A multicenter study on deep learning for glioblastoma auto-segmentation with prior knowledge in multimodal imaging.

A precise radiotherapy plan is crucial to ensure accurate segmentation of glioblastomas (GBMs) for radiation therapy. However, the traditional manual segmentation process is labor-intensive and heavily reliant on the experience of radiation oncologists. In this retrospective study, a novel auto-segmentation method is proposed to address these problems. To assess the method's applicability across diverse scenarios, we conducted its development and evaluation using a cohort of 148 eligible patients drawn from four multicenter datasets and retrospective data collection including noncontrast CT, multisequence MRI scans, and corresponding medical records. All patients were diagnosed with histologically confirmed high-grade glioma (HGG). A deep learning-based method (PKMI-Net) for automatically segmenting gross tumor volume (GTV) and clinical target volumes (CTV1 and CTV2) of GBMs was proposed by leveraging prior knowledge from multimodal imaging. The proposed PKMI-Net demonstrated high accuracy in segmenting, respectively, GTV, CTV1, and CTV2 in an 11-patient test set, achieving Dice similarity coefficients (DSC) of 0.94, 0.95, and 0.92; 95% Hausdorff distances (HD95) of 2.07, 1.18, and 3.95 mm; average surface distances (ASD) of 0.69, 0.39, and 1.17 mm; and relative volume differences (RVD) of 5.50%, 9.68%, and 3.97%. Moreover, the vast majority of GTV, CTV1, and CTV2 produced by PKMI-Net are clinically acceptable and require no revision for clinical practice. In our multicenter evaluation, the PKMI-Net exhibited consistent and robust generalizability across the various datasets, demonstrating its effectiveness in automatically segmenting GBMs. The proposed method using prior knowledge in multimodal imaging can improve the contouring accuracy of GBMs, which holds the potential to improve the quality and efficiency of GBMs' radiotherapy.

Machine learning-based ensemble prediction model for the gamma passing rate of VMAT-SBRT plan.

PURPOSE: The purpose of this study was to accurately predict or classify the beam GPR with an ensemble model by using machine learning for SBRT(VMAT) plans. METHODS: A total of 128 SBRT VMAT plans with 330 arc beams were retrospectively selected, and 216 radiomics and 34 plan complexity features were calculated for each arc beam. Three models for GPR prediction and classification using support vector machine algorithm were as follows: (1) plan complexity feature-based model (plan model); (2) radiomics feature-based model (radiomics model); and (3) an ensemble model combining the two models (ensemble model). The prediction performance was evaluated by calculating the mean absolute error (MAE), root mean square error (RMSE), and Spearman's correlation coefficient (SC), and the classification performance was measured by calculating the area under the receiver operating characteristic curve (AUC), accuracy, specificity, and sensitivity. RESULTS: The MAE, RMSE and SC at the 2 %/2 mm gamma criterion in the test dataset were 1.4 %, 2.57 %, and 0.563, respectively, for the plan model; 1.42 %, and 2.51 %, and 0.508, respectively, for the radiomics model; and 1.33 %, 2.49 %, and 0.611, respectively, for the ensemble model. The accuracy, specificity, sensitivity, and AUC at the 2 %/2 mm gamma criterion in the test dataset were 0.807, 0.824, 0.681, and 0.854, respectively, for the plan model; 0.860, 0.893, 0.624, and 0.877, respectively, for the radiomics model; and 0.852, 0.871, 0.710, and 0.896, respectively, for the ensemble model. CONCLUSIONS: The ensemble model can improve the prediction and classification performance for the GPR of SBRT (VMAT).

Dosimetric comparison of coplanar and noncoplanar volumetric modulated arc therapy for hippocampal-sparing whole-brain radiation therapy.

Whole brain radiation therapy with hippocampal-sparing (HS-WBRT) is a novel treatment of brain metastases, which can relieve symptoms reduce recurrence in the central nervous system, and spare the hippocampus without compromising target coverage. This study aims to find out the superior combination of the treatment planning system and linear accelerator between Eclipse (version 15.6) with TrueBeam and uRT-TPOIS (vision R001.4) with uRT-linac 506c in HS-WBRT. The coplanar and noncoplanar volumetric modulated arc therapy (VMAT) for HS-WBRT plans were evaluated and compared on both combinations, respectively. Twenty patients for HS-WBRT were retrospectively selected at Peking Union Medical College Hospital (PUMCH) from 2021 to 2022. The coplanar and noncoplanar HS-WBRT treatment plans were designed by Eclipse and uRT-TPOIS referring to RTOG 0933 dose criteria, and their dosimetry parameters were compared. In addition, the plan complexity, monitor units, and beam-on time were recorded for Eclipse plans delivered on TrueBeam and uRT-TPOIS plans delivered on uRT-linac 506c. The results demonstrated that the dosimetric criteria of 4 types of HS-WBRT plans could meet the requirements of RTOG 0933. In terms of target coverage, dosimetric indexes of Eclipse plans and uRT-TPOIS plans were comparable, and the former is slightly better. As for metrics of organs-at-risk protection, coplanar and noncoplanar plans conducted by uRT-TPOIS were greatly superior to those by Eclipse. For coplanar and noncoplanar plans designed by the same treatment planning system, most of the dosimetric indexes had no significant difference. The monitor units of uRT-TPOIS plans was higher than that of Eclipse plans, but the modulation complexity of them were close, and uRT-TPOIS with uRT-linac 506c significantly reduced beam-on-time consumption by 9% on average for coplanar plans and 26% for noncoplanar plans compared to Eclipse with TrueBeam. This study firstly compared the coplanar and noncoplanar HS-WBRT treatment plans between Eclipse with TrueBeam and uRT-TPOIS with uRT-linac 506c in terms of dosimetry indexes, modulation complexity, and time consumption. It is shown that the radiation treatment solution of uRT-TPOIS with uRT-linac 506c is comparable with Eclipse with TrueBeam in terms of planning design, and significantly reduced the delivery time, which can be applied in clinical practice and promoted as a treatment format.

Deep learning-based low-dose CT for adaptive radiotherapy of abdominal and pelvic tumors.

The shape and position of abdominal and pelvic organs change greatly during radiotherapy, so image-guided radiation therapy (IGRT) is urgently needed. The world's first integrated CT-linac platform, equipped with fan beam CT (FBCT), can provide a diagnostic-quality FBCT for achieve adaptive radiotherapy (ART). However, CT scans will bring the risk of excessive scanning radiation dose. Reducing the tube current of the FBCT system can reduce the scanning dose, but it will lead to serious noise and artifacts in the reconstructed images. In this study, we proposed a deep learning method, Content-Noise Cycle-Consistent Generative Adversarial Network (CNCycle-GAN), to improve the image quality and CT value accuracy of low-dose FBCT images to meet the requirements of adaptive radiotherapy. We selected 76 patients with abdominal and pelvic tumors who received radiation therapy. The patients received one low-dose CT scan and one normal-dose CT scan in IGRT mode during different fractions of radiotherapy. The normal dose CT images (NDCT) and low dose CT images (LDCT) of 70 patients were used for network training, and the remaining 6 patients were used to validate the performance of the network. The quality of low-dose CT images after network restoration (RCT) were evaluated in three aspects: image quality, automatic delineation performance and dose calculation accuracy. Taking NDCT images as a reference, RCT images reduced MAE from 34.34 ± 5.91 to 20.25 ± 4.27, PSNR increased from 34.08 ± 1.49 to 37.23 ± 2.63, and SSIM increased from 0.92 ± 0.08 to 0.94 ± 0.07. The P value is less than 0.01 of the above performance indicators indicated that the difference were statistically significant. The Dice similarity coefficients (DCS) between the automatic delineation results of organs at risk such as bladder, femoral heads, and rectum on RCT and the results of manual delineation by doctors both reached 0.98. In terms of dose calculation accuracy, compared with the automatic planning based on LDCT, the difference in dose distribution between the automatic planning based on RCT and the automatic planning based on NDCT were smaller. Therefore, based on the integrated CT-linac platform, combined with deep learning technology, it provides clinical feasibility for the realization of low-dose FBCT adaptive radiotherapy for abdominal and pelvic tumors.