Abstrakt

Background:
Patients with severe bone fractures and complex bone deformities are treated by orthopedic surgeons with external fixation for several months. During this long treatment period, there is a high risk of inflammation and infection at the superficial skin area (called the pin site). That situation in some cases develops further into a devastating, sometimes fatal, and always a costly condition of deep bone infection.

Objective: For pin site infection surveillance while avoiding frequent nursing care, it has been proposed that thermography technology could be the solution to build an objective and continuous home-based remote monitoring tool. However, further studies on clinical judgment of infection severity require a preliminary step to automate the process of locating and detecting the pin sites in thermal images efficiently, exactly, and reliably for sufficient research data.

Methods: For this purpose, our paper presents an automatic approach for identifying and annotating pin sites on visible images using bounding boxes and transferring them to the corresponding thermal images. The center of the pin site is detected by applying deep learning-based object detection architecture YOLOv5 with a novel loss evaluation and regression method, Control Distance Intersection over Union (CDIoU). Furthermore, this paper addresses detecting pin sites in a practical environment accurately through transfer learning.

Results and Conclusion: The proposed model offers the pin site detection in 1.8 ms with a high precision of 0.98 and enables temperature information extraction. Our work for automatic pin site annotation on thermography paves the way for future research on infection assessment on thermography.
OriginalsprogEngelsk
TidsskriftDigital Health
StatusAfsendt - 2022

Fingeraftryk

Dyk ned i forskningsemnerne om 'Preparing Infection Detection Technology for Hospital at Home after Lower Limb External Fixation'. Sammen danner de et unikt fingeraftryk.

Citationsformater