Scholarlink

Purpose <p>In clinics, musculoskeletal assessment mainly relies on conventional imaging which is expensive, involves radiation exposure, and lacks accessibility. Inferring skeletal morphology from 3D body surface scans shows potential as an alternative screening aid, although lacks detail in particular at extremities. This study leverages Statistical Shape Models (SSMs) to estimate position and orientation of the hand and foot bones from the skin surface.</p> Methods <p>Two datasets (140 feet, 79 hands with diverse morphologies and poses) were collected. For each dataset, a coupled skin-bone SSM was created. A nested cross-validation approach was used to optimize hyperparameters and prevent overfitting while fitting the isolated skin model of the coupled SSM to unseen skin data to infer bone structure and position.</p> Results <p>For the feet, the mean absolute error (MAE) was 1.68&#xa0;mm, with the highest errors occurring at the hindfoot. Similarly, for the hands, the MAE reached 1.37&#xa0;mm, with the largest deviations observed at carpal bones.</p> Conclusion <p>This study demonstrates the feasibility of predicting bone morphology from skin surfaces using SSM-based shape completion, offering a potential non-invasive and accessible alternative to traditional imaging for musculoskeletal assessments.</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

From Skin to Skeleton: A Statistical Shape Modelling Approach for Predicting Hand and Foot Bony Geometry

  • 期刊论文

  • 发表日期：

    2025年10月30日

查看全文
  • Kate Duquesne,
  • Adris Molnar,
  • Roel Huysentruyt,
  • Aline Van Oevelen,
  • Jing Li,
  • Jan Sijbers,
  • Wim Van Paepegem,
  • Emmanuel Audenaert

摘要

Purpose

In clinics, musculoskeletal assessment mainly relies on conventional imaging which is expensive, involves radiation exposure, and lacks accessibility. Inferring skeletal morphology from 3D body surface scans shows potential as an alternative screening aid, although lacks detail in particular at extremities. This study leverages Statistical Shape Models (SSMs) to estimate position and orientation of the hand and foot bones from the skin surface.

Methods

Two datasets (140 feet, 79 hands with diverse morphologies and poses) were collected. For each dataset, a coupled skin-bone SSM was created. A nested cross-validation approach was used to optimize hyperparameters and prevent overfitting while fitting the isolated skin model of the coupled SSM to unseen skin data to infer bone structure and position.

Results

For the feet, the mean absolute error (MAE) was 1.68 mm, with the highest errors occurring at the hindfoot. Similarly, for the hands, the MAE reached 1.37 mm, with the largest deviations observed at carpal bones.

Conclusion

This study demonstrates the feasibility of predicting bone morphology from skin surfaces using SSM-based shape completion, offering a potential non-invasive and accessible alternative to traditional imaging for musculoskeletal assessments.