Vision Transformers increase efficiency of 3D cardiac CT multi-label segmentation

Accurate segmentation of the heart is essential for personalized blood flow simulations and surgical intervention planning. Segmentations need to be accurate in every spatial dimension, which is not ensured by segmenting data slice by slice. Two cardiac computed tomography (CT) datasets consisting of 760 volumes across the whole cardiac cycle from 39 patients, and of 60 volumes from 60 patients respectively were used to train networks to simultaneously segment multiple regions representing the whole heart in 3D. The segmented regions included the left and right atrium and ventricle, left ventricular myocardium, ascending aorta, pulmonary arteries, pulmonary veins, and left atrial appendage. The widely used 3D U-Net and the UNETR architecture were compared to our proposed method optimized for large volumetric inputs. The proposed network architecture, termed Transformer Residual U-Net (TRUNet), maintains the cascade downsampling encoder, cascade upsampling decoder and skip connections from U-Net, while incorporating a Vision Transformer (ViT) block in the encoder alongside a modified ResNet50 block. TRUNet reached higher segmentation performance for all structures within approximately half the training time needed for 3D U-Net and UNETR. The proposed method achieved more precise vessel boundary segmentations and better captured the heart's overall anatomical structure compared to the other methods. The fast training time and accurate delineation of adjacent structures makes TRUNet a promising candidate for medical image segmentation tasks. The code for TRUNet is available at github.com/ljollans/TRUNet.