基于人工智能的 Neer3 或 4 部分肱骨近端骨折术前虚拟复位的临床验证。

Clinical validation of artificial intelligence-based preoperative virtual reduction for Neer 3- or 4-part proximal humerus fractures.

机构信息

Department of Orthopaedic Surgery, University of Ulsan College of Medicine, Ulsan University Hospital, 25, Daehakbyeongwon-ro, Dong-Gu, Ulsan, 44033, Republic of Korea.

Industrial R&D Center, KAVILAB Co. Ltd, Seoul, Republic of Korea.

出版信息

BMC Musculoskelet Disord. 2024 Aug 27;25(1):669. doi: 10.1186/s12891-024-07798-z.

DOI:10.1186/s12891-024-07798-z

PMID:39192203

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11348784/

Abstract

BACKGROUND

If reduction images of fractures can be provided in advance with artificial-intelligence (AI)-based technology, it can assist with preoperative surgical planning. Recently, we developed the AI-based preoperative virtual reduction model for orthopedic trauma, which can provide an automatic segmentation and reduction of fractured fragments. The purpose of this study was to validate a quality of reduction model of Neer 3- or 4-part proximal humerus fractures established by AI-based technology.

METHODS

To develop the AI-based preoperative virtual reduction model, deep learning performed the segmentation of fracture fragments, and a Monte Carlo simulation completed the virtual reduction to determine the best model. A total of 20 pre/postoperative three-dimensional computed tomography (CT) scans of proximal humerus fracture were prepared. The preoperative CT scans were employed as the input of AI-based automated reduction (AI-R) to deduce the reduction models of fracture fragments, meanwhile, the manual reduction (MR) was conducted using the same CT images. Dice similarity coefficient (DSC) and intersection over union (IoU) between the reduction model from the AI-R/MR and postoperative CT scans were evaluated. Working times were compared between the two groups. Clinical validity agreement (CVA) and reduction quality score (RQS) were investigated for clinical validation outcomes by 20 orthopedic surgeons.

RESULTS

The mean DSC and IoU were better when using AI-R that when using MR (0.78 ± 0.13 vs. 0.69 ± 0.16, p < 0.001 and 0.65 ± 0.16 vs. 0.55 ± 0.18, p < 0.001, respectively). The working time of AI-R was, on average, 1.41% of that of MR. The mean CVA of all cases was 81%±14.7% (AI-R, 82.25%±14.27%; MR, 76.75%±14.17%, p = 0.06). The mean RQS was significantly higher when AI-R compared with MR was used (91.47 ± 1.12 vs. 89.30 ± 1.62, p = 0.045).

CONCLUSION

The AI-based preoperative virtual reduction model showed good performance in the reduction model in proximal humerus fractures with faster working times. Beyond diagnosis, classification, and outcome prediction, the AI-based technology can change the paradigm of preoperative surgical planning in orthopedic surgery.

LEVEL OF EVIDENCE

Level IV.

摘要

背景

如果能够通过人工智能（AI）技术提前提供骨折的复位图像，这将有助于术前手术规划。最近，我们开发了一种基于 AI 的骨科创伤术前虚拟复位模型，可以实现骨折碎片的自动分割和复位。本研究的目的是验证一种基于 AI 技术的 Neer 3 或 4 部分肱骨近端骨折复位模型的质量。

方法

为了开发基于 AI 的术前虚拟复位模型，深度学习技术完成骨折碎片的分割，蒙特卡罗模拟完成虚拟复位，以确定最佳模型。共准备了 20 例肱骨近端骨折的术前和术后三维 CT 扫描。将术前 CT 扫描作为 AI 自动复位（AI-R）的输入，推导出骨折碎片的复位模型，同时使用相同的 CT 图像进行手动复位（MR）。评估 AI-R/MR 和术后 CT 扫描之间的复位模型的 Dice 相似系数（DSC）和交并比（IoU）。比较两组的工作时间。20 名骨科医生对临床验证结果进行了临床有效性一致性（CVA）和复位质量评分（RQS）的评估。

结果

AI-R 的平均 DSC 和 IoU 优于 MR（0.78±0.13 比 0.69±0.16，p<0.001 和 0.65±0.16 比 0.55±0.18，p<0.001）。AI-R 的平均工作时间为 MR 的 1.41%。所有病例的平均 CVA 为 81%±14.7%（AI-R，82.25%±14.27%；MR，76.75%±14.17%，p=0.06）。与 MR 相比，AI-R 时的平均 RQS 显著更高（91.47±1.12 比 89.30±1.62，p=0.045）。