Department of Ultrasound, The First Affiliated Hospital of Hebei North University, Zhangjiakou, 075000, China.
Department of Orthopedics, The First Affiliated Hospital of Hebei North University, Zhangjiakou, 075000, China.
J Ultrasound Med. 2023 Feb;42(2):363-371. doi: 10.1002/jum.16059. Epub 2022 Jul 16.
Our study aimed to develop and validate an efficient ultrasound image-based radiomic model for determining the Achilles tendinopathy in skiers.
A total of 88 feet of skiers clinically diagnosed with unilateral chronic Achilles tendinopathy and 51 healthy feet were included in our study. According to the time order of enrollment, the data were divided into a training set (n = 89) and a test set (n = 50). The regions of interest (ROIs) were segmented manually, and 833 radiomic features were extracted from red, green, blue color channels and grayscale of ROIs using Pyradiomics, respectively. Three feature selection and three machine learning modeling algorithms were implemented respectively, for determining the optimal radiomics pipeline. Finally, the area under the receiver operating characteristic curve (AUC), consistency analysis, and decision analysis were used to evaluate the diagnostic performance.
By comparing nine radiomics analysis strategies of three color channels and grayscale, the radiomic model under the green channel obtained the best diagnostic performance, using the Random Forest selection and Support Vector Machine modeling, which was selected as the final machine learning model. All the selected radiomic features were significantly associated with the Achilles tendinopathy (P < .05). The radiomic model had a training AUC of 0.98, a test AUC of 0.99, a sensitivity of 0.90, and a specificity of 1, which could bring sufficient clinical net benefits.
Ultrasound image-based radiomics achieved high diagnostic performance, which could be used as an intelligent auxiliary tool for the diagnosis of Achilles tendinopathy.
本研究旨在开发和验证一种基于超声图像的高效放射组学模型，以确定滑雪者的跟腱病。
本研究共纳入 88 只临床诊断为单侧慢性跟腱病的滑雪者的脚和 51 只健康脚。根据入组的时间顺序，数据被分为训练集（n=89）和测试集（n=50）。手动对感兴趣区域（ROI）进行分割，并使用 Pyradiomics 分别从 ROI 的红、绿、蓝颜色通道和灰度提取 833 个放射组学特征。分别实施了三种特征选择和三种机器学习建模算法，以确定最佳放射组学管道。最后，使用接收者操作特征曲线（AUC）下的面积、一致性分析和决策分析来评估诊断性能。
通过比较三种颜色通道和灰度的九种放射组学分析策略，绿色通道下的放射组学模型获得了最佳的诊断性能，使用随机森林选择和支持向量机建模，被选为最终的机器学习模型。所有选定的放射组学特征均与跟腱病显著相关（P<.05）。放射组学模型的训练 AUC 为 0.98，测试 AUC 为 0.99，灵敏度为 0.90，特异性为 1，可带来足够的临床净效益。
基于超声图像的放射组学具有较高的诊断性能，可作为跟腱病诊断的智能辅助工具。
