前交叉韧带损伤与术后人群超声图像中股四头肌横截面积的自动分割:卷积神经网络的开发与验证
本研究利用124例前交叉韧带损伤参与者的股四头肌全景超声图像训练卷积神经网络模型,并在100例未见外部验证图像上测试,所有模型与手动分割具有良好可比性(ICC>0.81),剔除错误预测后可比性极佳(ICC>0.94),可用于自动测量股外侧肌、股直肌和股内侧肌横截面积。
要点
- 新卷积神经网络模型可用于前交叉韧带损伤人群自动测量股外侧肌、股直肌和股内侧肌横截面积。
- 模型与手动分割结果具有高度可比性,能减少手动分割负担。
- 错误预测率:联合股外侧肌模型17%、联合股直肌模型11%、仅前交叉韧带损伤股内侧肌模型20%。
核心结论
- 新卷积神经网络模型可在前交叉韧带损伤人群中自动测量股外侧肌、股直肌和股内侧肌的横截面积,与手动分割结果高度可比,并减少手动分割负担。
研究设计与样本
- 研究利用124例前交叉韧带损伤参与者(年龄22.8±7.9岁,女性61例)的股四头肌全景超声图像训练卷积神经网络模型,股外侧肌n=430、股直肌n=349、股内侧肌n=723。
诊断标准与关键数值
- 所有模型与手动分割相比ICC>0.81、标准测量误差<14.1%、平均差异<1.56 cm²;剔除错误预测后ICC>0.94、标准测量误差<7.40%、平均差异<0.57 cm²。
临床应用与阅片要点
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: Deep learning approaches such as DeepACSA enable automated segmentation of muscle ultrasound cross-sectional area (CSA). Although they provide fast and accurate results, most are developed using data from healthy populations. The changes in muscle size and quality following anterior cruciate ligament (ACL) injury challenges the validity of these automated approaches in the ACL population. Quadriceps muscle CSA is an important outcome following ACL injury; therefore, our aim was to validate DeepACSA, a convolutional neural network (CNN) approach for ACL injury.
METHODS: Quadriceps panoramic CSA ultrasound images (vastus lateralis [VL] n = 430, rectus femoris [RF] n = 349, and vastus medialis [VM] n = 723) from 124 participants with an ACL injury (age 22.8 ± 7.9 y, 61 females) were used to train CNN models. For VL and RF, combined models included extra images from healthy participants (n = 153, age 38.2, range 13-78) that the DeepACSA was developed from. All models were tested on unseen external validation images (n = 100) from ACL-injured participants. Model predicted CSA results were compared to manual segmentation results.
RESULTS: All models showed good comparability (ICC > 0.81, < 14.1% standard error of measurement, mean differences of <1.56 cm2) to manual segmentation. Removal of the erroneous predictions resulted in excellent comparability (ICC > 0.94, < 7.40% standard error of measurement, mean differences of <0.57 cm2). Erroneous predictions were 17% for combined VL, 11% for combined RF, and 20% for ACL-only VM models.
CONCLUSION: The new CNN models provided can be used in ACL-injured populations to measure CSA of VL, RF, and VM muscles automatically. The models yield high comparability to manual segmentation results and reduce the burden of manual segmentation.
引用
- Tayfur B, Ritsche P, Sunderlik O, et al. Automatic Segmentation of Quadriceps Femoris Cross-Sectional Area in Ultrasound Images: Development and Validation of Convolutional Neural Networks in People With Anterior Cruciate Ligament Injury and Surgery. Ultrasound Med Biol. 2024. PMID: 39581823. doi:10.1016/j.ultrasmedbio.2024.11.004
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。