Scholarlink

Purpose <p>To identify MRCP-derived radiomics features associated with image-defined biliary dilation, evaluate their independence from demographic confounders, and assess diagnostic classification performance, including in borderline-caliber cases.</p> Methods <p>In this retrospective cross-sectional study, 135 patients (dilated: <i>n</i> = 60; non-dilated: <i>n</i> = 75) who underwent clinically indicated MRCP (September 2025-January 2026) were included. Two blinded radiologists independently classified biliary dilation (Cohen’s kappa = 0.87). Three-dimensional CBD segmentation was performed in 3D Slicer (v5.10.0), with feature extraction using PyRadiomics in compliance with IBSI guidelines. Feature reduction applied sequential reproducibility filtering (ICC (2,1) ≥ 0.80), low-variance filtering, Spearman correlation filtering (|r| &gt; 0.90), Benjamini–Hochberg FDR correction (q &lt; 0.05), and Cliff’s delta thresholding (|δ| &gt; 0.5). Multivariable linear regression adjusted for age, sex, and post-cholecystectomy status. Shape features were excluded from classification analyses to avoid incorporation bias. Three classifiers (Random Forest, Logistic Regression, and Naïve Bayes) were trained on the seven Bonferroni-confirmed texture features using five-fold stratified cross-validation. A post hoc exploratory analysis in borderline CBD caliber (6–10&#xa0;mm; <i>n</i> = 45) used a two-feature model with internal tenfold cross-validation.</p> Results <p>Twelve features met selection thresholds: four shape and eight texture features. The strongest discriminators were RunLengthNonUniformity (δ = 0.870; q = 1.09 × 10<sup>−16</sup>) and GrayLevelNonUniformity (δ = 0.861; q = 1.43 × 10<sup>−16</sup>). Multivariable regression demonstrated that 11 of 12 features were significant independent correlates of image-defined biliary dilation after Bonferroni correction (all <i>p</i> &lt; 0.001). In the full cohort (<i>n</i> = 135; seven texture features), Random Forest achieved AUC = 0.963, accuracy = 92.1%, sensitivity = 94.3%, and specificity = 89.5%. In the exploratory borderline subgroup (<i>n</i> = 45; 6–10&#xa0;mm; two-feature model), Random Forest achieved AUC = 0.832, suggesting potential discriminatory utility in equivocal cases.</p> Conclusion <p>MRCP-derived radiomic features are associated with image-defined CBD dilation and show exploratory internal cross-validated diagnostic performance, including in borderline cases, using standard clinical acquisitions. Prospective multicenter validation with independent clinical reference standards is required before clinical implementation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MRCP-derived radiomics features associated with biliary dilation: a multi-step feature reduction, multivariable regression, and diagnostic classification study

  • 期刊论文

  • 发表日期：

    2026年5月15日

查看全文
  • Alok Verma,
  • Naresh Kumar Mangalhara,
  • Shashank Sharma,
  • Naman Gupta,
  • Ayush Khandelwal,
  • Meenu Bagarhatta

摘要

Purpose

To identify MRCP-derived radiomics features associated with image-defined biliary dilation, evaluate their independence from demographic confounders, and assess diagnostic classification performance, including in borderline-caliber cases.

Methods

In this retrospective cross-sectional study, 135 patients (dilated: n = 60; non-dilated: n = 75) who underwent clinically indicated MRCP (September 2025-January 2026) were included. Two blinded radiologists independently classified biliary dilation (Cohen’s kappa = 0.87). Three-dimensional CBD segmentation was performed in 3D Slicer (v5.10.0), with feature extraction using PyRadiomics in compliance with IBSI guidelines. Feature reduction applied sequential reproducibility filtering (ICC (2,1) ≥ 0.80), low-variance filtering, Spearman correlation filtering (|r| > 0.90), Benjamini–Hochberg FDR correction (q < 0.05), and Cliff’s delta thresholding (|δ| > 0.5). Multivariable linear regression adjusted for age, sex, and post-cholecystectomy status. Shape features were excluded from classification analyses to avoid incorporation bias. Three classifiers (Random Forest, Logistic Regression, and Naïve Bayes) were trained on the seven Bonferroni-confirmed texture features using five-fold stratified cross-validation. A post hoc exploratory analysis in borderline CBD caliber (6–10 mm; n = 45) used a two-feature model with internal tenfold cross-validation.

Results

Twelve features met selection thresholds: four shape and eight texture features. The strongest discriminators were RunLengthNonUniformity (δ = 0.870; q = 1.09 × 10−16) and GrayLevelNonUniformity (δ = 0.861; q = 1.43 × 10−16). Multivariable regression demonstrated that 11 of 12 features were significant independent correlates of image-defined biliary dilation after Bonferroni correction (all p < 0.001). In the full cohort (n = 135; seven texture features), Random Forest achieved AUC = 0.963, accuracy = 92.1%, sensitivity = 94.3%, and specificity = 89.5%. In the exploratory borderline subgroup (n = 45; 6–10 mm; two-feature model), Random Forest achieved AUC = 0.832, suggesting potential discriminatory utility in equivocal cases.

Conclusion

MRCP-derived radiomic features are associated with image-defined CBD dilation and show exploratory internal cross-validated diagnostic performance, including in borderline cases, using standard clinical acquisitions. Prospective multicenter validation with independent clinical reference standards is required before clinical implementation.