先进神经网络用于分类银屑病关节炎、血清阴性及血清阳性类风湿关节炎的MRI
本研究利用ResNet神经网络,基于649例患者的手部MRI数据,评估其区分血清阳性RA、血清阴性RA与PsA的能力。结果显示,各对比的AUROC分别为75%、74%和67%,所有MRI序列均有分类价值,去除增强序列后性能仅轻微下降;加入人口学与临床参数未显著提升分类效果。银屑病患者多被归类为PsA,提示银屑病早期可能存在类PsA的MRI模式。
要点
- 神经网络可区分血清阳性RA、血清阴性RA与PsA的手部MRI炎症模式,AUROC为67%–75%。
- 去除基于对比剂的序列后分类性能仅轻微下降,加入人口学与临床数据未显著改善分类。
- 无临床关节炎的银屑病患者多被神经网络归类为PsA,提示早期即可出现类PsA的MRI模式。
核心结论
- 神经网络可成功训练用于区分血清阳性RA、血清阴性RA与PsA相关的MRI炎症。
研究设计与样本
- 利用ResNet神经网络,对649例患者(135例血清阴性RA、190例血清阳性RA、177例PsA、147例银屑病)的手部MRI数据进行分类比较。
- 比较血清阳性RA vs PsA、血清阴性RA vs PsA、血清阳性 vs 血清阴性RA,使用T1冠状位、T2冠状位、T1冠状位及轴位脂肪抑制增强序列、T2脂肪抑制轴位序列。
- 以受试者工作特征曲线下面积(AUROC)分析网络性能,分别在有和无人口学及临床参数呈现时评估。
主要发现
- AUROC:血清阳性RA vs PsA为75%,血清阴性RA vs PsA为74%,血清阳性 vs 血清阴性RA为67%。
- 所有MRI序列均与分类相关,但删除基于对比剂的序列后性能仅轻微下降。
- 加入人口学与临床数据未对分类提供显著改善。
- 银屑病患者多被神经网络归类为PsA,提示银屑病病程早期可能存在类PsA的MRI模式。
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 neural networks can distinguish between seropositive RA, seronegative RA, and PsA based on inflammatory patterns from hand MRIs and to test how psoriasis patients with subclinical inflammation fit into such patterns. METHODS: ResNet neural networks were utilized to compare seropositive RA vs PsA, seronegative RA vs PsA, and seropositive vs seronegative RA with respect to hand MRI data. Results from T1 coronal, T2 coronal, T1 coronal and axial fat-suppressed contrast-enhanced (CE), and T2 fat-suppressed axial sequences were used. The performance of such trained networks was analysed by the area under the receiver operating characteristics curve (AUROC) with and without presentation of demographic and clinical parameters. Additionally, the trained networks were applied to psoriasis patients without clinical arthritis. RESULTS: MRI scans from 649 patients (135 seronegative RA, 190 seropositive RA, 177 PsA, 147 psoriasis) were fed into ResNet neural networks. The AUROC was 75% for seropositive RA vs PsA, 74% for seronegative RA vs PsA, and 67% for seropositive vs seronegative RA. All MRI sequences were relevant for classification, however, when deleting contrast agent-based sequences the loss of performance was only marginal. The addition of demographic and clinical data to the networks did not provide significant improvements for classification. Psoriasis patients were mostly assigned to PsA by the neural networks, suggesting that a PsA-like MRI pattern may be present early in the course of psoriatic disease. CONCLUSION: Neural networks can be successfully trained to distinguish MRI inflammation related to seropositive RA, seronegative RA, and PsA.
引用
- Folle L, Bayat S, Kleyer A, et al. Advanced neural networks for classification of MRI in psoriatic arthritis, seronegative, and seropositive rheumatoid arthritis. Rheumatology (Oxford). 2022. PMID: 35333316. doi:10.1093/rheumatology/keac197
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。