Ankle fracture classification using deep learning: automating detailed AO Foundation/Orthopedic Trauma Association (AO/OTA) 2018 malleolar fracture identification reaches a high degree of correct classification

Abstract

Background and purpose — Classification of ankle fractures is crucial for guiding treatment but advanced classifications such as the AO Foundation/Orthopedic Trauma Association (AO/OTA) are often too complex for human observers to learn and use. We have therefore investigated whether an automated algorithm that uses deep learning can learn to classify radiographs according to the new AO/OTA 2018 standards. Method — We trained a neural network based on the ResNet architecture on 4,941 radiographic ankle examinations. All images were classified according to the AO/OTA 2018 classification. A senior orthopedic surgeon (MG) then re-evaluated all images with fractures. We evaluated the network against a test set of 400 patients reviewed by 2 expert observers (MG, AS) independently. Results — In the training dataset, about half of the examinations contained fractures. The majority of the fractures were malleolar, of which the type B injuries represented almost 60% of the cases. Average area under the area under the receiver operating characteristic curve (AUC) was 0.90 (95% CI 0.82–0.94) for correctly classifying AO/OTA class where the most common major fractures, the malleolar type B fractures, reached an AUC of 0.93 (CI 0.90–0.95). The poorest performing type was malleolar A fractures, which included avulsions of the fibular tip. Interpretation — We found that a neural network could attain the required performance to aid with a detailed ankle fracture classification. This approach could be scaled up to other body parts. As the type of fracture is an important part of orthopedic decision-making, this is an important step toward computer-assisted decision-making.

Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: an introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal

“…Image analysis (also coined as "computer vision") has gathered much attention and success. It entails analyzing and classifying the contents of images, for example, fractures (Olczak et al 2021). Sometimes the task is to classify the contents of the image and specify a feature's location in an image.…”

“…Together these have resulted in new and exciting developments. Examples range from new drug discoveries (Fleming 2018, Paul et al 2020) to skin cancer detection (Esteva et al 2017), automated screening of diabetic retinopathy (Gulshan et al 2016(Gulshan et al , 2019, fracture detection in radiographs (Badgeley et al 2019, Qi et al 2020, Olczak et al 2021, detecting rotator cuff tears in MRI (Shim et al 2020) or vertebral fractures in CT scans (Nicolaes et al 2019). As many methods require a deeper understanding of computer science, we see engineers perform much of the research geared towards healthcare professionals.…”

Real-world analysis of artificial intelligence in musculoskeletal trauma

“…DL can play a huge role as many of the classification systems are tedious and take time to interpret; this time could instead be better utilised in patient assessment. A DL model developed by Oczak et al 26 to classify the ankle fractures based on the 2018 Arbeitsgemeinschaft fur Osteosynthesefragen (AO)/Orthopedic Trauma Association (OTA) over a dataset of 4941 patients reached an average AUC of 0.90. A study by Li YC et alto classify vertebral fractures based on the Genant classification using plain lateral radiographs from 941 patients reached an AUC of 0.919, 0.989 and 0.990 for grades-1, 2 and 3 respectively.…”

Artificial intelligence in musculoskeletal conditions

“…AI has also been used to classify fractures. There are algorithms that have shown a hip fracture classification accuracy of 93.7% [20], a femur fracture classification ac-curacy of 86% [33], a proximal humerus fracture classification accuracy of 65-86% [34] and good performance in classifying fractures around the knees [35] and ankles [36].…”