(1) In this study, we developed a deep learning (DL) model that can be used to predict late bladder toxicity. (2) We collected data obtained from 281 uterine cervical cancer patients who underwent definitive radiation therapy. The DL model was trained using 16 features, including patient, tumor, treatment, and dose parameters, and its performance was compared with that of a multivariable logistic regression model using the following metrics: accuracy, prediction, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). In addition, permutation feature importance was calculated to interpret the DL model for each feature, and the lightweight DL model was designed to focus on the top five important features. (3) The DL model outperformed the multivariable logistic regression model on our dataset. It achieved an F1-score of 0.76 and an AUROC of 0.81, while the corresponding values for the multivariable logistic regression were 0.14 and 0.43, respectively. The DL model identified the doses for the most exposed 2 cc volume of the bladder (BD_2cc) as the most important feature, followed by BD_5cc and the ICRU bladder point. In the case of the lightweight DL model, the F-score and AUROC were 0.90 and 0.91, respectively. (4) The DL models exhibited superior performance in predicting late bladder toxicity compared with the statistical method. Through the interpretation of the model, it further emphasized its potential for improving patient outcomes and minimizing treatment-related complications with a high level of reliability.

We performed a prospective phase II study to compare acute toxicity among five different hypofractionated schedules using proton therapy. This study was an exploratory analysis to investigate the secondary end-point of biochemical failure-free survival (BCFFS) of patients with long-term follow-up. Eighty-two patients with T1-3bN0M0 prostate cancer who had not received androgen-deprivation therapy were randomized to one of five arms: Arm 1, 60 cobalt gray equivalent (CGE)/20 fractions/5 weeks; Arm 2, 54 CGE/15 fractions/5 weeks; Arm 3, 47 CGE/10 fractions/5 weeks; Arm 4, 35 CGE/5 fractions/2.5 weeks; and Arm 5, 35 CGE/5 fractions/4 weeks. In the current exploratory analysis, these ardms were categorized into the moderate hypofractionated (MHF) group (52 patients in Arms 1–3) and the extreme hypofractionated (EHF) group (30 patients in Arms 4–5). At a median follow-up of 7.5 years (range, 1.3–9.6 years), 7-year BCFFS was 76.2% for the MHF group and 46.2% for the EHF group (p = 0.005). The 7-year BCFFS of the MHF and EHF groups were 90.5 and 57.1% in the low-risk group (p = 0.154); 83.5 and 42.9% in the intermediate risk group (p = 0.018); and 41.7 and 40.0% in the high risk group (p = 0.786), respectively. Biochemical failure tended to be a late event with a median time to occurrence of 5 years. Acute GU toxicities were more common in the MHF than the EHF group (85 vs. 57%, p = 0.009), but late GI and GU toxicities did not differ between groups. Our results suggest that the efficacy of EHF is potentially inferior to that of MHF and that further studies are warranted, therefore, to confirm these findings. This study is registered at ClinicalTrials.gov, no. NCT01709253 ; registered October 18, 2012; retrospectively registered).

Purpose: Imaging, breath‐holding/gating, and fixation devices have been developed to minimize setup errors so that the prescribed dose can be exactly delivered to the target volume in radiotherapy. Despite these efforts, additional patient monitoring devices have been installed in the treatment room to view patients’ whole‐body movement. We developed a facial expression recognition system using deep learning with a convolutional neural network (CNN) to predict patients’ advanced movement, enhancing the stability of the radiation treatment by giving warning signs to radiation therapists.Materials and methods: Convolutional neural network model and extended Cohn‐Kanade datasets with 447 facial expressions of source images for training were used. Additionally, a user interface that can be used in the treatment control room was developed to monitor real‐time patient's facial expression in the treatment room, and the entire system was constructed by installing a camera in the treatment room. To predict the possibility of patients' sudden movement, we categorized facial expressions into two groups: (a) uncomfortable expressions and (b) comfortable expressions. We assumed that the warning sign about the sudden movement was given when the uncomfortable expression was recognized.Results: We have constructed the facial expression monitoring system, and the training and test accuracy were 100% and 85.6%, respectively. In 10 patients, their emotions were recognized based on their comfortable and uncomfortable expressions with 100% detection rate. The detected various emotions were represented by a heatmap and motion prediction accuracy was analyzed for each patient.Conclusion: We developed a system that monitors the patient's facial expressions and predicts patient's advanced movement during the treatment. It was confirmed that our patient monitoring system can be complementarily used with the existing monitoring system. This system will help in maintaining the initial setup and improving the accuracy of radiotherapy for the patients using deep learning in radiotherapy.

The feasibility of proton minibeam radiation therapy (pMBRT) using a multislit collimator (MSC) and a scattering device was evaluated for clinical use at a clinical proton therapy facility. We fabricated, through Monte Carlo (MC) simulations, not only an MSC with a high peak-to-valley dose ratio (PVDR) at the entrance of the proton beam, to prevent radiation toxicity, but also a scattering device to modulate the PVDR in depth. The slit width and center-to-center distance of the diverging MSC were 2.5 mm and 5.0 mm at the large end, respectively, and its thickness and available field size were 100 mm and 76 × 77.5 mm², respectively. Spatially fractionated dose distributions were measured at various depths using radiochromic EBT3 films and also tested on bacterial cells. MC simulation showed that the thicker the MSC, the higher the PVDR at the phantom surface. Dosimetric evaluations showed that lateral dose profiles varied according to the scatterer’s thickness, and the depths satisfying PVDR = 1.1 moved toward the surface as their thickness increased. The response of the bacterial cells to the proton minibeams’ depth was also established, in a manner similar to the dosimetric pattern. Conclusively, these results strongly suggest that pMBRT can be implemented in clinical centers by using MSC and scatterers.

Brachytherapy is an important technique to increase the overall survival of cervical cancer patients. However, a possible shift of the applicators in relation to the target and organs at risk may occur between imaging and treatment. Without daily adaptive brachytherapy planning, these applicator displacements can lead to a significant change in dose distribution. In order to resolve it, a robust optimization method had been developed using a genetic algorithm combined with a median absolute deviation as a robustness evaluation function. The resulting robustness plans from our strategy might be worth considering according to the GEC-ESTRO guidelines. From the point of view of dose delivery uncertainty from applicator displacement, the robust optimization may be considered with caution in a single-plan approach for High Dose Rate brachytherapy treatment planning and should be confirmed by a more thorough investigation.

Seohyeon An, Sang-il Pak, Seonghoon Jeong, Soonki Min, Tae Jeong Kim, Dongho Shin, Youngkyung Lim, Jong Hwi Jeong, Haksoo Kim, Se Byeong Lee. Progress in Medical Physics 2022;33:80-7. https://doi.org/10.14316/pmp.2022.33.4.80