Transfer learning-based ensemble convolutional neural network for accelerated diagnosis of foot fractures

• Published in: Physical and engineering sciences in medicine 2023-03, Vol.46 (1), p.265-277
• Main Authors: Kim, Taekyeong, Goh, Tae Sik, Lee, Jung Sub, Lee, Ji Hyun, Kim, Hayeol, Jung, Im Doo
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Biological and Medical Physics; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Deep Learning; Fractures, Bone - diagnostic imaging; Humans; Medical and Radiation Physics; Neural Networks, Computer; Radiography; Scientific Paper
• ISSN: 2662-4729; 2662-4737
• DOI: 10.1007/s13246-023-01215-w

The complex shape of the foot, consisting of 26 bones, variable ligaments, tendons, and muscles leads to misdiagnosis of foot fractures. Despite the introduction of artificial intelligence (AI) to diagnose fractures, the accuracy of foot fracture diagnosis is lower than that of conventional methods. We developed an AI assistant system that assists with consistent diagnosis and helps interns or non-experts improve their diagnosis of foot fractures, and compared the effectiveness of the AI assistance on various groups with different proficiency. Contrast-limited adaptive histogram equalization was used to improve the visibility of original radiographs and data augmentation was applied to prevent overfitting. Preprocessed radiographs were fed to an ensemble model of a transfer learning-based convolutional neural network (CNN) that was developed for foot fracture detection with three models: InceptionResNetV2, MobilenetV1, and ResNet152V2. After training the model, score class activation mapping was applied to visualize the fracture based on the model prediction. The prediction result was evaluated by the receiver operating characteristic (ROC) curve and its area under the curve (AUC), and the F1-Score. Regarding the test set, the ensemble model exhibited better classification ability (F1-Score: 0.837, AUC: 0.95, Accuracy: 86.1%) than other single models that showed an accuracy of 82.4%. With AI assistance for the orthopedic fellow, resident, intern, and student group, the accuracy of each group improved by 3.75%, 7.25%, 6.25%, and 7% respectively and diagnosis time was reduced by 21.9%, 14.7%, 24.4%, and 34.6% respectively.