Mahidol University's Institutional Repository
คลังสารสนเทศสถาบันของมหาวิทยาลัยมหิดล
"Wisdom Repository You Discover"
To collect Mahidol University's academic publications and intellectual properties more than 39 faculties
To present over 50,000 items of information in digital formats
To make it easy to access to all information at anytime, anywhere
Communities in Mahidol IR
Select a community to browse its collections.
Recent Submissions
Item
SEGSRNet for Stereo-Endoscopic Image Super-Resolution and Surgical Instrument Segmentation
(2024-01-01) Hayat M.; Aramvith S.; Achakulvisut T.; Hayat M.; Mahidol University
SEGSRNet addresses the challenge of precisely identifying surgical instruments in low-resolution stereo endoscopic images, a common issue in medical imaging and robotic surgery. Our innovative framework enhances image clarity and segmentation accuracy by applying state-of-the-art super-resolution techniques before segmentation. This ensures higher-quality inputs for more precise segmentation. SEGSRNet combines advanced feature extraction and attention mechanisms with spatial processing to sharpen image details, which is significant for accurate tool identification in medical images. Our proposed model, SEGSRNet, surpasses existing models in evaluation metrics including PSNR and SSIM for super-resolution tasks, as well as IoU and Dice Score for segmentation. SEGSRNet can provide image resolution and precise segmentation which can significantly enhance surgical accuracy and patient care outcomes.
Item
Data Analytics and Visualization in Bimanual Rehabilitation Monitoring Systems: A User-Centered Design Approach to Healthcare Professionals Decision Support
(2024-01-01) Wisedsri P.; Anutariya C.; Sujarae A.; Vachalathiti R.; Bovonsunthonchai S.; Wisedsri P.; Mahidol University
This study presents the design of a user-centered data visualization dashboard for stroke rehabilitation, which integrates the principles of visualization data analytics techniques in the field of healthcare. Addressing the complexities of visualizing for robotic bimanual rehabilitation, the design introduces novel methods to enhance data visualization, broadening monitoring capabilities, and improving the clarity of torque data. These enhancements lead to a clearer understanding of patient robot interactions. A prototype has been developed to visualize transparent torque data from a bimanual master slave robotic system, enabling healthcare professionals to monitor patient progress effectively. The dashboard features intuitive visual representations of master, slave, and assistive torques, simulating elbow joint movements through line and sunburst charts. Feedback from rehabilitation therapists during the design process ensures that the visualization approach is aligned with clinical needs. The findings suggest that the system can assist physiotherapists in devising personalized treatment strategies by providing actionable insights from the recorded data. However, additional research is needed to integrate real clinical data into the system for further enhancement and validation. This innovation has the potential to significantly improve stroke rehabilitation effectiveness and patient outcomes through a bimanual rehabilitation visualization and decision support system.
Item
Resilience of Quantum Key Distribution Source against Laser-Damage Attack by a Variety of Lasers
(2023-01-01) Ruzhitskaya D.; Zhluktova I.; Ponosova A.; Trefilov D.; Chaiwongkhot P.; Huang A.; Kamynin V.; Makarov V.; Ruzhitskaya D.; Mahidol University
Item
คู่มือปฏิบัติงาน การสำรองข้อมูลเครื่องคอมพิวเตอร์แม่ข่ายของคณะเภสัชศาสตร์ มหาวิทยาลัยมหิดล
(2566) โสรัจ ทัศนเจริญ