RESUMEN
The quality of tongue images has a significant influence on the performance of tongue diagnosis in Chinese medicine. During the acquisition process, the quality of the tongue image is easily affected by factors such as the illumination, camera parameters, and tongue extension of the subject. To ensure that the quality of the collected images meet the diagnostic criteria of traditional Chinese Medicine practitioners, we propose a deep learning model to evaluate the quality of tongue images. First, we acquired the tongue images of the patients under different lighting conditions, exposures, and tongue extension conditions using the inspection instrument, and experienced Chinese physicians manually screened them into high-quality and unqualified tongue datasets. We then designed a multi-task deep learning network to classify and evaluate the quality of tongue images by adding tongue segmentation as an auxiliary task, as the two tasks are related and can promote each other. Finally, we adaptively designed different task weight coefficients of a multi-task network to obtain better tongue image quality assessment (IQA) performance, as the two tasks have relatively different contributions in the loss weighting scheme. Experimental results show that the proposed method is superior to the traditional deep learning tongue IQA method, and as an additional task of the network, it can output the tongue segmentation area, which provides convenience for follow-up clinical tongue diagnosis. In addition, we used network visualization to verify the effectiveness of the proposed method qualitatively.
RESUMEN
Diabetic cardiomyopathy (DCM) is the leading cause of morbidity and mortality in diabetes mellitus (DM) patients. Previous studies have shown that the transforming growth factor-beta 1 (TGF-ß1)/Smad signaling pathway plays a key role in the development of myocardial fibrosis in DCM. Silymarin (SMN) is used clinically to treat liver disorders and acts by influencing TGF-ß1. However, the possible effects of silymarin on DCM remain to be elucidated. In our study, the DM animal model was induced by streptozotocin (STZ) injection. Fasting blood glucose level was measured, and the structure and function of the heart were measured by hematoxylin and eosin (H&E) and Masson staining, echocardiography, and transmission electron microscopy (TEM). Western blot was used to detect the expression of TGF-ß1, Smad2/3, phosphorylation Smad2/3(p-Smad2/3), and Smad7. Our results showed that silymarin downregulated blood glucose level and significantly improved cardiac fibrosis and collagen deposition in DM rats detected by H&E, Masson staining, and TEM assays. The echocardiography results showed that silymarin administration attenuated cardiac dysfunction in DM rats. Additionally, compared with untreated DM rats, levels of TGF-ß1 and p-Smad2/3 were decreased, whereas Smad7 was increased following silymarin administration. These data demonstrate that silymarin ameliorates DCM through the inhibition of TGF-ß1/Smad signaling, suggesting that silymarin may be a potential target for DCM treatment.
Asunto(s)
Cardiomiopatías Diabéticas/tratamiento farmacológico , Cardiomiopatías Diabéticas/metabolismo , Transducción de Señal , Silimarina/uso terapéutico , Proteínas Smad/metabolismo , Factor de Crecimiento Transformador beta1/metabolismo , Animales , Cardiomiopatías Diabéticas/fisiopatología , Fibrosis , Masculino , Miocardio/patología , Miocardio/ultraestructura , Ratas Sprague-Dawley , Silimarina/farmacologíaRESUMEN
Patients with type 2 diabetes mellitus (T2DM) are usually with poor immunity and easier to suffer from cancer and microbial infections. Herein, we report an efficient anti-diabetic medicinal mushroom, Coriolus versicolor (CV). This study aimed to investigate the anti-diabetic and anti-insulin-resistance effects of CV aqueous extract in myoblasts (L6 cells) and skeletal muscle of T2DM rat. Our results showed that CV extract treatment significantly reduced blood glucose levels of T2DM rats, whereas CV extract increased glucose consumption in insulin resistant L6 cells. Besides, the translocation and expression of glucose transporter 4 were enhanced by CV extract, which indicated that CV extract was effective in diabetic skeletal muscle. Moreover, CV extract treatments resulted in remarkable anti-insulin-resistance effects, which was reflected by the change of gene and protein expression levels in PI3K/Akt and p38 MAPK pathways. PI3K inhibitor, LY29004, and p38 MAPK inhibitor, SB203580 confirmed it further. In conclusion, our results demonstrated that the CV extract exhibited anti-diabetic and anti-insulin-resistance effects in diabetic skeletal muscle, and the effects were mediated by PI3K/Akt and p38 MAPK pathways. These findings are remarkable when considering the use of commercially available CV by diabetic patients who also suffer from cancer or microbial infections.