Objective To address the issue of noise in medical images,this paper proposes a left ventricular image segmentation method integrated with a denoising module to improve segmentation accuracy.Methods The denoising module is based on a denoising diffusion probabilistic model,and the segmentation model includes two branches:motion estimation and segmentation.This paper modifies the prediction target of the denoising module to the original signal instead of noise,enabling the end-to-end cascade training process of the denoising module and the segmentation model.Results On the EchoNet-Dynamic dataset,the segmentation performance of traditional denoising methods was inferior to the benchmark model;the Noise2Noise model showed improvement in three metrics,while our proposed method achieved improvement in all four metrics.On the ACDC dataset,our method outperformed the benchmark model,while other methods either performed worse than the benchmark or showed no statistical difference.Conclusion Traditional denoising methods can impair segmentation performance,whereas our proposed method can stably and effectively improve segmentation performance.Experiments verify the feasibility and potential clinical application value of the proposed method.

Objective To address the issue of noise in medical images,this paper proposes a left ventricular image segmentation method integrated with a denoising module to improve segmentation accuracy.Methods The denoising module is based on a denoising diffusion probabilistic model,and the segmentation model includes two branches:motion estimation and segmentation.This paper modifies the prediction target of the denoising module to the original signal instead of noise,enabling the end-to-end cascade training process of the denoising module and the segmentation model.Results On the EchoNet-Dynamic dataset,the segmentation performance of traditional denoising methods was inferior to the benchmark model;the Noise2Noise model showed improvement in three metrics,while our proposed method achieved improvement in all four metrics.On the ACDC dataset,our method outperformed the benchmark model,while other methods either performed worse than the benchmark or showed no statistical difference.Conclusion Traditional denoising methods can impair segmentation performance,whereas our proposed method can stably and effectively improve segmentation performance.Experiments verify the feasibility and potential clinical application value of the proposed method.

Background: Acute respiratory distress syndrome induced by acute lung injury (ALI) is the main cause for the high mortality of corona-virus disease 2019 (COVID-19). Huashi Baidu formula (HSBD) with the effects of eliminating dampness, clearing heat, ventilating lung, and removing toxin has been proven to be effective in the treatment of COVID-19, especially in severe cases. However, the underlying mechanism and target proteins of HSBD remain unclear. Objective: To provide evidence and decipher the mechanism of HSBD in alleviating inflammation and ALI. Materials and methods: A mouse model of ALI was induced by lipopolysaccharide (LPS), and hematoxylin-eosin staining was used to examine the protective effects of HSBD on the model mice. The cellular thermal shift assay and proteomics analysis were used to predict the target proteins. Furthermore, the A549 cells with peroxiredoxin 5 (PRDX5) knockdown were established to validate the predicted proteins. Results: Huashi Baidu formula treatment mitigated ALI and inflammatory cytokine dysfunction in LPS-induced mice, thus exerting a therapeutic effect on COVID-19. Huashi Baidu formula could serve as a therapeutic agent to alleviate inflammation and lung injury via nuclear factor k B and phosphatidylinositol 3-kinase signaling and interleukin 17 inhibition as well as targeting PRDX5, which could be one of the promising targets for treating inflammation. In the A549 cell line with PRDX5 knockdown (si-PRDX5), the anti-inflammation effects of HSBD, including reversing LPS-induced increase in the nitric oxide level and reduction in the hydrogen peroxide content, were attenuated. Thus, HSBD protected A549 cells from LPS-induced inflammation mainly by targeting PRDX5. Conclusions: Huashi Baidu formula alleviates ALI by targeting nuclear factor κB/phosphatidylinositol 3-kinase and PRDX5, as well as inhibiting the immune response induced by IL-17.