Objective: This study aimed to investigate the segmentation accuracy of organs at risk (OARs) when denoised computed tomography (CT) images are used as input data for a deep-learning-based auto-segmentation framework. Methods: We used non-contrast enhanced planning CT scans from 40 patients with breast cancer. The heart, lungs, esophagus, spinal cord, and liver were manually delineated by two experienced radiation oncologists in a double-blind manner. The denoised CT images were used as input data for the AccuContour^TM segmentation software to increase the signal difference between structures of interest and unwanted noise in non-contrast CT. The accuracy of the segmentation was assessed using the Dice similarity coefficient (DSC), and the results were compared with those of conventional deep-learning-based auto-segmentation without denoising. Results: The average DSC outcomes were higher than 0.80 for all OARs except for the esophagus. AccuContour^TM-based and denoising-based auto-segmentation demonstrated comparable performance for the lungs and spinal cord but showed limited performance for the esophagus. Denoising-based auto-segmentation for the liver was minimal but had statistically significantly better DSC than AccuContour^TM-based auto-segmentation (p < 0.05). Conclusions: Denoising-based auto-segmentation demonstrated satisfactory performance in automatic liver segmentation from non-contrast enhanced CT scans. Further external validation studies with larger cohorts are needed to verify the usefulness of denoising-based auto-segmentation.

Conventional non-local total variation (NLTV) approaches use the weight of a non-local means (NLM) filter, which degrades performance in low-dose cone-beam computed tomography (CBCT) images generated with a low milliampere-seconds (mAs) parameter value because a local patch used to determine the pixel weights comprises noisy-damaged pixels that reduce the similarity between corresponding patches. In this paper, we propose a novel type of NLTV based on a combination of mutual information (MI): MI-NLTV. It is based on a statistical measure for a similarity calculation between the corresponding bins of non-local patches vs. a reference patch. The weight is determined in terms of a statistical measure comprising the MI value between corresponding non-local patches and the reference-patch entropy. The MI-NLTV denoising process is applied to CBCT images generated by the analytical reconstruction algorithm using a ray-driven backprojector (RDB). The MI-NLTV objective function is minimized based on the steepest gradient descent optimization to augment the difference between a real structure and noise, cleaning noisy pixels without significant loss of the fine structure and details that remain in the reconstructed images. The proposed method was evaluated using patient data and actual phantom measurement data acquired with lower mAs. The results show that integrating the RDB further enhances the MI-NLTV denoising-based analytical reconstruction algorithm to achieve a higher CBCT image quality when compared with those generated by NLTV denoising-based approach, with an average of 15.97% higher contrast-to-noise ratio, 2.67% lower root mean square error, 0.12% lower spatial non-uniformity, 1.14% higher correlation, and an average of 18.11% higher detectability index. These quantitative results indicate that the incorporation of MI makes the NLTV more stable and robust than the conventional NLM filter for low-dose CBCT imaging. In addition, achieving clinically acceptable CBCT image quality despite low-mAs projection acquisition can reduce the burden on common online CBCT imaging, improving patient safety throughout the course of radiotherapy.

An HJ, et al. Prog Med Phys. 2019 Dec;30(4):160-166. https://doi.org/10.14316/pmp.2019.30.4.160

Jiwon Sung, Hyeongmin Jin, Jeongho Kim, Jong Min Park, Jung-in Kim, Chang Heon Choi, Minsoo Chun. Progress in Medical Physics 2020;31:163-71. https://doi.org/10.14316/pmp.2020.31.4.163

The purpose of this study is to evaluate RadCalc, an independent dose verification software, for patient-specific quality assurance (PSQA) in online adaptive planning with a magnetic resonance linear accelerator (MR-linac) of a 1.5 T. Version 7.1.4 of RadCalc to introduce the capability to establish a beam model that incorporates MR field characteristics. A total of six models were established, with one using manufacturer-provided data and the others differing in percentage depth dose (PDD) data sources. Overall, two models utilized PDD data from the treatment planning system (TPS), and three used commissioned PDD data from gantry angles of 0° and 270°. Simple tests on a virtual water phantom assessed dose-calculation accuracy, revealing percentage differences ranging from −0.5% to −20.6%. Excluding models with significant differences, clinical tests on 575 adaptive plans (prostate, liver, and breast) showed percentage differences of −0.51%, 1.12%, and 4.10%, respectively. The doses calculated using RadCalc demonstrated similar trends to those of the PSQA-based measurements. The newly released version of RadCalc enables beam modeling that considers the characteristics of the 1.5 T magnetic field. The accuracy of the software in calculating doses at 1.5 T magnetic fields has been verified, thereby making it a reliable and effective tool for PSQA in adaptive plans.

Sung J, et al. Prog Med Phys. 2019 Dec;30(4):150-154. https://doi.org/10.14316/pmp.2019.30.4.150