Department of Computer Engineering, College of IT Convergence, Gachon University, Seongnam, Republic of Korea.
Department of Health Sciences and Technology, Gachon Advanced Institute for Health Sciences and Technology, Gachon University, Incheon, Republic of Korea.
Sci Rep. 2024 May 28;14(1):12258. doi: 10.1038/s41598-024-63093-w.
With the recent increase in traffic accidents, pelvic fractures are increasing, second only to skull fractures, in terms of mortality and risk of complications. Research is actively being conducted on the treatment of intra-abdominal bleeding, the primary cause of death related to pelvic fractures. Considerable preliminary research has also been performed on segmenting tumors and organs. However, studies on clinically useful algorithms for bone and pelvic segmentation, based on developed models, are limited. In this study, we explored the potential of deep-learning models presented in previous studies to accurately segment pelvic regions in X-ray images. Data were collected from X-ray images of 940 patients aged 18 or older at Gachon University Gil Hospital from January 2015 to December 2022. To segment the pelvis, Attention U-Net, Swin U-Net, and U-Net were trained, thereby comparing and analyzing the results using five-fold cross-validation. The Swin U-Net model displayed relatively high performance compared to Attention U-Net and U-Net models, achieving an average sensitivity, specificity, accuracy, and dice similarity coefficient of 96.77%, of 98.50%, 98.03%, and 96.32%, respectively.
随着最近交通事故的增加，骨盆骨折的死亡率和并发症风险仅次于颅骨骨折。目前正在积极研究治疗内脏出血，这是与骨盆骨折相关的主要死亡原因。在肿瘤和器官分割方面也进行了相当多的初步研究。然而，基于已开发模型的骨骼和骨盆分割的临床有用算法的研究是有限的。在这项研究中，我们探讨了之前研究中提出的深度学习模型在准确分割 X 射线图像中骨盆区域的潜力。该研究的数据来自于 2015 年 1 月至 2022 年 12 月期间加图立大学仁川圣母医院的 940 名 18 岁或以上患者的 X 射线图像。为了分割骨盆，我们训练了 Attention U-Net、Swin U-Net 和 U-Net，并使用五折交叉验证比较和分析结果。与 Attention U-Net 和 U-Net 模型相比，Swin U-Net 模型的性能相对较高，平均灵敏度、特异性、准确性和 Dice 相似系数分别为 96.77%、98.50%、98.03%和 96.32%。
