Oriented histogram-based vector field embedding for characterizing 4D CT data sets in radiotherapy

In lung radiotherapy, the primary objective is to optimize treatment outcomes by minimizing exposure to healthy tissues while delivering the prescribed dose to the target volume. The challenge lies in accounting for lung tissue motion due to breathing, which impacts precise treatment alignment. To address this, the paper proposes a prospective approach that relies solely on pre-treatment information, such as planning CT scans and derived data like vector fields from deformable image registration. This data is compared to analogous patient data to tailor treatment strategies, i.e., to be able to review treatment parameters and success for similar patients. To allow for such a comparison, an embedding and clustering strategy of prospective patient data is needed. Therefore, the main focus of this study lies on reducing the dimensionality of deformable registration-based vector fields by employing a voxel-wise spherical coordinate transformation and a low-dimensional 2D oriented histogram representation. Afterwards, a fully unsupervised UMAP embedding of the encoded vector fields (i.e., patient-specific motion information) becomes applicable. The functionality of the proposed method is demonstrated with 71 in-house acquired 4D CT data sets and 33 external 4D CT data sets. A comprehensive analysis of the patient clusters is conducted, focusing on the similarity of breathing patterns of clustered patients. The proposed general approach of reducing the dimensionality of registration vector fields by encoding the inherent information into oriented histograms is, however, applicable to other tasks.

Deep learning-based conditional inpainting for restoration of artifact-affected 4D CT images

4D CT imaging is an essential component of radiotherapy of thoracic/abdominal tumors. 4D CT images are, however, often affected by artifacts that compromise treatment planning quality. In this work, deep learning (DL)-based conditional inpainting is proposed to restore anatomically correct image information of artifact-affected areas. The restoration approach consists of a two-stage process: DL-based detection of common interpolation (INT) and double structure (DS) artifacts, followed by conditional inpainting applied to the artifact areas. In this context, conditional refers to a guidance of the inpainting process by patient-specific image data to ensure anatomically reliable results. Evaluation is based on 65 in-house 4D CT data sets of lung cancer patients (48 with only slight artifacts, 17 with pronounced artifacts) and the publicly available DIRLab 4D CT data (independent external test set). Automated artifact detection revealed a ROC-AUC of 0.99 for INT and 0.97 for DS artifacts (in-house data). The proposed inpainting method decreased the average root mean squared error (RMSE) by 60% (DS) and 42% (INT) for the in-house evaluation data (simulated artifacts for the slight artifact data; original data were considered as ground truth for RMSE computation). For the external DIR-Lab data, the RMSE decreased by 65% and 36%, respectively. Applied to the pronounced artifact data group, on average 68% of the detectable artifacts were removed. The results highlight the potential of DL-based inpainting for the restoration of artifact-affected 4D CT data. Improved performance of conditional inpainting (compared to standard inpainting) illustrates the benefits of exploiting patient-specific prior knowledge.