Learning Models for Bone Marrow Edema Detection in Magnetic Resonance Imaging

Bone marrow edema (BME) is the term given to the abnormal fluid signal seen within the bone marrow on magnetic resonance imaging (MRI). It usually indicates the presence of underlying pathology and is associated with a myriad of conditions/causes. However, it can be misleading, as in some cases, it may be associated with normal changes in the bone, especially during the growth period of childhood, and objective methods for assessment are lacking. In this work, learning models for BME detection were developed. Transfer learning was used to overcome the size limitations of the dataset, and two different regions of interest (ROI) were defined and compared to evaluate their impact on the performance of the model: bone segmention and intensity mask. The best model was obtained for the high intensity masking technique, which achieved a balanced accuracy of 0.792 +/- 0.034. This study represents a comparison of different models and data regularization techniques for BME detection and showed promising results, even in the most difficult range of ages: children and adolescents. The application of machine learning methods will help to decrease the dependence on the clinicians, providing an initial stratification of the patients based on the probability of edema presence and supporting their decisions on the diagnosis.

Automated summary

Bone marrow edema (BME) refers to abnormal fluid signal in the bone marrow on MRI and can indicate underlying pathology. This study developed learning models for BME detection using transfer learning to overcome dataset limitations. Different regions of interest were compared, and the high intensity masking technique achieved the best model performance with a balanced accuracy of 0.792 +/- 0.034. The application of machine learning methods can decrease reliance on clinicians for diagnosing BME.