No abstract

Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field. A comprehensive thematic survey on medical image segmentation using deep learning techniques is presented. This paper makes two original contributions. Firstly, compared to traditional surveys that directly divide literatures of deep learning on medical image segmentation into many groups and introduce literatures in detail for each group, we classify currently popular literatures according to a multi‐level structure from coarse to fine. Secondly, this paper focuses on supervised and weakly supervised learning approaches, without including unsupervised approaches since they have been introduced in many old surveys and they are not popular currently. For supervised learning approaches, we analyse literatures in three aspects: the selection of backbone networks, the design of network blocks, and the improvement of loss functions. For weakly supervised learning approaches, we investigate literature according to data augmentation, transfer learning, and interactive segmentation, separately. Compared to existing surveys, this survey classifies the literatures very differently from before and is more convenient for readers to understand the relevant rationale and will guide them to think of appropriate improvements in medical image segmentation based on deep learning approaches.

Increasing evidence suggests that oxidative stress plays an essential role during carcinogenesis. However, the underlying mechanism between oxidative stress and carcinogenesis remains unknown. Recently, microRNAs (miRNAs) are revealed to be involved in oxidative stress response and carcinogenesis. This study aims to identify miRNAs in hepatocellular carcinoma (HCC) cells which might involve in oxidative stress response. An integrated analysis of miRNA expression signature was performed by employing robust rank aggregation (RRA) method, and four miRNAs (miR-34a-5p, miR-1915-3p, miR-638, and miR-150-3p) were identified as the oxidative stress-responsive miRNAs. Pathway enrichment analysis suggested that these four miRNAs played an important role in antiapoptosis process. Our data also revealed miR-34a-5p and miR-1915-3p, but not miR-150-3p and miR-638, were regulated by p53 in HCC cell lines under oxidative stress. In addition, clinical investigation revealed that these four miRNAs might be involved in oxidative stress response by targeting oxidative stress-related genes in HCC tissues. Kaplan-Meier analysis showed that these four miRNAs were associated with patients' overall survival. In conclusion, we identified four oxidative stress-responsive miRNAs, which were regulated by p53-dependent (miR-34a-5p and miR-1915-3p) and p53-independent pathway (miR-150-3p and miR-638). These four miRNAs may offer new strategy for HCC diagnosis and prognosis.

Acetaminophen- (APAP-) induced hepatic injury is an important clinical challenge. Oxidative stress, inflammation, apoptosis, and endoplasmic reticulum stress (ERS) contribute to the pathogenesis. Methane has potential anti-inflammatory, antioxidant, and antiapoptotic properties. This project was aimed at studying the protective effects and relative mechanisms of methane in APAP-induced liver injury. In the in vivo experiment, C57BL/6 mice were treated with APAP (400 mg/kg) to induce hepatic injury followed by methane-rich saline (MRS) 10 ml/kg i.p. after 12 and 24 h. We observed that MRS alleviated the histopathological lesions in the liver, decreased serum aminotransferase levels, reduced the levels of inflammatory cytokines, suppressed the nuclear factor-κB expression. Further, we found that MRS relieved oxidative stress by regulating the Nrf2/HO-1/NQO1 signaling pathway and their downstream products after APAP challenge. MRS also regulated proteins associated with ERS-induced apoptosis. In the in vitro experiment, the L-02 cell line was treated with APAP (10 mM) to induce hepatic injury. We found that a methane-rich medium decreased the levels of reactive oxygen species (DHE fluorescent staining), inhibited apoptosis (cell flow test), and regulated the Nrf2/HO-1/NQO1 signaling pathway. Our data indicated that MRS prevented APAP-induced hepatic injury via anti-inflammatory, antioxidant, anti-ERS, and antiapoptotic properties involving the Nrf2/HO-1/NQO1 signaling pathway.

No abstract