MUSCLE: Muscle Understanding through Synthetic Computation and Lesion Evaluation A Semi-Synthetic Dataset for Hamstring Injury Prediction Using Electrical Impedance

Hamstring Injuries (HSIs) are common among athletes and necessitate extended rehabilitation before Return to Sport (RTS). Post-injury, athletes undergo physical examinations, which often fall short in assessing injury severity or guiding rehabilitation. Therefore, imaging techniques such as Magnetic Resonance Imaging (MRI) are used to evaluate the injury more comprehensively, aiding in the assessment of optimal rehabilitation and RTS timelines. Given the significant impact of HSIs on athletic careers, early prediction is essential. This article investigates the use of Electrical Impedance Tomography (EIT) for HSI prediction. EIT, a noninvasive method, involves injecting a current or voltage into the affected area to detect property changes, allowing for real-time monitoring and supporting its role in HSI prediction. A semi-synthetic dataset was created using MRI scans of patients with hamstring injuries. The dataset was developed by mapping the boundaries of the hamstring muscles (semimembranosus, semitendinosus, and biceps femoris) with Electrical Impedance Tomography and Diffuse Optical Tomography Reconstruction Software (EIDORS). EIDORS generated EIT voltage measurements by defining muscle boundaries and setting appropriate properties, forming the basis for the dataset. Machine Learning (ML) models were then employed to validate the dataset by distinguishing between injured and healthy hamstrings. The best-performing model, Random Forest (RF), achieved an accuracy of 98%, demonstrating the potential of EIT in predicting HSIs. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=122 SRC="FIGDIR/small/24317096v1_fig1.gif" ALT="Figure 1"> View larger version (38K): org.highwire.dtl.DTLVardef@124532org.highwire.dtl.DTLVardef@17cd6adorg.highwire.dtl.DTLVardef@f23838org.highwire.dtl.DTLVardef@48ec32_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOFigure 1:C_FLOATNO Graphical Abstract C_FIG