Retina image segmentation using the three-path Unet model.

Unsupervised image segmentation is a technique that divides an image into distinct regions or objects without prior labeling. This approach offers flexibility and adaptability to various types of image data. Particularly for large datasets, it eliminates the need for manual labeling, thereby it presents advantages in terms of time and labor costs. However, when applied to retinal image segmentation, challenges arise due to variations in data, presence of noise, and manual threshold adjustments, which can lead to over-segmentation or under-segmentation of small blood vessel boundaries and endpoints. In order to enhance the precision and accuracy of retinal image segmentation, we propose a novel image supervised segmentation network based on three-path Unet model.Firstly, the Haar wavelet transform is employed to extract high-frequency image information, which forms the foundation for the proposed HaarNet, a Unet-inspired architecture. Next, the HaarNet is integrated with the Unet and SegNet frameworks to develop a three-path Unet model, referred to as TP-Unet. Finally, the model is further refined into TP-Unet+AE+DSL by incorporating the advantages of auto-encoding (AE) and deep supervised learning (DSL) techniques, thereby enhancing the overall performance of the system. To evaluate the effectiveness of our proposed model, we conduct experiments using the DRIVE and CHASE public datasets. On the DRIVE dataset, our recommended model achieves a Dice coefficient of 0.8291 and a sensitivity index of 0.8184. These results significantly outperform the Unet model by [Formula: see text] and [Formula: see text], respectively. Furthermore, our model demonstrates excellent performance on the CHASE dataset, with a Dice coefficient of 0.8162, a sensitivity of 0.8242, and an accuracy of 0.9664. These metrics surpass the Unet model by [Formula: see text], [Formula: see text], and [Formula: see text], respectively. Our proposed model provides more accurate and reliable results for retinal vessel segmentation, which holds significant potential for assisting doctors in their diagnosis.

Function of the transforming growth factor-ß1/c-Jun N-terminal kinase signaling pathway in the action of thalidomide on a rat model of pulmonary fibrosis.

The aims of this study were to observe the effects of thalidomide on a rat model of pulmonary fibrosis, to determine the protein expression levels of phosphorylated c-Jun N-terminal kinase (p-JNK) and α-smooth muscle actin (α-SMA) and to explore the mechanism underlying the preventive effect of thalidomide on pulmonary fibrosis. Ninety healthy male Wistar rats (200±20 g) were randomly divided into control (N), model (M), SP600125 (SP), thalidomide (T) and SP600125 plus thalidomide (SP + T) groups. Pulmonary fibrosis models were established in groups M, SP, T and SP + T by the intratracheal instillation of bleomycin (BLM). A gavage of thalidomide was administered to the rats in groups T and SP + T once daily, whereas normal saline was administered to the rats in the other groups. The rats in the SP and SP + T groups were injected intraperitoneally with SP600125 following BLM administration, whereas the rats in the other groups received dimethyl sulfoxide. Rats were randomly sacrificed on days 7, 14 and 28. Pathological changes were examined by light microscopy using hematoxylin and eosin staining. Hydroxyproline (HYP) levels in the lung tissues were detected using alkaline hydrolysis. The protein expression levels of p-JNK and α-SMA were measured by immunohistochemical staining and western blot analysis. In group M, alveolitis was most serious on day 7 and then eased on day 14; marked pulmonary fibrosis was observed on day 28. The fibrosis was markedly attenuated in the SP + T group compared with that in group M. The HYP content increased gradually with time after BLM administration and peaked on day 28. On days 14 and 28, the HYP content was lower in groups T and SP than in group M (P<0.05). The expression levels of p-JNK protein and α-SMA were significantly lower in groups SP, T and SP + T than those in group M on day 14 (P<0.05). The expression level of α-SMA was lower in group SP + T than those in groups SP and T on days 14 and 28 (P<0.05). The expression level of p-JNK protein in group T was higher than those in groups SP and SP + T on days 14 and 28 (P<0.05). Thus, thalidomide eased the degree of BLM-induced pulmonary fibrosis in rats by downregulating p-JNK and α-SMA expression.