深度学习在双能CT中提升痛风诊断:晶体与伪影鉴别的回顾性分析
本研究回顾性分析47例痛风患者和27例无痛风对照者的双能CT绿色焦点,提取18704个感兴趣区并按大小分组,用卷积神经网络按病灶、支持向量机按患者区分痛风石绿色编码与团块状伪影;小、中、大感兴趣区准确率分别为88.5%、88.6%、91.0%,按患者分析灵敏度87.2%、特异度100%、准确率91.8%。
要点
- 卷积神经网络区分小、中、大感兴趣区绿色编码与伪影的准确率分别为88.5%、88.6%、91.0%。
- 按患者分析的支持向量机鉴别痛风与无痛风对照的灵敏度87.2%、特异度100%、准确率91.8%。
- 深度学习用于双能CT痛风诊断可实现精准病灶分类,有助于早期诊断和及时干预。
核心结论
- 深度学习算法能有效区分双能CT扫描中提示晶体沉积的绿色编码与团块状伪影。
- 深度学习用于双能CT诊断痛风具有高灵敏度、特异度和准确率,可实现精准病灶分类,有助于早期诊断和促进及时干预。
研究设计与样本
- 回顾性分析47例痛风患者和27例无痛风对照者双能CT扫描绿色焦点中提取的18704个感兴趣区。
- 感兴趣区按大小分为小、中、大三组,行基于病灶的卷积神经网络分析和基于患者的支持向量机分析。
- 比较各模型的受试者工作特征曲线下面积、灵敏度、特异度、阳性预测值和阴性预测值。
主要发现
- 小感兴趣区卷积神经网络模型的灵敏度和特异度分别为81.5%和96.1%。
- 中感兴趣区卷积神经网络模型的灵敏度和特异度分别为82.7%和96.1%。
- 大感兴趣区卷积神经网络模型的灵敏度和特异度分别为91.8%和86.9%。
- 深度学习算法对小、中、大感兴趣区的准确率分别为88.5%、88.6%和91.0%。
- 按患者分析中,支持向量机区分痛风患者与无痛风对照的灵敏度87.2%、特异度100%、准确率91.8%。
临床怎么用
- 原文结论认为深度学习用于双能CT诊断痛风可实现精准病灶分类,有助于早期诊断和促进及时干预。
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)。
原文
OBJECTIVES: To evaluate whether the application of deep learning (DL) could achieve high diagnostic accuracy in differentiating between green colour coding, indicative of tophi, and clumpy artefacts observed in dual-energy computed tomography (DECT) scans. METHODS: A comprehensive analysis of 18,704 regions of interest (ROIs) extracted from green foci in DECT scans obtained from 47 patients with gout and 27 gout-free controls was performed. The ROIs were categorized into three size groups: small, medium, and large. Convolutional neural network (CNN) analysis on a per-lesion basis and support vector machine (SVM) analysis on a per-patient basis were performed. The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value of the models were compared. RESULTS: For small ROIs, the sensitivity and specificity of the CNN model were 81.5% and 96.1%, respectively; for medium ROIs, 82.7% and 96.1%, respectively; for large ROIs, 91.8% and 86.9%, respectively. Additionally, the DL algorithm exhibited accuracies of 88.5%, 88.6%, and 91.0% for small, medium, and large ROIs, respectively. In the per-patient analysis, the SVM approach demonstrated a sensitivity of 87.2%, a specificity of 100%, and an accuracy of 91.8% in distinguishing between patients with gout and gout-free controls. CONCLUSION: Our study demonstrates the effectiveness of the DL algorithm in differentiating between green colour coding indicative of crystal deposition and clumpy artefacts in DECT scans. With high sensitivity, specificity, and accuracy, the utilization of DL in DECT for diagnosing gout enables precise lesion classification, facilitating early-stage diagnosis and promoting timely intervention approaches.
引用
- Choi Y, Castro-Zunti R, Yun JS, et al. Enhancing diagnosis of gout with deep learning in dual-energy computed tomography: a retrospective analysis of crystal and artefact differentiation. Rheumatology (Oxford). 2025. PMID: 39565918. doi:10.1093/rheumatology/keae523
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。