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.

使用计算机断层扫描 (CT) 进行基于心脏总量 (TCV) 的尺寸匹配是一种比较儿科心脏移植中供体和受体心脏尺寸的新技术，可能会提高可用移植物的总体利用率。 TCV 需要手动分割，由于分割所需的时间、专用软件和培训，限制了其广泛使用。本研究旨在确定使用 3 维卷积神经网络 (3D-CNN) 计算 TCV 的深度学习 (DL) 方法的准确性，其临床目标是在所有移植中心实现快速、准确的 TCV 使用。根据 0-30 岁受试者的 CT 扫描对真实 TCV 进行分段，并进行回顾性识别。 Ground Truth 分割掩模用于训练和测试由 DenseNet 架构与 ResNet 架构的残差块组合组成的自定义 3D-CNN 模型。该模型在 270 名受试者的队列和 44 名受试者的验证队列中进行了训练（36 名正常受试者，8 名心脏病受试者保留用于模型测试）。验证队列的平均 Dice 相似系数为 0.94 ± 0.03（范围 0.84–0.97）。 TCV 估计的平均绝对百分比误差为 5.5%。模型准确性与受试者年龄、体重或身高之间没有显着关联。平均而言，正常心脏的 DL-TCV 比移植心脏的准确度更高（平均绝对百分比误差 4.5 ± 3.9 与 10.5 ± 8.5，p  = 0.08）。基于深度学习的 3D-CNN 模型可以从 CT 图像中准确自动测量 TCV。这项初步研究仅限于单中心研究，但未来的多中心研究可能通过纳入更多样化的心脏病理学和增加训练数据来实现通用且更准确的 TCV 测量。