Background

Four-dimensional computed tomography (4DCT) is an essential tool in radiation therapy. However, the 4D acquisition process may cause motion artifacts which can obscure anatomy and distort functional measurements from CT scans.

Purpose

We describe a deep learning algorithm to identify the location of artifacts within 4DCT images. Our method is flexible enough to handle different types of artifacts, including duplication, misalignment, truncation, and interpolation.

Methods

We trained and validated a U-net convolutional neural network artifact detection model on more than 23 000 coronal slices extracted from 98 4DCT scans. The receiver operating characteristic (ROC) curve and precision-recall curve were used to evaluate the model's performance at identifying artifacts compared to a manually identified ground truth. The model was adjusted so that the sensitivity in identifying artifacts was equivalent to that of a human observer, as measured by computing the average ratio of artifact volume to lung volume in a given scan.

Results

The model achieved a sensitivity, specificity, and precision of 0.78, 0.99, and 0.58, respectively. The ROC area-under-the-curve (AUC) was 0.99 and the precision-recall AUC was 0.73. Our model sensitivity is 8% higher than previously reported state-of-the-art artifact detection methods.

Conclusions

The model developed in this study is versatile, designed to handle duplication, misalignment, truncation, and interpolation artifacts within a single image, unlike earlier models that were designed for a single artifact type.