGROUND: Donor-to-recipient size matching for heart transplantation typically involves comparing donor and recipient body weight; however, weight is not linearly related to cardiac size. Attention has shifted toward the use of computed tomography- (CT-) derived total cardiac volume (TCV), that is, CT-TCV, to compare donor and recipient heart organ size. At this time, TCV size matching is near impossible for most centers due to logistical limitations. To overcome this impediment, echocardiogram-derived TCV (ECHO-TCV) is an attractive, alternative option to estimate CT-TCV. The goal of this study is to test whether ECHO-TCV is an accurate and reliable surrogate for TCV measurement compared with the gold standard CT-TCV. METHODS: ECHO-TCV and CT-TCV were measured in a cohort spanning the neonatal to young adult age range with the intention to simulate the pediatric heart transplant donor pool. ECHO-TCV was measured using a modified Simpson's summation-of-discs method from the apical 4-chamber (A4C) view. The gold standard of CT-TCV was measured from CT scans using three-dimensional reconstruction software. The relationship between ECHO-TCV and CT-TCV was evaluated and compared with other anthropometric and image-based markers that may predict CT-TCV. Inter-rater reliability of ECHO-TCV was tested among 4 independent observers. Subanalyses were performed to identify imaging views and timing that enable greater accuracy of ECHO-TCV. RESULTS: Banked imaging data of 136 subjects with both echocardiogram and CT were identified. ECHO-TCV demonstrated a linear relationship to CT-TCV with a Pearson correlation coefficient of r = 0.96 (95% CI, 0.95-0.97; P < .0001) and mean absolute percent error of 8.6%. ECHO-TCV correlated most strongly with CT-TCV in the subset of subjects <4 years of age (n = 33; r = 0.98; 95% CI, 0.96-0.99; P < .0001). The single-score intraclass correlation coefficient across all 4 raters is 0.96 (interquartile range, 0.93-0.98). ECHO-TCV measured from a standard A4C view at end diastole with the atria in the plane of view had the strongest correlation to CT-TCV. CONCLUSIONS: ECHO-TCV by the A4C view was found to be both an accurate and reliable alternative measurement of CT-TCV and is derived from readily available donor ECHO images. The ECHO-TCV findings in this study make the ECHO method an attractive means of direct donor-to-recipient TCV size matching in pediatric heart transplantation.

Deep Learning for Automated Measurement of Total Cardiac Volume for Heart Transplantation Size Matching.

Background: Total Cardiac Volume (TCV) based size matching using Computed Tomography (CT) is a novel technique to compare donor and recipient heart size in pediatric heart transplant that may increase overall utilization of available grafts. TCV requires manual segmentation, which limits its widespread use due to time and specialized software and training needed for segmentation. Objective: This study aims to determine the accuracy of a Deep Learning (DL) approach using 3-dimensional Convolutional Neural Networks (3D-CNN) to calculate TCV, with the clinical aim of enabling fast and accurate TCV use at all transplant centers. Materials and Methods: Ground truth TCV was segmented on CT scans of subjects aged 0-30 years, identified retrospectively. Ground truth segmentation masks were used to train and test a custom 3D-CNN model consisting of a Dense-Net architecture in combination with residual blocks of ResNet architecture. Results: The model was trained on a cohort of 270 subjects and a validation cohort of 44 subjects (36 normal, 8 heart disease retained for model testing). The average Dice similarity coefficient of the validation cohort was 0.94 ± 0.03 (range 0.84-0.97). The mean absolute percent error of TCV estimation was 5.5%. There is no significant association between model accuracy and subject age, weight, or height. DL-TCV was on average more accurate for normal hearts than those listed for transplant (mean absolute percent error 4.5 ± 3.9 vs. 10.5 ± 8.5, p = 0.08). Conclusion: A deep learning based 3D-CNN model can provide accurate automatic measurement of TCV from CT images.

Comparing donor and recipient total cardiac volume predicts risk of short-term adverse outcomes following heart transplantation.

INTRODUCTION: In pediatric heart transplantation, donor: recipient weight ratio (DRWR) has long been the sole metric for size matching. Total cardiac volume (TCV)-based size matching has emerged as a novel method to precisely identify an upper limit of donor organ size of a heart transplant recipient while minimizing the risk of complications from oversizing. The clinical adoption of donor: recipient volume ratio (DRVR) to prevent short-term adverse outcomes of oversizing is unknown. The purpose of this single-center study is to determine the relationship of DRWR and DRVR to the risk of post-operative complications from allograft oversizing. METHODS: Recipient TCV was measured from imaging studies and donor TCV was calculated from published TCV prediction models. DRVR was defined as donor TCV divided by recipient TCV. The primary outcome was short-term post-transplant complications (SPTC), a composite outcome of delayed chest closure and prolonged intubation > 7 days. A multivariable logistic regression model of DRWR (cubic spline), DRVR (linear) and linear interaction between DRWR and DRVR was used to examine the probability of experiencing a SPTC over follow-up as a function of DRWR and DRVR. RESULTS: A total of 106 transplant patients' records were reviewed. Risk of the SPTC increased as DRVR increased. Both low and high DRWR was associated with the SPTC. A logistic regression model including DRWR and DRVR predicted SPTC with an AUROC curve of 0.74. [95% CI 0.62 0.85]. The predictive model identified a "low-risk zone" of donor-recipient size match between a weight ratio of 0.8 and 2.0 and a TCV ratio less than 1.0. CONCLUSION: DRVR in combination with DRWR predicts short-term post-transplant adverse events. Accepting donors with high DRWR may be safely performed when DRVR is considered.

Transplantation and Arch Repair in Fontan 3 Years After HeartMate 3: Technical Considerations.

We previously reported the first successful implantation of the HeartMate 3 (Abbott Laboratories) in a Fontan patient. We now report his successful transplantation after 1104 days of support, the longest reported bridge to transplant of a Fontan patient. We describe our operative technique complicated by not only the Fontan anatomy and ventricular assist device but also by a >10-cm ascending and aortic arch aneurysm. Additionally the posttransplant hemodynamics of this patient appeared to demonstrate that effective ventricular assist device support may induce reversal of chronic effects of the failing Fontan circulation, which in this case was the elimination of his aortopulmonary collateral burden.

Evidence supporting total cardiac volumes instead of weight for transplant size-matching.

Total cardiac volume (TCV)-based size matching for heart transplantation offers individualization in size matching that increases the number of suitable donors. Here we describe our clinical protocol for using TCV to determine an acceptable donor weight range for heart transplant candidates. We compare candidate imaging-derived TCV to a nomogram of subjects with normal TCV to determine a precise maximum donor weight at the time of listing. For nearly half of our transplant patients, we have increased weight range by an average of 70% with no oversizing related adverse events, such as delayed chest closure to avoid tamponade or bronchial compression. Widespread adoption of TCV-based size matching can lead to a more efficient heart allocation system by the data-driven bypass of poor size matches.

3D Holographic Virtual Surgical Planning for a Single Right Ventricle Fontan Patient Needing Heartmate III Placement.

A 15 year old female with hypoplastic left heart syndrome status post Norwood with Sano modification, bidirectional Glenn and extracardiac conduit Fontan developed severe right ventricular (RV) systolic dysfunction. Due to symptomatic heart failure, she underwent assessment for ventricular assist device (VAD) placement as a bridge-to-cardiac transplantation strategy. To evaluate her atypical anatomy, a chest computed tomography (CT) was uploaded into an EchoPixel True3D (Santa Clara, CA) view portal along with an accurately scaled 3D surface model of the HeartMate III (HM3) device. The surgeon then manipulated the position of the HM3 to evaluate multiple potential device positions in relation to anatomic features such as the intraventricular septum, tricuspid valve annulus, and RV muscle bundles. The patient was taken to the operating room and the HM3 device was placed just anterior to the RV apex as virtually planned. She had an uneventful postoperative course, underwent cardiac transplantation on postoperative day (POD) 63 and is doing well now 19 months post-transplantation.

Reducing the wait: TCV can expand the donor pool for heart transplant candidates.

A 16-year-old with new-onset dilated cardiomyopathy underwent VAD placement, later complicated by low flow from outflow graft kinking. To expedite heart transplantation, TCV was calculated and compared with 141 normal patients pinpointing the upper weight threshold. He was transplanted 2 days later within the expanded weight range with no post-transplant complications.

A novel method of donor‒recipient size matching in pediatric heart transplantation: A total cardiac volume‒predictive model.

BACKGROUND: The pediatric heart transplant community uses weight-based donor-to-recipient size matching almost exclusively, despite no evidence to validate weight as a reliable surrogate of cardiac size. Donor size mismatch is the second most common reason for the refusal of donor hearts in current practice (∼30% of all refusals). Whereas case-by-case segmentation of total cardiac volume (TCV) by computed tomography (CT) for direct virtual transplantation is an attractive option, it remains limited by the unavailability of donor chest CT. We sought to establish a predictive model for donor TCV on the basis of anthropomorphic and chest X-ray (CXR) cardiac measures. METHODS: Banked imaging studies from 141 subjects with normal CT chest angiograms were obtained and segmented using 3-dimensional modeling to derive TCV. CXR data were available for 62 of those subjects. A total of 3 predictive models of TCV were fit through multiple linear regression using the following variables: Model A (weight only); Model B (weight, height, sex, and age); Model C (weight, height, sex, age, and 1-view anteroposterior CXR maximal horizontal cardiac width). RESULTS: Model C provided the most accurate prediction of TCV (optimism corrected R2 = 0.99, testing set R2 = 0.98, mean absolute percentage error [MAPE] = 8.6%) and outperformed Model A (optimism corrected R2 = 0.94, testing set R2 = 0.94, MAPE = 16.1%) and Model B (optimism corrected R2 = 0.97, testing set R2 = 0.97, MAPE = 11.1%). CONCLUSIONS: TCV can be predicted accurately using readily available anthropometrics and a 1-view CXR from donor candidates. This simple and scalable method of TCV estimation may provide a reliable and consistent method to improve donor size matching.

Expanding the donor pool for congenital heart disease transplant candidates by implementing 3D imaging-derived total cardiac volumes.

BACKGROUND: Heart transplant waitlist mortality remains high in infants <1 year of age and among those with CHD. Currently, the median accepted donor-to-recipient weight percentage is approximately 130% of the recipient's weight. We hypothesized that patients with CHD may accept a larger organ using novel 3D-derived imaging data to estimate donor and recipient TCV. METHODS: A single-center, retrospective study was performed using CT data for 13 patients with CHD and 94 control patients. 3D visualization software was used to create digital 3D heart models that provide an estimate of TCV. In addition, echocardiograms obtained prior to cross-sectional imaging were reviewed for presence of ventricular chamber dilation. RESULTS: Sixty-two percent (8/13) of patients with CHD had 3D-derived TCV resulting in a weight that was >130% larger than their actual weight. This was seen in single-ventricle patients following Blalock-Taussig shunt and Fontan palliation, and patients with biventricular repair. Of those, 75% (6/8) had reported moderate-to-severe ventricular chamber dilation by echocardiogram or cardiac magnetic resonance imaging. CONCLUSIONS: In a large portion of patients with CHD, 3D-derived TCV place the recipient at a higher listing weight than their actual weight. We propose obtaining cross-sectional imaging to better assess TCV in a recipient, which may increase the donor range for CHD recipients and improve organ utilization in pediatrics.

First report of successfully palliating a hypoplastic left heart syndrome patient with anomalous left coronary artery from the pulmonary artery beyond Fontan.

We report a case of hypoplastic left heart syndrome with an anomalous left coronary artery from the pulmonary artery (ALCAPA) identified intraoperatively during the Stage-II palliation. Due to recurring ventricular fibrillation on sternotomy, a hybrid Stage-I palliation was performed. During comprehensive Stage-II, the ALCAPA was reimplanted in the neoaorta and measures, including a nontraditional Damus connection/arch reconstruction and classic bilateral Glenn procedures, were taken to avoid compression of the coronary artery. After a successful Fontan procedure, he continues to do well at 5 years old, becoming the first patient reported in the literature to survive all the three stages of single-ventricle palliation.

Time for evidence-based, standardized donor size matching for pediatric heart transplantation.

BACKGROUND: Accurately predicting cardiac size by other body parameters has long been problematic to determine whether a donor heart will serve a given waitlist candidate, yet hundreds of heart donors are turned down annually for size mismatch. OBJECTIVES: We sought to describe how donor body weight parameters are currently utilized in cardiac transplantation and its influence on waitlist outcomes. METHODS: From the United Network for Organ Sharing database, pediatric (age <18 years) heart transplant candidates were divided into lower quartile, interquartile, and upper quartile categories based on final maximum acceptable donor-candidate weight ratio (DCW), expressed as percentage. Baseline characteristics and waitlist outcomes, including monthly offers/candidate and survival were compared. RESULTS: Overall median DCW was 200% (range, 159%-241%). Patients with congenital heart disease had higher DCW than those with cardiomyopathy (223% vs 203%; P < .001). Number of monthly offers/candidate (5.0, 5.6, and 7.2, respectively; P < .001) increased with quartile of DCW. Posttransplant survival was similar amongst the groups (log-rank P > .05). Subgroup analysis of critically ill children showed a waitlist survival advantage in those listed with a DCW ≥200% (P < .001). CONCLUSIONS: Despite substantial practice variation in acceptable donor weight in pediatric heart transplantation, patients listed with variable DCW had similar posttransplant survival. However, in critically ill patients, higher DCW was associated with greater waitlist survival. Better understanding of the importance of donor weight could reduce practice variability and improve organ use and waitlist outcomes for pediatric cardiac transplant candidates.

Three-dimensional printing and virtual surgery for congenital heart procedural planning.

Complex unrepaired congenital heart disease requires extensive planning to determine the optimal procedural approach. Conventional noninvasive diagnostic imaging initially provides only two-dimensional (2D) representations of the complex, three-dimensional cardiovascular anatomy. With the expansion of 3D visualization techniques in imaging, a paradigm shift has occurred in complex congenital heart disease surgical planning using digital and 3D printed heart models. There has been early success in demonstrating the benefit of these models in interdisciplinary communication and education. The future goal of this work is to demonstrate a clinical outcome benefit using digital and 3D printed models to plan both surgical and catheterization-based interventional procedures. Ultimately, the hope is that advanced procedural planning with virtual surgery and 3D printing will enhance decision-making in complex congenital heart disease cases resulting in improved perioperative performance by reducing operative times, complications, and reoperations.