Han Chan Sik, Jeong Sun Woo, Kim Hyung Won, Choi Seung Myung, Lee Keon Myung
Department of Computer Science, Chungbuk National University, Cheongju 28644, Republic of Korea.
Department of Electronics Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea.
Diagnostics (Basel). 2024 Dec 5;14(23):2740. doi: 10.3390/diagnostics14232740.
Tibiofibula fractures occur across all age groups, and postoperative complications are frequent. An accurate and rapid classification methodology for these fractures could significantly assist physicians. Clinically, tibiofibula fractures occur at various locations, and the fracture types are not evenly distributed.
This paper presents a deep learning model for the interpretable multi-label classification of tibiofibula fractures in two-dimensional (2D) CT scan images, addressing the challenges posed by a limited sample size and an uneven distribution of fracture types. We retrospectively collected 2494 2D CT images from 168 patients with tibia or fibula fractures. The types of fractures identified in the CT scan images were classified according to the AO/OTA fracture classification. A deep learning model was developed to classify composite fractures in 2D CT images, providing visual interpretation for each identified class. The visual interpretation was given with the saliency maps constructed by the Grad-CAM++ method. The deep learning model was trained using data augmentation techniques to address class imbalance and the limited dataset size.
Our experiments demonstrated that the proposed model achieved a mean average precision (mAP) of 95.71%.
The saliency map-based visual interpretation enables the verification of whether the model provides reliable decision-making for classification.
胫腓骨骨折在所有年龄组中均有发生，术后并发症很常见。一种准确且快速的骨折分类方法能够显著帮助医生。临床上，胫腓骨骨折发生在不同部位，且骨折类型分布不均。
本文提出一种深度学习模型，用于对二维（2D）CT扫描图像中的胫腓骨骨折进行可解释的多标签分类，以应对样本量有限和骨折类型分布不均所带来的挑战。我们回顾性收集了168例胫腓骨骨折患者的2494张二维CT图像。CT扫描图像中识别出的骨折类型根据AO/OTA骨折分类进行分类。开发了一种深度学习模型来对二维CT图像中的复合骨折进行分类，并为每个识别出的类别提供可视化解释。通过Grad-CAM++方法构建的显著性图给出可视化解释。使用数据增强技术训练深度学习模型，以解决类别不平衡和数据集规模有限的问题。
我们的实验表明，所提出的模型实现了95.71%的平均精度均值（mAP）。
基于显著性图的可视化解释能够验证模型是否为分类提供可靠的决策。
