肾微血管与间质微环境交互的计算病理分析临床意义
研究纳入344例肾小球疾病患者,利用深度学习分割管周毛细血管(PTC)并提取230个空间与形状特征,分析其与间质纤维化/肾小管萎缩(IFTA)微环境的交互。结果显示非IFTA区PTC空间架构及IFTA区PTC形状与疾病进展相关,机器学习风险评分在独立测试集上显著关联疾病进展。
要点
- PTC与IFTA区域存在调节效应,非IFTA区PTC空间架构与肾小球疾病进展显著相关。
- IFTA区PTC形状特征与肾小球疾病进展显著相关。
- 机器学习生成的风险评分在独立测试集上显著关联疾病进展。
核心结论
- 研究揭示了既往未被充分认识的计算病理生物标志物,以及PTC状态与间质微环境复杂交互的临床相关性。
研究设计与样本
- 研究纳入344例肾病综合征研究网络/CureGN参与者,包括112例微小病变、134例局灶节段性肾小球硬化、61例膜性肾病和37例IgA肾病。
- 每例患者一张PAS染色全切片图像被手动分割为皮质、pre-IFTA和成熟IFTA区域,并计算间质分数空间(IFS)。
- 应用深度学习模型分割PTC,从皮质、IFTA和非IFTA亚区提取230个空间与形状PTC病理组学特征。
- 参与者按1:1分为训练集和测试集,采用单变量模型和LASSO回归筛选与疾病进展相关的PTC特征,并构建机器学习模型。
主要发现
- pre+成熟IFTA和IFS中的PTC密度、pre+成熟IFTA中的形状特征以及非IFTA区域的空间架构特征与疾病进展相关。
临床怎么用
- 基于PTC空间架构和形状特征的计算病理分析可用于肾小球疾病进展风险分层。
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
KEY POINTS: There is a modulatory effect between peritubular capillaries (PTCs) and areas of interstitial fibrosis and tubular atrophy (IFTA). The spatial architecture of non-IFTA PTCs on the cortex is significantly associated with glomerular disease progression. The shape of IFTA PTCs on the cortex is significantly associated with glomerular disease progression. BACKGROUND: Interstitial fibrosis and tubular atrophy (IFTA) and density and shape of peritubular capillaries (PTCs) are independently prognostic of disease progression. The aim of this study was to identify novel digital biomarkers of disease progression and assess the clinical relevance of the interplay between a variety of PTC characteristics and their microenvironment in glomerular diseases. METHODS: A total of 344 Nephrotic Syndrome Study Network/CureGN participants were included: 112 with minimal change disease, 134 with focal segmental glomerulosclerosis, 61 with membranous nephropathy, and 37 with IgA nephropathy. A periodic acid-Schiff-stained whole-slide image per patient was manually segmented for cortex, pre-, and mature IFTA. Interstitial fractional space (IFS) was computationally quantified. A deep learning model was applied to segment PTCs. Spatial and shape PTC pathomic features (230) were extracted from the cortex, IFTA, and non-IFTA subregions. Participants were divided into training and testing datasets (1:1). Univariate models incorporating IFTA subregions and IFS-PTC density were constructed. Least absolute shrinkage and selection operator regression models were used to identify the top PTC features associated with disease progression stratified by IFTA and non-IFTA subregions. Machine learning models were built using the top PTC features in IFTA and non-IFTA subregions to prognosticate disease progression. RESULTS: PTC density in pre+mature IFTA and IFS, shape features in pre+mature IFTA, and spatial architecture features in the non-IFTA regions were associated with disease progression. The machine learning-generated risk scores showed a significant association with disease progression on the independent testing set. CONCLUSIONS: We uncovered previously under-recognized digital biomarkers of disease progression and the clinical relevance of the complex interplay between the status of the PTCs and interstitial microenvironment.
引用
- Chen Y, Wang B, Demeke D, et al. Clinical Relevance of Computational Pathology Analysis of Interplay between Kidney Microvasculature and Interstitial Microenvironment. Clin J Am Soc Nephrol. 2024. PMID: 39714939. doi:10.2215/CJN.0000000597
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。