Search

In this study, we developed an AI-based real-time motion feedback system for patients with spinal cord injury (SCI) during rehabilitation, aiming to enhance their interest and motivation. The effectiveness of the system in improving upper-limb muscle strength during the Thera band exercises was evaluated. The motion analysis program, including exercise repetition counts and calorie consumption, was developed using MediaPipe, focusing on three key motions (chest press, shoulder press, and arm curl) for upper extremity exercises. The participants with SCI were randomly assigned to the experimental group (EG = 4) or control group (CG = 5), engaging in 1 h sessions three times a week for 8 weeks. Muscle strength tests (chest press, shoulder press, lat pull-down, and arm curl) were performed before and after exercises. Although both groups did not show significant differences, the EG group exhibited increased strength in all measured variables, whereas the CG group showed constant or reduced results. Consequently, the computer program-based system developed in this study could be effective in muscle strengthening. Furthermore, these findings may serve as a valuable foundation for future AI-driven rehabilitation exercise systems. [ABSTRACT FROM AUTHOR]

As part of an ongoing investigation into the development of a dental digital radiographic (DDR) system using a complementary metal-oxide semiconductor (CMOS) sensor, this study developed hardware and software with a graphical user interface to acquire and display intra-oral images from a prototype DDR system. The aim of this study was to develop a DDR system using a CMOS sensor and evaluate its characteristics. Electrical signals that were generated by the CMOS sensor were transformed into digital images by a control computer equipped using a USB board. The distance between the X-ray tube and the CMOS sensor was adjusted within the range of 10-40 cm to provide the optimal image quality. In order to evaluate the image quality according to variations in the dose, phantom images (60 kVp, 7 mA) were obtained at exposure times of 0.03, 0.05, 0.08, 0.10, and 0.12 s, and the signal-to-noise ratio (SNR) was calculated from the phantom image data. The modulation transfer function (MTF) was obtained from a Fourier transform of the line spread function, which was itself derived from the edge spread function of a sharp edge image acquired using the exposure conditions of 60 kVp, 7 mA, and 0.08 s exposure time. The best contrast and focus were obtained at 20 cm. The SNR level was found to increase with increasing exposure time ranging from 0.03 to 0.08 s. The results obtained at 10% of the MTF showed that the resolution of the DDR system was approximately 6.2 line pairs per millimeter. The characteristics of the prototype DDR system have potential applications in intra-oral dental radiographic imaging. The fully developed DDR system can be used for making a clinical diagnosis with further improvements in the acquisition time and spatial resolution. Index Terms--CMOS sensor, dental digital radiographic (DDR) system, modulation transfer function (MTF).

Purpose: White matter hyperintensities (WMH) are typically segmented using MRI because WMH are hardly visible on 18F-FDG PET/CT. This retrospective study was conducted to segment WMH and estimate their volumes from 18F-FDG PET with a generative adversarial network (WhyperGAN). Methods: We selected patients whose interval between MRI and FDG PET/CT scans was within 3 months, from January 2017 to December 2018, and classified them into mild, moderate, and severe groups by following the semiquantitative rating method of Fazekas. For each group, 50 patients were selected, and of them, we randomly selected 35 patients for training and 15 for testing. WMH were automatically segmented from FLAIR MRI with manual adjustment. Patches of WMH were extracted from 18F-FDG PET and segmented MRI. WhyperGAN was compared with H-DenseUnet, a deep learning method widely used for segmentation tasks, for segmentation performance based on the dice similarity coefficient (DSC), recall, and average volume differences (AVD). For volume estimation, the predicted WMH volumes from PET were compared with ground truth volumes. Results: The DSC values were associated with WMH volumes on MRI. For volumes >60 mL, the DSC values were 0.751 for WhyperGAN and 0.564 for H-DenseUnet. For volumes ≤60 mL, the DSC values rapidly decreased as the volume decreased (0.362 for WhyperGAN vs. 0.237 for H-DenseUnet). For recall, WhyperGAN achieved the highest value in the severe group (0.579 for WhyperGAN vs. 0.509 for H-DenseUnet). For AVD, WhyperGAN achieved the lowest score in the severe group (0.494 for WhyperGAN vs. 0.941 for H-DenseUnet). For the WMH volume estimation, WhyperGAN performed better than H-DenseUnet and yielded excellent correlation coefficients (r = 0.998, 0.983, and 0.908 in the severe, moderate, and mild group). Conclusions: Although limited by visual analysis, the WhyperGAN based can be used to automatically segment and estimate volumes of WMH from 18F-FDG PET/CT. This would increase the usefulness of 18F-FDG PET/CT for the evaluation of WMH in patients with cognitive impairment. [ABSTRACT FROM AUTHOR]