Scholarlink

Introduction <p>Prediction of cartilage structural properties through MRI could allow earlier detection of joint pathologies, such as osteoarthritis.</p> Materials &amp; Methods <p>Bovine patellar cartilage samples (<i>n</i> = 12) were imaged using magnetic resonance fingerprinting, followed by histological examination of proteoglycan content and collagen fiber anisotropy. The relaxation time maps and raw signal data were then used for training Gaussian process regression (GPR) models to predict the histology results.</p> Results <p>Proteoglycan content was predicted by the GPR models with high accuracy (median <i>r</i> = 0.81, <i>σ</i> = 0.08 and NRMSE = 11.7%). Predictions performed using raw MRF data outperformed those done using qMRI maps. Collagen fiber anisotropy predictions found only weak correlation (median <i>r</i> = 0.40, <i>σ</i> = 0.25 &amp; NRMSE = 26.4%) and no significant difference was seen between models trained on raw MRF or relaxation time maps.</p> Discussion <p>These findings indicate that noninvasive prediction of proteoglycan content in cartilage from MRF measurements using a 3&#xa0;T clinical scanner is feasible, holding promise for future clinical applications. Collagen fiber anisotropy could not be reliably estimated with the current setup. GPR-based prediction models were found to outperform reference linear models using the same prediction data.</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

Machine learning assisted prediction of cartilage histology using MR fingerprinting – a preliminary study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月4日

查看全文
  • Ville Kantola,
  • Olli Nykänen,
  • Victor Casula,
  • Ville-Pauli Karjalainen,
  • Martijn A. Cloos,
  • Riccardo Lattanzi,
  • Mikko J. Nissi,
  • Miika T. Nieminen

摘要

Introduction

Prediction of cartilage structural properties through MRI could allow earlier detection of joint pathologies, such as osteoarthritis.

Materials & Methods

Bovine patellar cartilage samples (n = 12) were imaged using magnetic resonance fingerprinting, followed by histological examination of proteoglycan content and collagen fiber anisotropy. The relaxation time maps and raw signal data were then used for training Gaussian process regression (GPR) models to predict the histology results.

Results

Proteoglycan content was predicted by the GPR models with high accuracy (median r = 0.81, σ = 0.08 and NRMSE = 11.7%). Predictions performed using raw MRF data outperformed those done using qMRI maps. Collagen fiber anisotropy predictions found only weak correlation (median r = 0.40, σ = 0.25 & NRMSE = 26.4%) and no significant difference was seen between models trained on raw MRF or relaxation time maps.

Discussion

These findings indicate that noninvasive prediction of proteoglycan content in cartilage from MRF measurements using a 3 T clinical scanner is feasible, holding promise for future clinical applications. Collagen fiber anisotropy could not be reliably estimated with the current setup. GPR-based prediction models were found to outperform reference linear models using the same prediction data.