Abstract Background Automatic contouring can reduce the time required for delineating organs at risk (OARs) in brachytherapy planning and minimize interobserver variability. Purpose This study aimed to develop and evaluate a deep learning‐based automatic contouring model for OARs in three‐dimensional image‐guided brachytherapy (3D‐IGBT) for cervical and endometrial cancer, including cases with interstitial needles. Methods The dataset comprised 100 patients (140 cases) with cervical or endometrial cancer who underwent 3D‐IGBT. Interstitial needles were used in 74 cases. The nnU‐Net model was trained (80 patients, 80 cases) and tested (20 patients, 60 cases). The OARs considered were the bladder, small bowel, rectum, and sigmoid. Ground truth (GT) contours were manually delineated by radiation oncologists and medical physicists. Evaluation included measuring inference time and assessing geometric agreement using dice similarity coefficient (DSC), surface DSC (sDSC), Hausdorff distance (HD), and 95th percentile HD (95HD). These metrics were also calculated for a combined structure of the rectum and sigmoid (Rec+Sig). Furthermore, D _2cc was calculated based on both the GT and predicted contours using the clinical dose distribution, and the difference between them (ΔD _2cc ) was evaluated. Differences in accuracy with or without interstitial needles were compared using Welch's t ‐test (significance level: p  < 0.05). Results Mean processing time was 30.3 s per case. Mean DSC values for the bladder, small bowel, rectum, sigmoid, and Rec+Sig were 0.96, 0.79, 0.83, 0.76, and 0.87, respectively. Mean 95HD values (mm) were 4.01, 18.8, 13.6, 25.5, and 17.8, respectively; ΔD _2cc values (Gy) were 0.17, 0.53, 0.014, −0.073, and −0.045, respectively. No significant accuracy differences related to interstitial needles were observed for any of the OARs. Conclusions The proposed deep learning model demonstrated potential for application in cases involving interstitial needles and may contribute to improving the efficiency of the treatment planning workflow.

PURPOSE: Two-dimensional (2D) cine magnetic resonance imaging (MRI), available with a MR-linear accelerator (MR-Linac), allows real-time visualization of anatomical information during irradiation. The present study aimed to develop and evaluate a deep learning model that can estimate the organ-at-risk (OAR) dose constraints (mainly bladder V37Gy) from 2D cine MRI. METHODS: The present study enrolled 91 prostate cancer patients treated with MR-Linac. From 381 treatment fractions, sagittal images at the start and end of the 2D cine MRI were extracted. Additionally, 3D MRI data acquired pre- and post-irradiation were collected, from which bladder V37Gy was calculated. We designed the deep learning model to predict the end-of-irradiation bladder V37Gy value based on the bladder image on the end-of-irradiation 2D cine MRI. The model inputs included the start and end 2D cine MR images, a difference image between them, and the pre-irradiation bladder V37Gy. The model output was the post-irradiation bladder V37Gy. We utilized a five-fold cross-validation for model training and evaluated the performance using a test dataset. For reference, we also evaluated the predictions made using only the pre-irradiation bladder V37Gy. RESULTS: In the test dataset, the model-predicted and true bladder V37Gy values showed a strong correlation (r = 0.89), with a mean absolute error (MAE) of 1.40 cm3. Using only the pre-irradiation bladder V37Gy value yielded an r of 0.79 and an MAE of 2.02 cm3. Our model also achieved an area under the curve, sensitivity, and specificity values of 0.98, 0.91, and 0.95, respectively, in detecting dose constraint violations (bladder V37Gy of > 10 cm3). CONCLUSIONS: Our results demonstrated that deep learning can effectively predict the OAR dose constraints during irradiation. However, it is noteworthy that these results show only a limited improvement and are constrained by several limitations.

Urinary toxicities are one of the serious complications of radiotherapy for prostate cancer, and dose-volume histogram of prostatic urethra has been associated with such toxicities in previous reports. Previous research has focused on estimating the prostatic urethra, which is difficult to delineate in CT images; however, these studies, which are limited in number, mainly focused on cases undergoing brachytherapy uses low-dose-rate sources and do not involve external beam radiation therapy (EBRT). In this study, we aimed to develop a deep learning-based method of determining the position of the prostatic urethra in patients eligible for EBRT. We used contour data from 430 patients with localized prostate cancer. In all cases, a urethral catheter was placed when planning CT to identify the prostatic urethra. We used 2D and 3D U-Net segmentation models. The input images included the bladder and prostate, while the output images focused on the prostatic urethra. The 2D model determined the prostate's position based on results from both coronal and sagittal directions. Evaluation metrics included the average distance between centerlines. The average centerline distances for the 2D and 3D models were 2.07 ± 0.87 mm and 2.05 ± 0.92 mm, respectively. Increasing the number of cases while maintaining equivalent accuracy as we did in this study suggests the potential for high generalization performance and the feasibility of using deep learning technology for estimating the position of the prostatic urethra.

In external radiotherapy of head and neck (HN) cancers, the reduction of irradiation accuracy due to HN volume reduction often causes a problem. Adaptive radiotherapy (ART) can effectively solve this problem; however, its application to all cases is impractical because of cost and time. Therefore, finding priority cases is essential. This study aimed to predict patients with HN cancers are more likely to need ART based on a quantitative measure of large HN volume reduction and evaluate model accuracy. The study included 172 cases of patients with HN cancer who received external irradiation. The HN volume was calculated using cone-beam computed tomography (CT) for irradiation-guided radiotherapy for all treatment fractions and classified into two groups: cases with a large reduction in the HN volume and cases without a large reduction. Radiomic features were extracted from the primary gross tumor volume (GTV) and nodal GTV of the planning CT. To develop the prediction model, four feature selection methods and two machine-learning algorithms were tested. Predictive performance was evaluated by the area under the curve (AUC), accuracy, sensitivity and specificity. Predictive performance was the highest for the random forest, with an AUC of 0.662. Furthermore, its accuracy, sensitivity and specificity were 0.692, 0.700 and 0.813, respectively. Selected features included radiomic features of the primary GTV, human papillomavirus in oropharyngeal cancer and the implementation of chemotherapy; thus, these features might be related to HN volume change. Our model suggested the potential to predict ART requirements based on HN volume reduction .

PURPOSE: Accurate identification of the prostatic urethra and bladder can help determine dosing and evaluate urinary toxicity during intensity-modulated radiation therapy (IMRT) planning in patients with localized prostate cancer. However, it is challenging to locate the prostatic urethra in planning computed tomography (pCT). In the present study, we developed a multiatlas-based auto-segmentation method for prostatic urethra identification using deformable image registration accuracy prediction with machine learning (ML) and assessed its feasibility. METHODS: We examined 120 patients with prostate cancer treated with IMRT. All patients underwent temporary urinary catheter placement for identification and contouring of the prostatic urethra in pCT images (ground truth). Our method comprises the following three steps: (a) select four atlas datasets from the atlas datasets using the deformable image registration (DIR) accuracy prediction model, (b) deform them by structure-based DIR, (3) and propagate urethra contour using displacement vector field calculated by the DIR. In (a), for identifying suitable datasets, we used the trained support vector machine regression (SVR) model and five feature descriptors (e.g., prostate volume) to increase DIR accuracy. This method was trained/validated using 100 patients and performance was evaluated within an independent test set of 20 patients. Fivefold cross-validation was used to optimize the hype parameters of the DIR accuracy prediction model. We assessed the accuracy of our method by comparing it with those of two others: Acostas method-based patient selection (previous study method, by Acosta et al.), and the Waterman's method (defines the prostatic urethra based on the center of the prostate, by Waterman et al.). We used the centerlines distance (CLD) between the ground truth and the predicted prostatic urethra as the evaluation index. RESULTS: The CLD in the entire prostatic urethra was 2.09 ± 0.89 mm (our proposed method), 2.77 ± 0.99 mm (Acosta et al., P = 0.022), and 3.47 ± 1.19 mm (Waterman et al., P < 0.001); our proposed method showed the highest accuracy. In segmented CLD, CLD in the top 1/3 segment was highly improved from that of Waterman et.al. and was slightly improved from that of Acosta et.al., with results of 2.49 ± 1.78 mm (our proposed method), 2.95 ± 1.75 mm (Acosta et al., P = 0.42), and 5.76 ± 3.09 mm (Waterman et al., P < 0.001). CONCLUSIONS: We developed a DIR accuracy prediction model-based multiatlas-based auto-segmentation method for prostatic urethra identification. Our method identified prostatic urethra with mean error of 2.09 mm, likely due to combined effects of SVR model employment in patient selection, modified atlas dataset characteristics and DIR algorithm. Our method has potential utility in prostate cancer IMRT and can replace use of temporary indwelling urinary catheters.