Artificial Intelligence System for Automatic Quantitative Analysis and Radiology Reporting of Leg Length Radiographs.

Leg length discrepancies are common orthopedic problems with the potential for poor functional outcomes. These are frequently assessed using bilateral leg length radiographs. The objective was to determine whether an artificial intelligence (AI)-based image analysis system can accurately interpret long leg length radiographic images. We built an end-to-end system to analyze leg length radiographs and generate reports like radiologists, which involves measurement of lengths (femur, tibia, entire leg) and angles (mechanical axis and pelvic tilt), describes presence and location of orthopedic hardware, and reports laterality discrepancies. After IRB approval, a dataset of 1,726 extremities (863 images) from consecutive examinations at a tertiary referral center was retrospectively acquired and partitioned into train/validation and test sets. The training set was annotated and used to train a fasterRCNN-ResNet101 object detection convolutional neural network. A second-stage classifier using a EfficientNet-D0 model was trained to recognize the presence or absence of hardware within extracted joint image patches. The system was deployed in a custom web application that generated a preliminary radiology report. Performance of the system was evaluated using a holdout 220 image test set, annotated by 3 musculoskeletal fellowship trained radiologists. At the object detection level, the system demonstrated a recall of 0.98 and precision of 0.96 in detecting anatomic landmarks. Correlation coefficients between radiologist and AI-generated measurements for femur, tibia, and whole-leg lengths were > 0.99, with mean error of < 1%. Correlation coefficients for mechanical axis angle and pelvic tilt were 0.98 and 0.86, respectively, with mean absolute error of < 1°. AI hardware detection demonstrated an accuracy of 99.8%. Automatic quantitative and qualitative analysis of leg length radiographs using deep learning is feasible and holds potential in improving radiologist workflow.

Rapidly progressive idiopathic arthritis of the hip: incidence and risk factors in a controlled cohort study of 1471 patients after intra-articular corticosteroid injection.

OBJECTIVE: Rapidly progressive idiopathic arthritis of the hip (RPIA) is defined by progressive joint space narrowing of > 2 mm or > 50% within 1 year. Our aims were to assess (a) the occurrence of RPIA after intra-articular steroid injection, and (b) possible risk factors for RPIA including: patient age, BMI, joint space narrowing, anesthetic and steroid selections, bone mineral density, and pain reduction after injection. MATERIALS AND METHODS: A retrospective search of our imaging database identified 1471 patients who had undergone fluoroscopically guided hip injection of triamcinolone acetonide (Kenalog) and anesthetic within a 10-year period. Patient data, including hip DXA results and patient-reported pain scores, were recorded. Pre-injection and follow-up radiographs were assessed for joint space narrowing, femoral head deformity, and markers of osteoarthritis. Osteoarthritis was graded by Croft score. Associations between patient characteristics and outcome variables were analyzed. RESULTS: One hundred six of 1471 injected subjects (7.2%) met the criteria for RPIA. A control group of 161 subjects was randomly selected from subjects who underwent hip injections without developing RPIA. Compared to controls, patients with RPIA were older, had narrower hip joint spaces, and higher Croft scores before injection (p < 0.05). Patients who developed RPIA did not differ from controls in sex, BMI, hip DXA T-score, anesthetic and steroid injectates, or pain improvement after injection. CONCLUSION: We found that approximately 7% of patients undergoing steroid hip injection developed RPIA. More advanced patient age, greater joint space narrowing, and more severe osteoarthritis are risk factors for the development of RPIA after intra-articular steroid injection.