Facial expression monitoring system for predicting patient's sudden movement during radiotherapy using deep learning.

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.

Feasibility study of shutter scan acquisition for region of interest (ROI) digital tomosynthesis.

Dose reduction techniques have been studied in medical imaging. We propose shutter scan acquisition for region of interest (ROI) imaging to reduce the patient exposure dose received from a digital tomosynthesis system. A prototype chest digital tomosynthesis (CDT) system (LISTEM, Wonju, Korea) and the LUNGMAN phantom (Kyoto Kagaku, Japan) with lung nodules 8, 10, and 12 mm in size were used for this study. A total of 41 projections with shutter scan acquisition consisted of 21 truncated projections and 20 non-truncated projections. For comparison, 41 projections using conventional full view scan acquisition were also acquired. Truncated projections obtained by shutter scan acquisition were corrected by proposed image processing procedure to remove the truncation artifacts. The image quality was evaluated using the contrast to noise ratio (CNR), coefficient of variation (COV), and figure of merit (FOM). We measured the dose area product (DAP) value to verify the dose reduction using shutter scan acquisition. The ROI of the reconstructed image from shutter scan acquisition showed enhanced contrast. The results showed that CNR values of 8 and 12 mm lung nodules increased by 6.38% and 21.21%, respectively, and the CNR value of 10 mm lung nodule decreased by 3.63%. COV values of the lung nodules were lower in a shutter scan image than in a full view scan image. FOM values of 8, 10, and 12 mm lung nodules increased by 3.06, 2.25, and 2.33 times, respectively. This study compared the proposed shutter scan and conventional full view scan acquisition. In conclusion, using a shutter scan acquisition method resulted in enhanced contrast images within the ROI and higher FOM values. The patient exposure dose of the proposed shutter scan acquisition method can be reduced by limiting the field of view (FOV) to focus on the ROI.