Artificial intelligence (AI) in medicine is a rapidly growing field. In orthopedics, the clinical implementations of AI have not yet reached their full potential. Deep learning algorithms have shown promising results in computed radiographs for fracture detection, classification of OA, bone age, as well as automated measurements of the lower extremities. Studies investigating the performance of AI compared to trained human readers often show equal or better results, although human validation is indispensable at the current standards. The objective of this narrative review is to give an overview of AI in medicine and summarize the current applications of AI in orthopedic radiography imaging. Due to the different AI software and study design, it is difficult to find a clear structure in this field. To produce more homogeneous studies, open-source access to AI software codes and a consensus on study design should be aimed for.

Background/Objectives: scoliosis is a three-dimensional structural deformity characterized by lateral and rotational curvature of the spine. The current gold-standard method to assess scoliosis is the measurement of lateral curvature of the spine using the Cobb angle in coronal plane radiographs. The interrater variability for Cobb angle measurements reaches up to 10°. The purpose of this study was to describe and assess the performance of a fully automated method for measuring Cobb angles using a commercially available artificial intelligence (AI) model trained on over 17,000 images, and investigate its interrater/intrarater agreement with a reference standard. Methods: in total, 196 AP/PA full-spine radiographs were included in this study. A reference standard was established by four radiologists, defined as the median of their Cobb angle measurements. Independently, an AI-based software, IB Lab SQUIRREL (version 1.0), also performed Cobb angle measurements on the same radiographs. Results: after comparing the readers’ Cobb angle end vertebrae selection to the AI’s outputs, 194 curvatures were considered valid for performance assessment, displaying an accuracy of 88.58% in end vertebrae selection. The AI’s performance showed very low absolute bias, with a mean difference and standard deviation of differences from the reference standard of 0.16° ± 0.35° in the Cobb angle measurements. The ICC comparing the reference standard and the AI’s measurements was 0.97. Conclusions: the AI model demonstrated good results in the determination of end vertebrae and excellent results in automated Cobb angle measurements compared to radiologists and could serve as a reliable tool in clinical practice and research.

The morphometry of the hip and pelvis can be evaluated in native radiographs. Artificial-intelligence-assisted analyses provide objective, accurate, and reproducible results. This study investigates the performance of an artificial intelligence (AI)-based software using deep learning algorithms to measure radiological parameters that identify femoroacetabular impingement and hip dysplasia. Sixty-two radiographs (124 hips) were manually evaluated by three observers and fully automated analyses were performed by an AI-driven software (HIPPO™, ImageBiopsy Lab, Vienna, Austria). We compared the performance of the three human readers with the HIPPO™ using a Bayesian mixed model. For this purpose, we used the absolute deviation from the median ratings of all readers and HIPPO™. Our results indicate a high probability that the AI-driven software ranks better than at least one manual reader for the majority of outcome measures. Hence, fully automated analyses could provide reproducible results and facilitate identifying radiographic signs of hip disorders.

Lower limb malalignment can complicate symptoms and accelerate knee osteoarthritis (OA), necessitating consideration in study population selection. In this study, we develop and validate a deep learning model that classifies leg alignment as “normal” or “malaligned” from knee antero-posterior (AP)/postero-anterior (PA) radiographs alone, using an adjustable hip-knee-ankle (HKA) angle threshold. We utilized 8878 digital radiographs, including 6181 AP/PA full-leg x-rays (LLRs) and 2697 AP/PA knee x-rays (2292 with positioning frame, 405 without). The model's evaluation involved two steps: In step 1, the model's predictions on knee images cropped from LLRs were compared against the ground truth from the original LLRs. In step 2, the model was tested on knee AP radiographs, using corresponding same-day LLRs as a proxy for ground truth. The model effectively classified alignment, with step one achieving sensitivity and specificity of 0.92 for a threshold of 7.5°, and 0.90 and 0.85 for 5°. For positioning frame images, step two showed a sensitivity of 0.85 and specificity of 0.81 for 7.5°, and 0.79 and 0.74 for 5°. For non-positioning frame images, sensitivity and specificity were 0.91 and 0.83 for 7.5°, and 0.9 and 0.86 for 5°. The model developed in this study accurately classifies lower limb malalignment from AP/PA knee radiographs using adjustable thresholds, offering a practical alternative to LLRs. This can enhance the precision of study population selection and patient management.

A combination of an anterior sternoclavicular (SC) joint dislocation with a midshaft clavicle fracture is an extremely rare injury. If left untreated, it can lead to severely impaired function of the shoulder with a high risk for complications. A 45-year-old male patient presented with pain and impaired range of motion (ROM) in the left shoulder after a mountain bike crash. Radiographs and a computed tomography scan showed an anterior dislocation of the left SC joint and an ipsilateral midshaft fracture of the clavicle. Open reduction and internal fixation (ORIF) of the clavicle combined with SC joint stabilization using transosseous sutures was performed. Postoperatively, a shoulder-arm bandage was applied with passive motion starting on the first postoperative day. During follow-up, the patient showed an improved clinical function and could return to work after three weeks. Radiographs at eight weeks showed fracture healing without any signs of recurrent SC dislocation. At the final follow-up at 12 weeks, the patient returned to his pre-injury activity level and recreational sports. Despite minimal redislocation in the SC joint, the Constant-Murley Score showed a continuous improvement with 93%, compared to the contralateral side. In conclusion, surgical treatment of anterior SC joint dislocation with a midshaft clavicle fracture can restore shoulder function with no surgery-associated complications.