Validation of an Automated Open Source Pipeline for Comprehensive Knee MRI Segmentation and Measurement of Quantitative Outcomes
Motivation: Our motivation was to determine a way to decrease the time dedicated to tissue segmentation and data analysis. Goal(s): Our goal was to test the validity of the DOSMA automated segmentation pipeline for OA analysis. Approach: Building on previous DOSMA frameworks we compared the segmentation metrics and cartilage qualitative metrics associated with OA risk of two manual readers with the automatic reader. Results: The study demonstrated performance of the DOSMA automated pipeline for bone and cartilage segmentation and quantitative analysis of musculoskeletal tissues that was on par or better than inter-reader performance. Impact: Automated segmentation and analysis of bone and cartilage have the potential to greatly improve the translation potential of quantitative MSK MRI biomarkers.
Authors
- Constance R. Chu (ORCID: https://orcid.org/0000-0002-4998-5846)
- Bryan Haddock (ORCID: https://orcid.org/0000-0002-9721-4712)
- Anthony Gatti
- Ananya Goyal (ORCID: https://orcid.org/0000-0002-5023-998X)
- Feliks Kogan (ORCID: https://orcid.org/0000-0003-0580-7308)
- Akshay Sanjay Chaudhari (ORCID: https://orcid.org/0000-0002-3667-6796)
- Ashley A. Williams (ORCID: https://orcid.org/0000-0002-5845-7957)
- Vyoma Sahani (ORCID: https://orcid.org/0000-0001-9904-3956)
- Yael Vainberg (ORCID: https://orcid.org/0000-0002-2954-3143)
- Rune Ploegstra Pedersen
- Francesca Belibi
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2025-09-16
- DOI
- https://doi.org/10.58530/2025/1720
- Primary Topic
- Total Knee Arthroplasty Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00