{"title":"利用深度学习对青少年特发性脊柱侧凸进行伦克自动分类","authors":"Baolin Zhang, Kanghao Chen, Haodong Yuan, Zhiheng Liao, Taifeng Zhou, Weiming Guo, Shen Zhao, Ruixuan Wang, Peiqiang Su","doi":"10.1002/jsp2.1327","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Purpose</h3>\n \n <p>The Lenke classification system is widely utilized as the preoperative evaluation protocol for adolescent idiopathic scoliosis (AIS). However, manual measurement is susceptible to observer-induced variability, which consequently impacts the evaluation of progression. The goal of this investigation was to develop an automated Lenke classification system utilizing innovative deep learning algorithms.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Using the database from the First Affiliated Hospital of Sun Yat-sen University, the whole spinal x-rays images were retrospectively collected. Specifically, images collection was divided into AIS and control group. The control group consisted of individuals who underwent routine health checks and did not have scoliosis. Afterwards, relative features of all images were annotated. Deep learning was implemented through the utilization of the key-point based detection method to realize the vertebral detection, and Cobb angle measurement and scoliosis classification were performed based on relevant standards. Besides, the segmentation method was employed to achieve the recognition of lumbar vertebral pedicle to determine the type of lumbar spine modifier. Finally, the model performance was further quantitatively analyzed.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>In the study, a total of 2082 spinal x-ray images were collected from 407 AIS patients and 227 individuals in the control group. The model for vertebral detection achieved an F1-score of 0.809 for curve type evaluation and an F1-score of 0.901 for thoracic sagittal profile. The intraclass correlation efficient (ICC) of the Cobb angle measurement was 0.925. In the analysis of performance for vertebra pedicle segmentation model, the F1-score of lumbar modification profile was 0.942, the intersection over union (IOU) of the target pixels was 0.827, and the Hausdorff distance (HD) was 6.565 ± 2.583 mm. Specifically, the F1-score for ultimate Lenke type classifier was 0.885.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>This study has constructed an automated Lenke classification system by employing the deep learning networks to achieve the recognition pattern and feature extraction. Our models require further validation in additional cases in the future.</p>\n </section>\n </div>","PeriodicalId":14876,"journal":{"name":"JOR Spine","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jsp2.1327","citationCount":"0","resultStr":"{\"title\":\"Automatic Lenke classification of adolescent idiopathic scoliosis with deep learning\",\"authors\":\"Baolin Zhang, Kanghao Chen, Haodong Yuan, Zhiheng Liao, Taifeng Zhou, Weiming Guo, Shen Zhao, Ruixuan Wang, Peiqiang Su\",\"doi\":\"10.1002/jsp2.1327\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Purpose</h3>\\n \\n <p>The Lenke classification system is widely utilized as the preoperative evaluation protocol for adolescent idiopathic scoliosis (AIS). However, manual measurement is susceptible to observer-induced variability, which consequently impacts the evaluation of progression. The goal of this investigation was to develop an automated Lenke classification system utilizing innovative deep learning algorithms.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>Using the database from the First Affiliated Hospital of Sun Yat-sen University, the whole spinal x-rays images were retrospectively collected. Specifically, images collection was divided into AIS and control group. The control group consisted of individuals who underwent routine health checks and did not have scoliosis. Afterwards, relative features of all images were annotated. Deep learning was implemented through the utilization of the key-point based detection method to realize the vertebral detection, and Cobb angle measurement and scoliosis classification were performed based on relevant standards. Besides, the segmentation method was employed to achieve the recognition of lumbar vertebral pedicle to determine the type of lumbar spine modifier. Finally, the model performance was further quantitatively analyzed.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>In the study, a total of 2082 spinal x-ray images were collected from 407 AIS patients and 227 individuals in the control group. The model for vertebral detection achieved an F1-score of 0.809 for curve type evaluation and an F1-score of 0.901 for thoracic sagittal profile. The intraclass correlation efficient (ICC) of the Cobb angle measurement was 0.925. In the analysis of performance for vertebra pedicle segmentation model, the F1-score of lumbar modification profile was 0.942, the intersection over union (IOU) of the target pixels was 0.827, and the Hausdorff distance (HD) was 6.565 ± 2.583 mm. Specifically, the F1-score for ultimate Lenke type classifier was 0.885.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusions</h3>\\n \\n <p>This study has constructed an automated Lenke classification system by employing the deep learning networks to achieve the recognition pattern and feature extraction. Our models require further validation in additional cases in the future.</p>\\n </section>\\n </div>\",\"PeriodicalId\":14876,\"journal\":{\"name\":\"JOR Spine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2024-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jsp2.1327\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JOR Spine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/jsp2.1327\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ORTHOPEDICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JOR Spine","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/jsp2.1327","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0
摘要
目的 Lenke分类系统被广泛用作青少年特发性脊柱侧凸(AIS)的术前评估方案。然而,人工测量容易受到观察者引起的变异的影响,从而影响对进展的评估。本研究的目标是利用创新的深度学习算法开发一种自动伦克分类系统。 方法 使用中山大学附属第一医院的数据库,回顾性地收集整个脊柱的 X 光图像。具体来说,图像收集分为 AIS 组和对照组。对照组由接受常规健康检查且没有脊柱侧弯的人组成。之后,对所有图像的相对特征进行注释。利用基于关键点的检测方法实现深度学习,从而实现脊椎检测,并根据相关标准进行 Cobb 角度测量和脊柱侧弯分类。此外,还采用分割方法实现了腰椎椎弓根的识别,以确定腰椎改建者的类型。最后,进一步对模型性能进行了定量分析。 结果 研究共收集了 407 名 AIS 患者和 227 名对照组患者的 2082 张脊柱 X 光图像。脊椎检测模型在曲线类型评估方面的 F1 分数为 0.809,在胸椎矢状剖面方面的 F1 分数为 0.901。Cobb角测量的类内相关效率(ICC)为0.925。在椎体椎弓根分割模型的性能分析中,腰椎修正剖面的 F1 分数为 0.942,目标像素的交点大于结合点(IOU)为 0.827,豪斯多夫距离(HD)为 6.565 ± 2.583 毫米。具体来说,终极伦克类型分类器的 F1 分数为 0.885。 结论 本研究通过采用深度学习网络来实现识别模式和特征提取,构建了一个自动化的伦克分类系统。我们的模型还需要在未来的更多案例中进一步验证。
Automatic Lenke classification of adolescent idiopathic scoliosis with deep learning
Purpose
The Lenke classification system is widely utilized as the preoperative evaluation protocol for adolescent idiopathic scoliosis (AIS). However, manual measurement is susceptible to observer-induced variability, which consequently impacts the evaluation of progression. The goal of this investigation was to develop an automated Lenke classification system utilizing innovative deep learning algorithms.
Methods
Using the database from the First Affiliated Hospital of Sun Yat-sen University, the whole spinal x-rays images were retrospectively collected. Specifically, images collection was divided into AIS and control group. The control group consisted of individuals who underwent routine health checks and did not have scoliosis. Afterwards, relative features of all images were annotated. Deep learning was implemented through the utilization of the key-point based detection method to realize the vertebral detection, and Cobb angle measurement and scoliosis classification were performed based on relevant standards. Besides, the segmentation method was employed to achieve the recognition of lumbar vertebral pedicle to determine the type of lumbar spine modifier. Finally, the model performance was further quantitatively analyzed.
Results
In the study, a total of 2082 spinal x-ray images were collected from 407 AIS patients and 227 individuals in the control group. The model for vertebral detection achieved an F1-score of 0.809 for curve type evaluation and an F1-score of 0.901 for thoracic sagittal profile. The intraclass correlation efficient (ICC) of the Cobb angle measurement was 0.925. In the analysis of performance for vertebra pedicle segmentation model, the F1-score of lumbar modification profile was 0.942, the intersection over union (IOU) of the target pixels was 0.827, and the Hausdorff distance (HD) was 6.565 ± 2.583 mm. Specifically, the F1-score for ultimate Lenke type classifier was 0.885.
Conclusions
This study has constructed an automated Lenke classification system by employing the deep learning networks to achieve the recognition pattern and feature extraction. Our models require further validation in additional cases in the future.