Pediatric osteopenia prediction and interpretation in wrist x-rays

Osteopenia, a condition marked by reduced bone mineral density (BMD), affects millions globally. Patients diagnosed with osteopenia typically have a BMD valued below the normal reference measure, but not low enough to meet the diagnostic criteria for osteoporosis. Deep learning techniques, and Convolutional Neural Networks (CNNs) in particular, have revolutionized various fields, including medicine and diagnostics. This class of deep learning algorithms, excel in image analysis and pattern recognition tasks. In medical diagnostics, CNNs have shown remarkable potential for accurately detecting diseases in various medical imaging modalities, such as Xrays, MRIs, and CT scans. These networks can identify subtle patterns and anomalies that may be challenging for human observers to detect. Recently, research has increasingly focused on machine learning interpretability and explainable AI, aiming to provide insights into the decision-making processes of these algorithms. In this work, we fine-tuned deep network models on a pediatric wrist X-ray dataset to classify osteopenia versus healthy bone patterns. We also employed a decision interpretability algorithm to understand the CNNs’ predictions. Our results indicate that CNNs can effectively learn bone tissue patterns, achieving an accuracy of over 95% in classifying osteopenia in pediatric wrist X-rays. The visual explanations may offer valuable insights into the key areas within the X-ray images that contribute most to the deep network predictions.