# 4D CNN for semantic segmentation of cardiac volumetric sequences

## TL;DR

This paper introduces a 4D CNN for cardiac CT segmentation that effectively utilizes sparse annotations and temporal information to produce consistent segmentations across sequences.

## Contribution

The paper presents a novel 4D CNN architecture with a sparse loss function that leverages unlabeled data for cardiac volumetric sequence segmentation.

## Key findings

- The 4D CNN achieves accurate, temporally consistent segmentation results.
- It outperforms traditional 3D segmentation methods on cardiac 4D CCTA data.
- The approach effectively uses sparse annotations to train the model.

## Abstract

We propose a 4D convolutional neural network (CNN) for the segmentation of retrospective ECG-gated cardiac CT, a series of single-channel volumetric data over time. While only a small subset of volumes in the temporal sequence is annotated, we define a sparse loss function on available labels to allow the network to leverage unlabeled images during training and generate a fully segmented sequence. We investigate the accuracy of the proposed 4D network to predict temporally consistent segmentations and compare with traditional 3D segmentation approaches. We demonstrate the feasibility of the 4D CNN and establish its performance on cardiac 4D CCTA.