A HYBRID MULTI-MODAL DEEP LEARNING FRAMEWORK FOR AUTOMATED FRACTURE DETECTION IN RADIOGRAPHS AND CT IMAGES
DOI:
https://doi.org/10.53555/eijmhs.v11i1.274Keywords:
Fracture detection, X-ray, CT scan, multi-modal learning, deep learningAbstract
Bone fractures are among the most prevalent musculoskeletal injuries, necessitating prompt and accurate diagnosis to ensure effective treatment and reduce complications. Traditional fracture detection relies heavily on manual interpretation of X-ray and computed tomography (CT) images by radiologists, which is time-intensive and susceptible to human error, especially in the case of subtle or complex fractures. To address these challenges, this paper proposes FracturaX, a novel hybrid multi-modal deep learning framework designed for automated fracture detection across both X-ray and CT modalities. The proposed architecture integrates handcrafted radiomics features with deep convolutional features through a multi-stream network and an attention-based feature fusion mechanism, enhancing detection accuracy and robustness. The framework was evaluated on diverse datasets, demonstrating superior performance compared to existing single-modality approaches and providing interpretable visual explanations to support clinical decision-making. Experimental results confirm that FracturaX offers a promising step toward reliable, generalizable, and explainable computer-aided fracture diagnosis, potentially reducing diagnostic workload and improving patient outcomes.
References
Alam A, Al-Shamayleh AS, Thalji N, Raza A, Morales Barajas EA, Thompson EB, et al. Novel transfer learning based bone fracture detection using radiographic images. BMC Medical Imaging. 2025 Jan 3;25(1):5.
Dlshad Ahmed K, Hawezi R. Detection of bone fracture based on machine learning techniques. Measurement: Sensors. 2023 Jun;27:100723.
R. A. Rajpurkar, et al., "CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning," arXiv preprint arXiv:1711.05225, 2017.
A. Lindsey, et al., "Deep neural network improves fracture detection by clinicians," PNAS, vol. 115, no. 45, pp. 11591–11596, 2018.
A. Badgeley, et al., "Deep learning predicts hip fracture using confounding patient and healthcare variables," npj Digital Medicine, vol. 2, no. 1, p. 31, 2019.
J. Chung, et al., "Automated detection of clavicle fractures using deep learning," Radiology, vol. 297, no. 3, pp. 626–634, 2020.
H. Gale, et al., "Detection of pediatric wrist fractures using deep learning," Radiology: Artificial Intelligence, vol. 3, no. 2, 2021.
Y. Kim, et al., "Automatic segmentation of bone structures in CT images using U-Net," Computers in Biology and Medicine, vol. 121, 2020.
M. Bien, et al., "Deep-learning-assisted diagnosis for knee MRI," Radiology, vol. 287, no. 1, pp. 448–458, 2018.
K. Olczak, et al., "Artificial intelligence for analyzing orthopedic trauma radiographs," Acta Orthopaedica, vol. 88, no. 6, pp. 581–586, 2017.
C. Burns, et al., "Deep learning algorithms for automatic detection of vertebral fractures in CT images," European Radiology, vol. 29, no. 12, pp. 6610–6618, 2019.
S. Yasaka, et al., "Deep learning for automated detection of rib fractures at trauma CT," Radiology, vol. 287, no. 2, pp. 473–482, 2018.
B. Langerhuizen, et al., "Artificial intelligence in the emergency department: automatic fracture detection in ankle radiographs," Emergency Radiology, vol. 27, no. 6, pp. 643–650, 2020.
M. Cicero, et al., "Training and validating a deep convolutional neural network for computer-aided detection and classification of fractures in radiographs," Radiology, vol. 295, no. 3, pp. 628–640, 2020.
S. Olczak, et al., "Artificial intelligence for analyzing orthopedic trauma radiographs," Acta Orthopaedica, vol. 88, no. 6, pp. 581–586, 2017.
S. Thian, et al., "Convolutional neural networks for automated fracture detection and classification in wrist radiographs," Radiology: Artificial Intelligence, vol. 1, no. 1, 2019.
T. Chen, et al., "Multi-task learning for vertebrae fracture detection and localization in CT scans," Medical Image Analysis, vol. 67, 2021.
J. Krogue, et al., "Deep learning for detection of femur fractures on plain radiographs," Journal of Digital Imaging, vol. 33, pp. 655–660, 2020.
S. Cheng, et al., "Radiomics-based machine learning for prediction of vertebral compression fractures," European Spine Journal, vol. 29, pp. 445–453, 2020.
H. Liang, et al., "Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence," Nature Medicine, vol. 25, pp. 433–438, 2019.
Z. Yan, et al., "Domain adaptation for automatic fracture detection," Medical Image Analysis, vol. 61, 2020.
A. Olczak, et al., "Deep learning for detection of fractures in wrist radiographs," Radiology: Artificial Intelligence, vol. 1, no. 1, 2019.
