Guillaume Gatineau Doctorant (Primary Author) , El Hassen Ahmed Lebrahim (Contributing Author Data Scientist) , Karen Hind (Contributing Author) , Lamy Olivier Prof., MD, PhD (Contributing Author) , Elena Gonzalez Rodriguez MD, PhD (Contributing Author) , Lionel Beaugé CTO (Contributing Author) , Didier Hans Prof., MD, PhD Professor (Contributing Author)
{"title":"Evaluation of AI-based spine segmentation (SpS) for the analysis of lumbar spine dual energy X-ray absorptiometry scans","authors":"Guillaume Gatineau Doctorant (Primary Author) , El Hassen Ahmed Lebrahim (Contributing Author Data Scientist) , Karen Hind (Contributing Author) , Lamy Olivier Prof., MD, PhD (Contributing Author) , Elena Gonzalez Rodriguez MD, PhD (Contributing Author) , Lionel Beaugé CTO (Contributing Author) , Didier Hans Prof., MD, PhD Professor (Contributing Author)","doi":"10.1016/j.jocd.2023.101410","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose/Aims</h3><p>The aim of this study was to evaluate a new deep-learning artificial intelligence (AI) -based model for automated SpS. First, we compared bone mineral density (BMD), trabecular bone<span> score (TBS) and bone surface area outcomes across three methods for SpS: 1) the manufacturer default, 2) the clinical DXA expert (criterion) and 3) the new AI-application. Second, we examined longitudinal reproducibility for the measurement of spine surface area.</span></p></div><div><h3>Rationale/Background</h3><p>The antero-posterior (AP) lumbar spine<span> dual energy X-ray absorptiometry (DXA) scan is an important diagnostic measure, used for the assessment of osteoporosis. The quality of the scan is dependent on the accuracy of the vertebral bone mask, derived from bone edge detection and spine segmentation (SpS).</span></p><p>Reducing technical error requires manual validation of the default bone mask for each scan. However, this can be time-consuming in practice.</p></div><div><h3>Methods</h3><p>A sub-sample of 130 women (mean age: 67.1; BMI: 25.2; with no vertebral anomalies) were selected from the OsteoLaus population cohort, having previously received two LS DXA scans (GE Lunar iDXA, encore v 18), 2.5 years apart. Scans were analyzed according to each of the three methods (default, clinical expert and AI), and the primary outcomes (BMD, TBS and surface area) were compared using Student's t-tests and one-way repeated measures-ANOVA. The coefficient of variation (CV%) for bone surface area was also computed.</p></div><div><h3>Results</h3><p>There were significant differences in mean BMD and TBS outcomes derived from the default bone mask method compared to the DXA clinical expert (p=0.01, Table 1). There were no differences in BMD and TBS derived using the AI SpS bone mask method compared to the DXA clinical expert (p=0.67, Table 1).</p><p>Reproducibility for bone surface area was superior for the clinical expert and the AI model compared to the default method (Table 2).</p></div><div><h3>Implications</h3><p>The AI based model demonstrated improved accuracy and reproducibility for lumbar spine bone segmentation compared to the default analysis method, and in close agreement with the clinical criterion. Overall, these results suggest that the new AI-based model for automated SpS may be a valuable tool for reducing time and improving accuracy for the analysis of lumbar spine DXA scans.</p></div>","PeriodicalId":50240,"journal":{"name":"Journal of Clinical Densitometry","volume":"26 3","pages":"Article 101410"},"PeriodicalIF":1.7000,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical Densitometry","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1094695023000604","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose/Aims
The aim of this study was to evaluate a new deep-learning artificial intelligence (AI) -based model for automated SpS. First, we compared bone mineral density (BMD), trabecular bone score (TBS) and bone surface area outcomes across three methods for SpS: 1) the manufacturer default, 2) the clinical DXA expert (criterion) and 3) the new AI-application. Second, we examined longitudinal reproducibility for the measurement of spine surface area.
Rationale/Background
The antero-posterior (AP) lumbar spine dual energy X-ray absorptiometry (DXA) scan is an important diagnostic measure, used for the assessment of osteoporosis. The quality of the scan is dependent on the accuracy of the vertebral bone mask, derived from bone edge detection and spine segmentation (SpS).
Reducing technical error requires manual validation of the default bone mask for each scan. However, this can be time-consuming in practice.
Methods
A sub-sample of 130 women (mean age: 67.1; BMI: 25.2; with no vertebral anomalies) were selected from the OsteoLaus population cohort, having previously received two LS DXA scans (GE Lunar iDXA, encore v 18), 2.5 years apart. Scans were analyzed according to each of the three methods (default, clinical expert and AI), and the primary outcomes (BMD, TBS and surface area) were compared using Student's t-tests and one-way repeated measures-ANOVA. The coefficient of variation (CV%) for bone surface area was also computed.
Results
There were significant differences in mean BMD and TBS outcomes derived from the default bone mask method compared to the DXA clinical expert (p=0.01, Table 1). There were no differences in BMD and TBS derived using the AI SpS bone mask method compared to the DXA clinical expert (p=0.67, Table 1).
Reproducibility for bone surface area was superior for the clinical expert and the AI model compared to the default method (Table 2).
Implications
The AI based model demonstrated improved accuracy and reproducibility for lumbar spine bone segmentation compared to the default analysis method, and in close agreement with the clinical criterion. Overall, these results suggest that the new AI-based model for automated SpS may be a valuable tool for reducing time and improving accuracy for the analysis of lumbar spine DXA scans.
目的/目的本研究的目的是评估一种新的基于深度学习人工智能(AI)的自动化sp模型。首先,我们比较了三种SpS方法的骨矿物质密度(BMD)、骨小梁评分(TBS)和骨表面积结果:1)制造商默认值,2)临床DXA专家(标准)和3)新的人工智能应用。其次,我们检查了脊柱表面积测量的纵向可重复性。理由/背景腰椎前后(AP)双能x线吸收仪(DXA)扫描是评估骨质疏松症的一项重要诊断措施。扫描的质量取决于椎体骨掩膜的准确性,该掩膜来源于骨边缘检测和脊柱分割(SpS)。减少技术错误需要手动验证每次扫描的默认骨掩码。然而,这在实践中可能会很耗时。方法对130名女性(平均年龄67.1岁;体重指数:25.2;从OsteoLaus人群队列中选择,之前接受过两次LS DXA扫描(GE Lunar iDXA, encore v 18),间隔2.5年。根据三种方法(默认、临床专家和人工智能)分析扫描结果,并使用学生t检验和单向重复测量-方差分析比较主要结果(BMD、TBS和表面积)。计算了骨表面积变异系数(CV%)。结果与DXA临床专家相比,默认骨掩膜法获得的平均骨密度和TBS结果存在显著差异(p=0.01,表1)。与DXA临床专家相比,使用AI SpS骨掩膜法获得的骨密度和TBS结果无差异(p=0.67,表1)。与默认方法相比,临床专家和人工智能模型的骨表面积再现性优于默认方法(表2)。意义与默认分析方法相比,基于人工智能的模型显示腰椎骨分割的准确性和再现性更高,并且与临床标准密切一致。总的来说,这些结果表明,新的基于人工智能的自动sp模型可能是减少时间和提高腰椎DXA扫描分析准确性的宝贵工具。
期刊介绍:
The Journal is committed to serving ISCD''s mission - the education of heterogenous physician specialties and technologists who are involved in the clinical assessment of skeletal health. The focus of JCD is bone mass measurement, including epidemiology of bone mass, how drugs and diseases alter bone mass, new techniques and quality assurance in bone mass imaging technologies, and bone mass health/economics.
Combining high quality research and review articles with sound, practice-oriented advice, JCD meets the diverse diagnostic and management needs of radiologists, endocrinologists, nephrologists, rheumatologists, gynecologists, family physicians, internists, and technologists whose patients require diagnostic clinical densitometry for therapeutic management.