Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quantifying Knee Cartilage Shape and Lesion: From Image to Metrics

Yongcheng Yao, Weitian Chen

TL;DR

A deep-learning-based medical image analysis application for knee cartilage morphometrics, CartiMorph Toolbox (CMT), and a 2-stage joint template learning and registration network, CMT-reg, which demonstrated competitive results compared to other state-of-the-art models.

Abstract

Imaging features of knee articular cartilage have been shown to be potential imaging biomarkers for knee osteoarthritis. Despite recent methodological advancements in image analysis techniques like image segmentation, registration, and domain-specific image computing algorithms, only a few works focus on building fully automated pipelines for imaging feature extraction. In this study, we developed a deep-learning-based medical image analysis application for knee cartilage morphometrics, CartiMorph Toolbox (CMT). We proposed a 2-stage joint template learning and registration network, CMT-reg. We trained the model using the OAI-ZIB dataset and assessed its performance in template-to-image registration. The CMT-reg demonstrated competitive results compared to other state-of-the-art models. We integrated the proposed model into an automated pipeline for the quantification of cartilage shape and lesion (full-thickness cartilage loss, specifically). The toolbox provides a comprehensive, user-friendly solution for medical image analysis and data visualization. The software and models are available at https://github.com/YongchengYAO/CMT-AMAI24paper .

Quantifying Knee Cartilage Shape and Lesion: From Image to Metrics

TL;DR

A deep-learning-based medical image analysis application for knee cartilage morphometrics, CartiMorph Toolbox (CMT), and a 2-stage joint template learning and registration network, CMT-reg, which demonstrated competitive results compared to other state-of-the-art models.

Abstract

Imaging features of knee articular cartilage have been shown to be potential imaging biomarkers for knee osteoarthritis. Despite recent methodological advancements in image analysis techniques like image segmentation, registration, and domain-specific image computing algorithms, only a few works focus on building fully automated pipelines for imaging feature extraction. In this study, we developed a deep-learning-based medical image analysis application for knee cartilage morphometrics, CartiMorph Toolbox (CMT). We proposed a 2-stage joint template learning and registration network, CMT-reg. We trained the model using the OAI-ZIB dataset and assessed its performance in template-to-image registration. The CMT-reg demonstrated competitive results compared to other state-of-the-art models. We integrated the proposed model into an automated pipeline for the quantification of cartilage shape and lesion (full-thickness cartilage loss, specifically). The toolbox provides a comprehensive, user-friendly solution for medical image analysis and data visualization. The software and models are available at https://github.com/YongchengYAO/CMT-AMAI24paper .
Paper Structure (13 sections, 2 equations, 5 figures, 3 tables)

This paper contains 13 sections, 2 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methods
  4. Toolbox Overview
  5. DL Models
  6. Joint Template Learning and Registration Model
  7. Experiments & Results
  8. Registration Model Evaluation
  9. Data
  10. Results & Discussion
  11. Conclusion
  12. Acknowledgments.
  13. Disclosure of Interests.

Figures (5)

  • Figure 1: Structure of CartiMorph Toolbox (CMT).
  • Figure 2: Deep learning models and quantification algorithms in CMT.
  • Figure 3: The proposed joint template learning and registration model, CMT-reg.
  • Figure 4: Learned template images from variants of Aladdin and the proposed model, CMT-reg. Numbers in the upper left corner are indices of sagittal slices.
  • Figure 5: Examples of data visualization in CartiMorph Viewer (CMV)