In vivo fluorescence molecular imaging of the vascular endothelial growth factor in rats with early diabetic retinopathy

Semi-Supervised Dual Stream Segmentation Network for Fundus Lesion Segmentation

Accurate segmentation of retinal images can assist ophthalmologists to determine the degree of retinopathy and diagnose other systemic diseases. However, the structure of the retina is complex, and different anatomical structures often affect the segmentation of fundus lesions. In this paper, a new segmentation strategy called a dual stream segmentation network embedded into a conditional generative adversarial network is proposed to improve the accuracy of retinal lesion segmentation. First, a dual stream encoder is proposed to utilize the capabilities of two different networks and extract more feature information. Second, a multiple level fuse block is proposed to decode the richer and more effective features from the two different parallel encoders. Third, the proposed network is further trained in a semi-supervised adversarial manner to leverage from labeled images and unlabeled images with high confident pseudo labels, which are selected by the dual stream Bayesian segmentation network. An annotation discriminator is further proposed to reduce the negativity that prediction tends to become increasingly similar to the inaccurate predictions of unlabeled images. The proposed method is cross-validated in 384 clinical fundus fluorescein angiography images and 1040 optical coherence tomography images. Compared to state-of-the-art methods, the proposed method can achieve better segmentation of retinal capillary non-perfusion region and choroidal neovascularization.

The Relationship between VEGFC Gene Polymorphisms and Autoimmune Thyroiditis

Background

Autoimmune thyroid diseases (AITDs), representative autoimmune diseases, mainly consist of Graves' disease (GD) and Hashimoto's thyroiditis (HT). In this passage, we investigated the association between vascular endothelial growth factor C (VEGFC) gene polymorphisms and AITDs.

Methods

A total of 1084 patients with AITDs and 794 healthy controls were tested for VEGFC gene genotypes in four single nucleotide polymorphisms (SNPs) by high-throughput sequencing, and the correlation between VEGFC gene polymorphisms and AITDs was statistically analyzed.

Results

The genotype distribution of rs3775194 was statistically associated with AITDs compared with the control group. Rs3775194 was associated with AITDs under the overdominant model, both before and after adjusting for confounding factors, while the other three SNPs were not associated with GD and HT. There was a prominent discrepancy between male healthy controls and male AITD patients under overdominant model in rs3775194 and the recessive model in rs11947611. The genotype distribution of rs3775194 was statistically related to male HT.

Conclusion

These results reveal the correlation between VEGFC mutation and AITD susceptibility.