Scholarlink

Objective <p>Liver stiffness measurement is important for assessing chronic liver disease (CLD). MR elastography (MRE) requires specialized hardware and expertise. Non-invasive deep learning (DL) models using multiparametric abdominal MRI may provide an accessible alternative. We sought to develop and validate a DL model for predicting continuous liver shear stiffness from non-contrast multiparametric abdominal MRI and electronic health record (EHR) data across multiple sites and vendors.</p> Materials and methods <p>This was a retrospective, multi-institutional study. We analyzed 3680 abdominal MRI examinations from 3376 patients with confirmed or suspected CLD. Non-contrast T1-weighted (T1w), T2-weighted (T2w), and diffusion-weighted imaging (DWI) with EHR data were used as inputs. MRE-derived liver shear stiffness served as the reference. A transformer-based multi-channel DL model was trained using multi-site 10-fold cross-validation and evaluated on temporally held-out internal (<i>n</i> = 1224) and independent external (<i>n</i> = 365) test sets. Performance was measured by Pearson’s correlation coefficient (r); residual analysis assessed bias.</p> Results <p>In cross-validation, the model achieved an r of 0.78 (95% CI: 0.75, 0.80). On the internal test set, r was 0.77 (95% CI: 0.73, 0.80), and on the external set, r was 0.76 (95% CI: 0.69, 0.83). The model showed no significant bias based on age, sex, or BMI (<i>p</i> &gt; 0.05). In patients with and without steatotic liver disease, r was 0.74 and 0.76, respectively.</p> Conclusion <p>Our transformer-based multi-channel model predicts continuous liver shear stiffness from routinely acquired multiparametric MRI and EHR data with moderate correlation to MRE, representing a potential step toward accessible, non-invasive liver stiffness estimation.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis><i> Can routinely acquired multiparametric abdominal MRI and electronic health record data predict liver stiffness across multiple sites and scanner vendors using a deep learning approach?</i></p> <p><Emphasis Type="BoldItalic">Findings</Emphasis><i> The optimized deep learning model predicted liver stiffness with r = 0.78 in cross-validation and r = 0.76 in external validation using multiparametric MRI and electronic health record data</i>.</p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis><i> This study introduces a preliminary yet robust AI method to estimate liver stiffness from routine multiparametric MRI and EHR data, offering a scalable fibrosis assessment approach suitable for opportunistic evaluation and as a complementary tool when MRE is unavailable</i>.</p> Graphical Abstract <p></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

Development and validation of a deep learning model for liver shear stiffness regression using abdominal multiparametric MRI across multiple sites and vendors

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月13日

查看全文
  • Redha Ali,
  • Hailong Li,
  • Scott B. Reeder,
  • David Harris,
  • William Masch,
  • Anum Aslam,
  • Krishna P. Shanbhogue,
  • Nehal A. Parikh,
  • Lili He,
  • Jonathan R. Dillman

摘要

Objective

Liver stiffness measurement is important for assessing chronic liver disease (CLD). MR elastography (MRE) requires specialized hardware and expertise. Non-invasive deep learning (DL) models using multiparametric abdominal MRI may provide an accessible alternative. We sought to develop and validate a DL model for predicting continuous liver shear stiffness from non-contrast multiparametric abdominal MRI and electronic health record (EHR) data across multiple sites and vendors.

Materials and methods

This was a retrospective, multi-institutional study. We analyzed 3680 abdominal MRI examinations from 3376 patients with confirmed or suspected CLD. Non-contrast T1-weighted (T1w), T2-weighted (T2w), and diffusion-weighted imaging (DWI) with EHR data were used as inputs. MRE-derived liver shear stiffness served as the reference. A transformer-based multi-channel DL model was trained using multi-site 10-fold cross-validation and evaluated on temporally held-out internal (n = 1224) and independent external (n = 365) test sets. Performance was measured by Pearson’s correlation coefficient (r); residual analysis assessed bias.

Results

In cross-validation, the model achieved an r of 0.78 (95% CI: 0.75, 0.80). On the internal test set, r was 0.77 (95% CI: 0.73, 0.80), and on the external set, r was 0.76 (95% CI: 0.69, 0.83). The model showed no significant bias based on age, sex, or BMI (p > 0.05). In patients with and without steatotic liver disease, r was 0.74 and 0.76, respectively.

Conclusion

Our transformer-based multi-channel model predicts continuous liver shear stiffness from routinely acquired multiparametric MRI and EHR data with moderate correlation to MRE, representing a potential step toward accessible, non-invasive liver stiffness estimation.

Key Points

Question Can routinely acquired multiparametric abdominal MRI and electronic health record data predict liver stiffness across multiple sites and scanner vendors using a deep learning approach?

Findings The optimized deep learning model predicted liver stiffness with r = 0.78 in cross-validation and r = 0.76 in external validation using multiparametric MRI and electronic health record data.

Clinical relevance This study introduces a preliminary yet robust AI method to estimate liver stiffness from routine multiparametric MRI and EHR data, offering a scalable fibrosis assessment approach suitable for opportunistic evaluation and as a complementary tool when MRE is unavailable.

Graphical Abstract