Radiomics and Machine Learning for Skeletal Muscle Injury Recovery Prediction

Radiomics as a novel quantitative approach to medical imaging is an emerging area in the field of radiology. Artificial Intelligence offers promising tools for exploiting and analyzing radiomics. The objective present study propose methodology design, development, evaluation Machine Learning (ML) models prediction recovery progress skeletal muscle injury over time rats using were extracted from contrast enhanced Computed Tomography (CT) data ML algorithms trained compared their predictive value based on different CT parameters. Ten regression tested optimal combination radiomics each algorithm parameter settings was studied. best ensemble learning model, 70kVp, 100mA dataset, achieved Mean Absolute Error score 1.22. results suggest that images can be used input predict volume rats. Moreover, show impact performance models, indicating lower values tube current peak kilovoltage contribute more accurate predictions.