Scholarlink

Purpose <p>The tongue is a critical soft tissue of the upper airway; excessive enlargement can narrow or collapse the airway, contributing to obstructive sleep apnea (OSA). To our knowledge, no existing methods quantify OSA-related tongue geometric features using deep learning segmentation. We present a deep learning model (TOSA-Net) capable of accurately segmenting and measuring tongue geometry, offering a more efficient approach for future OSA tongue research.</p> Materials and Methods <p>A dataset (n = 207) of front and profile tongue images, along with manually segmented and quantified tongue dimensions, was used for model development and evaluation. We modified a U-Net architecture using multi-scale convolution filters for feature extraction. Automated segmentations were used to calculate tongue geometric features. Dice coefficient, Pearson correlation, agreement analyses, and expert-derived clinical parameters assessed segmentation and measurement accuracy between deep learning and manual methods.</p> Results <p>Five-fold cross-validation yielded a mean Dice coefficient of 0.870 across all subjects, with the highest mean Dice (0.914) in OSA patients. Tongue features (area, length, thickness, curvature) showed strong correlation with manual measurements, with no statistically significant differences <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\((\text {p} &lt; 0.05\)</EquationSource> </InlineEquation>).</p> Conclusion <p>The high accuracy of automated segmentation and measurement indicates the proposed method’s potential to replace time-consuming manual tasks in clinical and large-scale OSA research.</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

Automatic segmentation and measurement of tongue geometric features using TOSA-Net for obstructive sleep apnoea

  • 期刊论文

  • 发表日期：

    2025年11月12日

查看全文
  • Yingjie Li,
  • Qiang Cai,
  • Shuai He,
  • Yanzhao Ren,
  • Huanpu Yin

摘要

Purpose

The tongue is a critical soft tissue of the upper airway; excessive enlargement can narrow or collapse the airway, contributing to obstructive sleep apnea (OSA). To our knowledge, no existing methods quantify OSA-related tongue geometric features using deep learning segmentation. We present a deep learning model (TOSA-Net) capable of accurately segmenting and measuring tongue geometry, offering a more efficient approach for future OSA tongue research.

Materials and Methods

A dataset (n = 207) of front and profile tongue images, along with manually segmented and quantified tongue dimensions, was used for model development and evaluation. We modified a U-Net architecture using multi-scale convolution filters for feature extraction. Automated segmentations were used to calculate tongue geometric features. Dice coefficient, Pearson correlation, agreement analyses, and expert-derived clinical parameters assessed segmentation and measurement accuracy between deep learning and manual methods.

Results

Five-fold cross-validation yielded a mean Dice coefficient of 0.870 across all subjects, with the highest mean Dice (0.914) in OSA patients. Tongue features (area, length, thickness, curvature) showed strong correlation with manual measurements, with no statistically significant differences \((\text {p} < 0.05\) ).

Conclusion

The high accuracy of automated segmentation and measurement indicates the proposed method’s potential to replace time-consuming manual tasks in clinical and large-scale OSA research.