Scholarlink

Objectives <p>To develop a deep learning-based multimodal framework for automated segmentation of orbital soft tissues and identify quantitative imaging biomarkers for precise grading of thyroid eye disease (TED).</p> Materials and methods <p>This retrospective multicenter study enrolled 330 TED patients from a primary center for model development and 113 patients from two external centers for validation. From the primary cohort, 182 mild and 138 moderate-to-severe TED were subsequently selected for further analysis. All subjects underwent 3 T MRI with water-fat separation and fat-suppressed (FS) T2 mapping sequences. TED-Net, a deep learning model integrating ConvNeXt and Transformer architectures, was developed to segment orbital structures including the extraocular muscles, lacrimal gland, orbital fat, and eyeball. The model automatically extracted both morphological parameters (volume and volume ratio) and functional parameters (water fraction, fat fraction, and FS T2 relaxation time), enabling quantitative comparison between mild and moderate-to-severe TED. Diagnostic performance for evaluating orbital involvement was assessed using receiver operating characteristic analysis and decision curve analysis.</p> Results <p>TED-Net achieved Dice similarity coefficients &gt; 0.80 across all orbital structures. Volumetric measurements showed high consistency among different sequences (intraclass correlation coefficient = 0.843). Significant differences in morphological and functional parameters were observed between mild and moderate-to-severe TED (all <i>p</i> &lt; 0.05). The combined volumetric-functional model demonstrated superior diagnostic accuracy (area under the curve [AUC] = 0.982) over the volumetric model (AUC = 0.908).</p> Conclusions <p>TED-Net enables accurate automated segmentation and multiparametric quantification of orbital soft tissues, providing reliable imaging biomarkers for objective assessment of TED severity.</p> Key Points <p><Emphasis Type="BoldItalic">Question</Emphasis> <i>MRI-based quantitative metrics are essential for assessing orbital involvement in TED, but effective tools for rapid and accurate parameter extraction are currently lacking</i>.</p> <p><Emphasis Type="BoldItalic">Findings</Emphasis> <i>TED-Net achieved precise orbital segmentation and multiparametric quantification; the integration of volumetric and functional parameters yielded an AUC of 0.982 for evaluating orbital involvement</i>.</p> <p><Emphasis Type="BoldItalic">Clinical relevance</Emphasis> <i>The proposed TED-Net provides a reliable approach for quantifying orbital soft tissue involvement, and its clinical implementation enables more accurate assessment of TED severity</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

MRI-based automated segmentation and multiparametric quantification for assessing orbital soft tissue involvement in thyroid eye disease

  • 期刊论文

  • 发表日期：

    2026年5月6日

查看全文
  • Linhan Zhai,
  • Yan Zeng,
  • Yu Chen,
  • Yangyang Yin,
  • Huan Liu,
  • Lihui Dai,
  • Haoyue Shao,
  • Baoyi Wang,
  • Qiuxia Wang,
  • Lian Yang,
  • Feng Li,
  • Gang Yuan,
  • Lei Chen,
  • Jing Zhang

摘要

Objectives

To develop a deep learning-based multimodal framework for automated segmentation of orbital soft tissues and identify quantitative imaging biomarkers for precise grading of thyroid eye disease (TED).

Materials and methods

This retrospective multicenter study enrolled 330 TED patients from a primary center for model development and 113 patients from two external centers for validation. From the primary cohort, 182 mild and 138 moderate-to-severe TED were subsequently selected for further analysis. All subjects underwent 3 T MRI with water-fat separation and fat-suppressed (FS) T2 mapping sequences. TED-Net, a deep learning model integrating ConvNeXt and Transformer architectures, was developed to segment orbital structures including the extraocular muscles, lacrimal gland, orbital fat, and eyeball. The model automatically extracted both morphological parameters (volume and volume ratio) and functional parameters (water fraction, fat fraction, and FS T2 relaxation time), enabling quantitative comparison between mild and moderate-to-severe TED. Diagnostic performance for evaluating orbital involvement was assessed using receiver operating characteristic analysis and decision curve analysis.

Results

TED-Net achieved Dice similarity coefficients > 0.80 across all orbital structures. Volumetric measurements showed high consistency among different sequences (intraclass correlation coefficient = 0.843). Significant differences in morphological and functional parameters were observed between mild and moderate-to-severe TED (all p < 0.05). The combined volumetric-functional model demonstrated superior diagnostic accuracy (area under the curve [AUC] = 0.982) over the volumetric model (AUC = 0.908).

Conclusions

TED-Net enables accurate automated segmentation and multiparametric quantification of orbital soft tissues, providing reliable imaging biomarkers for objective assessment of TED severity.

Key Points

Question MRI-based quantitative metrics are essential for assessing orbital involvement in TED, but effective tools for rapid and accurate parameter extraction are currently lacking.

Findings TED-Net achieved precise orbital segmentation and multiparametric quantification; the integration of volumetric and functional parameters yielded an AUC of 0.982 for evaluating orbital involvement.

Clinical relevance The proposed TED-Net provides a reliable approach for quantifying orbital soft tissue involvement, and its clinical implementation enables more accurate assessment of TED severity.

Graphical Abstract