Objective: We evaluated a fully automated femoral cartilage segmentation model for measuring T2 relaxation values and longitudinal changes using multi-echo spin-echo (MESE) magnetic resonance imaging (MRI). We open sourced this model and developed a web app available at https://kl.stanford.edu into which users can drag and drop images to segment them automatically.

Design: We trained a neural network to segment femoral cartilage from MESE MRIs. Cartilage was divided into 12 subregions along medial-lateral, superficial-deep, and anterior-central-posterior boundaries. Subregional T2 values and four-year changes were calculated using a radiologist's segmentations (Reader 1) and the model's segmentations. These were compared using 28 held-out images. A subset of 14 images were also evaluated by a second expert (Reader 2) for comparison.

Results: Model segmentations agreed with Reader 1 segmentations with a Dice score of 0.85 ± 0.03. The model's estimated T2 values for individual subregions agreed with those of Reader 1 with an average Spearman correlation of 0.89 and average mean absolute error (MAE) of 1.34 ms. The model's estimated four-year change in T2 for individual subregions agreed with Reader 1 with an average correlation of 0.80 and average MAE of 1.72 ms. The model agreed with Reader 1 at least as closely as Reader 2 agreed with Reader 1 in terms of Dice score (0.85 vs. 0.75) and subregional T2 values.

Conclusions: Assessments of cartilage health using our fully automated segmentation model agreed with those of an expert as closely as experts agreed with one another. This has the potential to accelerate osteoarthritis research.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8808775PMC
http://dx.doi.org/10.1177/19476035211042406DOI Listing

Publication Analysis

Top Keywords

agreed reader
20
fully automated
8
femoral cartilage
8
segmentation model
8
reader
8
dice score
8
score 085
8
model's estimated
8
individual subregions
8
subregions agreed
8

Similar Publications

Deep learning algorithm enables automated Cobb angle measurements with high accuracy.

Skeletal Radiol

December 2024

Department of Radiology, Chobanian and Avedisian School of Medicine, Boston University, Boston, MA, USA.

Objective: To determine the accuracy of automatic Cobb angle measurements by deep learning (DL) on full spine radiographs.

Materials And Methods: Full spine radiographs of patients aged > 2 years were screened using the radiology reports to identify radiographs for performing Cobb angle measurements. Two senior musculoskeletal radiologists and one senior orthopedic surgeon independently annotated Cobb angles exceeding 7° indicating the angle location as either proximal thoracic (apices between T3 and T5), main thoracic (apices between T6 and T11), or thoraco-lumbar (apices between T12 and L4).

View Article and Find Full Text PDF

The impact of amino acids on tumor immunotherapy is gradually being uncovered. In this study, we screened various essential and non-essential amino acids and found that methionine enhances mRNA methylation and reduced the activation of Type I interferon pathway in bladder cancer. Through RNA sequencing, point mutations, MB49 mouse tumor models, and single-cell RNA sequencing, we demonstrated that high methionine levels elevate the expression of mA reader YTHDF1, promoting the degradation of RIG-I, thereby inhibiting the RIG-I/MAVS-mediated IFN-I pathway and reducing the efficacy of tumor immunotherapy.

View Article and Find Full Text PDF
Article Synopsis
  • - Breast cancer is the most common cancer diagnosed in women globally, characterized by its diverse molecular makeup and complex types, which pose challenges in treatment due to tumor heterogeneity and resistance.
  • - Recent research has identified nearly 200 RNA modifications, with methylation playing a crucial role in cancer development, progression, and treatment resistance, particularly the N6-methyladenosine (m6A) modification, which involves key "writers," "readers," and "erasers."
  • - The review discusses various RNA methylation types (m6A, m7G, m5C, m1A, and m3C), their effects on tumor behavior, and highlights their potential as therapeutic targets, suggesting they may enhance
View Article and Find Full Text PDF

[Corrigendum] Anti‑carcinogenic properties of omeprazole against human colon cancer cells and azoxymethane‑induced colonic aberrant crypt foci formation in rats.

Int J Oncol

January 2025

Center for Chemoprevention and Cancer Drug Development, Department of Medicine, Hem-Onc Section, PC Stephenson Oklahoma Cancer Center, University of Oklahoma Health Sciences Center, Oklahoma City, OK 73104, USA.

Following the publication of the above article, an interested reader drew to the authors' attention that certain of the in vitro image panels shown in Fig. 3B (featuring the effects of adding five different concentrations of omeprazole on acridine orange/ethidium bromide‑stained HCA‑7 cells) and Fig. 4 (showing western blotting experiments) on p.

View Article and Find Full Text PDF

[Corrigendum] Spicatoside A in red displays a laxative effect in a constipation rat model via regulating mAChRs and ER stress signaling.

Int J Mol Med

February 2025

Department of Biomaterials Science, College of Natural Resources and Life Science/Life and Industry Convergence Research Institute, Pusan National University, Miryang 627-706, Republic of Korea.

Following the publication of the above article, an interested reader drew to the Editor's attention that various of the histological structural images shown in Fig. 5 on p. 190 were strikingly similar to data that were featured in Fig.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!