基于超微血管成像的可解释深度学习模型用于无创诊断慢性肾脏病间质纤维化
本研究纳入2022年5月至2023年10月期间接受肾活检、二维超声和超微血管成像(SMI)的365例慢性肾脏病患者,按病理间质纤维化(IF)评分分为轻微-轻度组(≤25%)和中重度组(>25%),构建基于SMI的可解释深度学习(XDL)模型,并与超声影像组学模型和彩色多普勒超声(CDUS)模型对照。验证组中DL、超声影像组学和CDUS模型的AUC分别为0.854、0.784和0.745,测试组分别为0.824、0.792和0.752。基于Shapley加性解释(SHAP)的饼图和热图为模型提供了可解释性,显示哪些图像区域有助于诊断IF程度。
要点
- 基于SMI的深度学习模型在验证组和测试组诊断IF程度的AUC分别为0.854和0.824。
- 验证组中DL模型AUC 0.854高于超声影像组学0.784和CDUS 0.745。
- 测试组中DL模型AUC 0.824高于超声影像组学0.792和CDUS 0.752。
核心结论
- 与超声影像组学和CDUS模型相比,基于SMI的深度学习模型在无创判断CKD患者IF程度方面具有更高准确性,基于Shapley的饼图和热图可解释哪些图像区域有助于诊断IF程度。
研究设计与样本
- 研究纳入2022年5月至2023年10月期间接受肾活检、二维超声和SMI检查的365例CKD患者,按病理IF评分分为轻微-轻度IF(≤25%)和中重度IF(>25%)两组,构建基于SMI的可解释深度学习模型,并建立超声影像组学模型和CDUS模型作为对照组,采用ROC曲线和决策曲线分析评估模型效用。
诊断标准与关键数值
- 以病理IF评分≤25%为轻微-轻度IF、>25%为中重度IF;验证组DL、超声影像组学和CDUS模型的AUC分别为0.854、0.784和0.745;测试组DL、超声影像组学和CDUS模型的AUC分别为0.824、0.792和0.752。
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)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: To develop an interpretable deep learning (XDL) model based on superb microvascular imaging (SMI) for the noninvasive diagnosis of the degree of interstitial fibrosis (IF) in chronic kidney disease (CKD).
METHODS: We included CKD patients who underwent renal biopsy, two-dimensional ultrasound, and SMI examinations between May 2022 and October 2023. Based on the pathological IF score, they were divided into two groups: minimal-mild IF (≤25%) and moderate-severe IF (>25%). An XDL model based on the SMI while establishing an ultrasound radiomics model and a color doppler ultrasonography (CDUS) model as the control group. The utility of the proposed model was evaluated using the receiver operating characteristic curve (ROC) and decision curve analysis.
RESULTS: In total, 365 CKD patients were included herein. In the validation group, AUCs of the ROC curves for the DL, ultrasound radiomics, and CDUS models were 0.854, 0.784, and 0.745, respectively. In the test group, AUCs of the ROC curve for the DL ultrasound radiomics, and CDUS models were 0.824, 0.792, and 0.752, respectively. The pie chart and heat map based on Shapley additive explanations (SHAP) provided substantial interpretability for the model.
CONCLUSION: Compared with the ultrasound radiomics and CDUS models, the DL model based on the SMI had higher accuracy in the noninvasive judgment of the degree of IF in CKD patients. Pie and heat maps based on Shapley can explain which image regions are helpful in diagnosing the degree of IF.
引用
- Qin X, Liu X, Xiao W, et al. Interpretable Deep-learning Model Based on Superb Microvascular Imaging for Noninvasive Diagnosis of Interstitial Fibrosis in Chronic Kidney Disease. Acad Radiol. 2024. PMID: 39690075. doi:10.1016/j.acra.2024.11.067
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。