INTRODUCTION: Magnetic resonance imaging is a useful technique to visualize soft tissues within the knee joint. Cartilage delineation in magnetic resonance (MR) images helps in understanding the disease progressions. Convolutional neural networks (CNNs) have shown promising results in computer vision tasks, and various encoder-decoder-based segmentation neural networks are introduced in the last few years. However, the performances of such networks are unknown in the context of cartilage delineation.
METHODS: This study trained and compared 10 encoder-decoder-based CNNs in performing cartilage delineation from knee MR images. The knee MR images are obtained from the Osteoarthritis Initiative (OAI). The benchmarking process is to compare various CNNs based on physical specifications and segmentation performances.
RESULTS: LadderNet has the least trainable parameters with the model size of 5 MB. UNetVanilla crowned the best performances by having 0.8369, 0.9108, and 0.9097 on JSC, DSC, and MCC.
CONCLUSION: UNetVanilla can be served as a benchmark for cartilage delineation in knee MR images, while LadderNet served as an alternative if there are hardware limitations during production.
METHODS: CT scans of the neck of two hundred patients were analysed by two groups of raters. For thyrohyoid approach, mean distance from the superior border of the thyroid cartilage to the laryngeal cavity (THd) and mean angle from the superior border of the thyroid cartilage to mid-true cords (THa) were measured. For transthyroid approach, mean distance from mid-thyroid cartilage to mid-true cords (TTd) and Hounsfield unit (HU) at mid-thyroid cartilage (TTc) were measured. For cricothyroid approach, mean distance from the inferior border of the thyroid cartilage to the laryngeal cavity (CTd) and mean angle from the inferior border of the thyroid cartilage to mid-true cords (CTa) were measured.
RESULTS: There were statistically significant differences between males and females for all measurements except for CTa (p 0.05). There was a significant fair positive correlation between age and TTc (p = 0.0002). For all measurements obtained, there were moderate to excellent inter-group consistency and intra-rater reliability.
CONCLUSION: This study demonstrated a significant sex dimorphism that may influence the three TIL approaches except for needle angulation in the cricothyroid approach. The knowledge of laryngeal dimension is important to increase success in TIL procedure.
METHODS: A total of 28 articular cartilage samples from adult cats (14 OA and 14 normal), 10 synovial membranes from adult cats (five OA and five normal) and three cartilage samples from 9-week-old fetal cats were used. The presence of PAR2 and matriptase in the cartilage and synovial membrane of the adult samples was detected by immunohistochemical (IHC) staining, while real-time PCR was used for mRNA expression analyses in all samples.
RESULTS: PAR2 was detected in all OA and normal articular cartilage and synovial membrane samples but confined to only a few superficial chondrocytes in the normal samples. Matriptase was only detected in OA articular cartilage and synovial membrane samples. PAR2 and matriptase mRNA expression were, however, detected in all cartilage and synovial membrane samples. PAR2 and matriptase mRNA expression levels in OA articular cartilage were five (P <0.001) and 3.3 (P <0.001) times higher than that of the healthy group, respectively. There was no significant difference (P = 0.05) in the OA synovial membrane PAR2 and matriptase mRNA expression compared with the normal samples.
CONCLUSIONS AND RELEVANCE: Detection of PAR2 and matriptase proteins and gene expression in feline articular tissues is a novel and important finding, and supports the hypothesis that serine proteases are involved in the pathogenesis of feline OA. The consistent presence of PAR2 and matriptase protein in the cytoplasm of OA chondrocytes suggests a possible involvement of proteases in cartilage degradation. Further investigations into the PAR2 and matriptase pathobiology could enhance our understanding of the proteolytic cascades in feline OA, which might lead to the development of novel therapeutic strategies.