Transformer-based Multi-label Deep Learning Model is Efficient for Detecting Ankle Lateral and Medial Ligament Injuries on MRI and Improving Clinicians' Diagnostic Accuracy for Rotational Chronic Ankle Instability.

PURPOSE: To develop a deep learning (DL) model that can simultaneously detect lateral and medial collateral ligament injuries of the ankle, aiding in the diagnosis of chronic ankle instability (CAI), and assess its impact on clinicians' diagnostic performance. METHODS: DL models were developed and external validated on retrospectively collected ankle MRIs between April 2016 and March 2022 respectively at three centers. Included patients were confirmed diagnoses of CAI through arthroscopy, as well as individuals who had undergone MRI and physical examinations that ruled out ligament injuries. DL models were constructed based on a multi-label paradigm. A transformer-based multi-label DL model (AnkleNet) was developed and compared with four convolution neural network (CNN) models. Subsequently, a reader study was conducted to evaluate the impact of model assistance on clinicians when diagnosing challenging cases: identifying rotational CAI (RCAI). Diagnostic performance was assessed using area under the receiver operating characteristic curve (AUC). RESULTS: Our transformer-based model achieved AUC of 0.910 and 0.892 for detecting lateral and medial collateral ligament injury, respectively, both of which was significantly higher than that of CNN-based models (all P < 0.001). In terms of further CAI diagnosis, it exhibited a macro-average AUC of 0.870 and a balanced accuracy of 0.805. The reader study indicated that incorporation with our model significantly enhanced the diagnostic accuracy of clinicians (P = 0.042), particularly junior clinicians, and led to a reduction in diagnostic variability. The code of the model can be accessed at https://github.com/ChiariRay/AnkleNet. CONCLUSION: Our transformer-based model was able to detect lateral and medial collateral ligament injuries based on MRI and outperformed CNN-based models, demonstrating a promising performance in diagnosing CAI, especially RCAI patients.

The PIEZO1/miR-155-5p/GDF6/SMAD2/3 signaling axis is involved in inducing the occurrence and progression of osteoarthritis under excessive mechanical stress.

OBJECTIVE: To elucidate the molecular mechanism of overloading-induced osteoarthritis (OA) and to find a novel therapeutic target. METHODS: We utilized human cartilage specimens, mouse chondrocytes, a destabilization of the medial meniscus (DMM) mouse model, and a mouse hindlimb weight-bearing model to validate the role of overloading on chondrocyte senescence and OA development. Then, we observed the effect of PIEZO1-miR-155-5p-GDF6-SMAD2/3 signaling axis on the preservation of joint metabolic homeostasis under overloading in vivo, in vitro and ex vivo by qPCR, Western blot, enzyme-linked immunosorbent assay (ELISA), immunohistochemistry, immunofluorescence, SA-ß-gal staining, CCK8 assay, et al. Finally, we verified the therapeutic effects of intra-articular injection of miR-155-5p inhibitor or recombinant GDF6 on the murine overloading-induced OA models. RESULTS: Chondrocytes sensesed the mechanical overloading through PIEZO1 and up-regulated miR-155-5p expression. MiR-155-5p mimics could copy the effects of overloading-induced chondrocyte senescence and OA. Additionally, miR-155-5p could suppress the mRNA expression of Gdf6-Smad2/3 in various tissues within the joint. Overloading could disrupt joint metabolic homeostasis by downregulating the expression of anabolism indicators and upregulating the expression of catabolism indicators in the chondrocytes and synoviocytes, while miR-155-5p inhibition or GDF6 supplementation could exert an antagonistic effect by preserving the joint homeostasis. Finally, in the in vivo overloading models, intra-articular injection of miR-155-5p inhibitor or recombinant GDF6 could significantly mitigate the severity of impending OA and lessened the progression of existing OA. CONCLUSION: GDF6 overexpression or miR-155-5p inhibition could attenuate overloading-induced chondrocyte senescence and OA through the PIEZO1-miR-155-5p-GDF6-SMAD2/3 signaling pathway. Our study provides a new therapeutic target for the treatment of overloading-induced OA.

Systematic Pharmacology and Experimental Validation to Reveal the Alleviation of Astragalus membranaceus Regulating Ferroptosis in Osteoarthritis.

Background: Astragalus membranaceus (AM) shows promise as a therapeutic agent for osteoarthritis (OA), a debilitating condition with high disability rates. OA exacerbation is linked to chondrocyte ferroptosis, yet the precise pharmacological mechanisms of AM remain unclear. Methods: We validated AM's protective efficacy in an anterior cruciate ligament transection (ACLT) mouse model of OA. The Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP) database was utilized to identify AM's active components and their targets. FerrDb (a database for regulators and markers of ferroptosis and ferroptosis-disease associations) pinpointed ferroptosis-related targets, while GeneCards, Online Mendelian Inheritance in Man (OMIM), Pharmacogenomics Knowledgebase (PharmGKB), Therapeutic Target Database (TTD), and DrugBank sourced OA-related genes. Molecular docking analysis further validated these targets. Ultimately, the validation of the results was accomplished through in vitro experiments. Results: AM exhibited anabolic effects and suppressed catabolism in OA chondrocytes. Network pharmacology identified 19 common genes, and molecular docking suggested quercetin, an AM constituent, interacts with key proteins like HO-1 and NRF2 to inhibit chondrocyte ferroptosis. In vitro experiments confirmed AM's ability to modulate the NRF2/HO-1 pathway via quercetin, mitigating chondrocyte ferroptosis. Conclusion: This study elucidates how AM regulates chondrocyte ferroptosis, impacting OA progression, providing a theoretical basis and experimental support for AM's scientific application.

Injectable hyperbranched PEG crosslinked hyaluronan hydrogel microparticles containing mir-99a-3p modified subcutaneous ADSCs-derived exosomes was beneficial for long-term treatment of osteoarthritis.

Exosomes (Exos) secreted by adipose-derived stem cells (ADSCs) have shown potential in alleviating osteoarthritis (OA). Previous studies indicated that infrapatellar fat pad (IPFP) derived stem cells (IPFSCs) may be more suitable for the treatment of OA than subcutaneous adipose tissue (ScAT) derived stem cells (ScASCs). However, it remains unclear which type of Exos offers superior therapeutic benefit for OA. This study first compared the differences between Exos derived from IPFP stem cells (ExosIPFP) and ScAT stem cells (ExosScAT) in OA treatment. Results suggested that ExosIPFP significantly inhibit the degradation of cartilage extracellular matrix (ECM) than ExosScAT, following this, the differences in microRNA (miRNA) expression between the two types of Exos using small RNA sequencing were performed. Subsequently, miR-99 b-3p was chosen and over-expressed in ExosScAT (ExosScAT-99b-3p), both in vivo and in vitro experiments demonstrated its efficacy in inhibiting the expression of ADAMTS4, promoting the repair of the ECM in OA. Finally, microfluidic technology was performed to fabricate a hyaluronan-based hydrogel microparticles (HMPs) for encapsulating Exos (HMPs@exos), the injectability, sustained release of Exos and long-term therapeutic effect on OA were validated. In summary, these results suggest miR-99 b-3p regulates the degradation of cartilage ECM by targeting ADAMTS4, the upregulation of miR-99 b-3p in ExosScAT would enable them to exhibit comparable or even superior effectiveness to ExosIPFP for OA treatment, making it a promising approach for OA treatment. Considering the abundant resources of ScAT and the limited availability of IPFP, ScAT harvested through liposuction could be genetically engineered to yield Exos for OA treatment. Furthermore, the encapsulation of Exos in HMPs provides an injectable sustained local drug release system, which could potentially enhance the efficacy of Exos and hold potential as future therapeutic strategies.