Double-Balanced Loss for Imbalanced Colorectal Lesion Classification.

Colorectal cancer has a high incidence rate in all countries around the world, and the survival rate of patients is improved by early detection. With the development of object detection technology based on deep learning, computer-aided diagnosis of colonoscopy medical images becomes a reality, which can effectively reduce the occurrence of missed diagnosis and misdiagnosis. In medical image recognition, the assumption that training samples follow independent identical distribution (IID) is the key to the high accuracy of deep learning. However, the classification of medical images is unbalanced in most cases. This paper proposes a new loss function named the double-balanced loss function for the deep learning model, to improve the impact of datasets on classification accuracy. It introduces the effects of sample size and sample difficulty to the loss calculation and deals with both sample size imbalance and sample difficulty imbalance. And it combines with deep learning to build the medical diagnosis model for colorectal cancer. Experimentally verified by three colorectal white-light endoscopic image datasets, the double-balanced loss function proposed in this paper has better performance on the imbalance classification problem of colorectal medical images.

White-Light Endoscopic Colorectal Lesion Detection Based on Improved YOLOv5.

As an effective tool for colorectal lesion detection, it is still difficult to avoid the phenomenon of missed and false detection when using white-light endoscopy. In order to improve the lesion detection rate of colorectal cancer patients, this paper proposes a real-time lesion diagnosis model (YOLOv5x-CG) based on YOLOv5 improvement. In this diagnostic model, colorectal lesions were subdivided into three categories: micropolyps, adenomas, and cancer. In the course of convolutional network training, Mosaic data enhancement strategy was used to improve the detection rate of small target polyps. At the same time, coordinate attention (CA) mechanism was introduced to take into account channel and location information in the network, so as to realize the effective extraction of three kinds of pathological features. The Ghost module was also used to generate more feature maps through linear processing, which reduces the stress of learning model parameters and speeds up detection. The experimental results show that the lesion diagnosis model proposed in this paper has a more rapid and accurate lesion detection ability, and the AP value of polyps, adenomas, and cancer is 0.923, 0.955, and 0.87, and mAP@50 is 0.916.

Biotransformation of Polyphenols in Apple Pomace Fermented by ß-Glucosidase-Producing Lactobacillus rhamnosus L08.

Apple pomace, the main by-product in apple processing, is a cheap source of bioactive compounds that could be used in the food industry. However, the value of this by-product is still far from being fully realized. In this study, 11 strains of Lactobacillus strains were assayed for ß-glucosidase activity, and only Lactobacillus rhamnosus L08 (L. rhamnosus L08) showed high cell-membrane associated ß-glucosidase activity. We then evaluated the effects of fermentation of apple pomace using the selected strain, focusing on the biotransformation of polyphenols and antioxidant capacity. We found that L. rhamnosus L08 fermentation significantly reduced the contents of quercitrin and phlorizin in apple pomace, while increasing the contents of quercetin and phloretin. The contents of gallic acid, epicatechin acid, caffeic acid, and ferulic acid were also increased in apple pomace after fermentation. In addition, the antioxidant activities of apple pomace were enhanced during fermentation, based on the bioconversion of phenolic profiles. Our results demonstrate that lactic acid bacteria fermentation is a promising approach to enhance the bioactivity of phenolic compounds in apple pomace. Moreover, this study demonstrates that, as a valuable processing by-product with bioactive components, apple pomace can be used in the food industry to provide economic benefits.

Application of Deep Learning for Early Screening of Colorectal Precancerous Lesions under White Light Endoscopy.

METHODS: We collected and sorted out the white light endoscopic images of some patients undergoing colonoscopy. The convolutional neural network model is used to detect whether the image contains lesions: CRC, colorectal adenoma (CRA), and colorectal polyps. The accuracy, sensitivity, and specificity rates are used as indicators to evaluate the model. Then, the instance segmentation model is used to locate and classify the lesions on the images containing lesions, and mAP (mean average precision), AP50, and AP75 are used to evaluate the performance of an instance segmentation model. RESULTS: In the process of detecting whether the image contains lesions, we compared ResNet50 with the other four models, that is, AlexNet, VGG19, ResNet18, and GoogLeNet. The result is that ResNet50 performs better than several other models. It scored an accuracy of 93.0%, a sensitivity of 94.3%, and a specificity of 90.6%. In the process of localization and classification of the lesion in images containing lesions by Mask R-CNN, its mAP, AP50, and AP75 were 0.676, 0.903, and 0.833, respectively. CONCLUSION: We developed and compared five models for the detection of lesions in white light endoscopic images. ResNet50 showed the optimal performance, and Mask R-CNN model could be used to locate and classify lesions in images containing lesions.

Biomonitoring of chlorinated polyfluoroalkyl ether sulfonic acid in the general population in central and eastern China: Occurrence and associations with age/sex.

Although chlorinated polyfluoroalkyl ether sulfonic acid (Cl-PFESA) has been reported to be widespread in different environmental matrices of China, its exposure data in the general Chinese population are very limited. In the present study, the serum-to-whole-blood ratio was first assessed for 6:2 Cl-PFESA (mean/median: 2.07/1.82) based on its paired concentrations (n = 36), which allows a comparison in different blood matrices. The exposure levels of Cl-PFESAs in the general population were investigated by collecting blood samples (n = 1516) from residents of seven cities in central and eastern China. 6:2 Cl-PFESA was observed as the third-highest contributing polyfluoroalkyl substance (PFAS) (8.69%), with the median concentration at 2.18 ng/mL, indicating its importance for assessing the human exposure risks of PFASs. The regional difference between 6:2 Cl-PFESA and perfluorooctane sulfonate (PFOS) can be explained by their use pattern in China. Overall, similar to PFOS, 6:2 Cl-PFESA displays significantly increasing levels with increasing age for both males and females, with significantly higher levels in males. However, a significant sex dependence was found for 6:2 Cl-PFESA in one specific age group (41-60), while there was no significance in the other groups although males display higher levels than females. Our study provides robust data regarding human exposure to 6:2 Cl-PFESA in the general population in central and eastern China.

Mild changes in the mucosal microbiome during terminal ileum inflammation.

Patients with inflammation in the terminal ileum have high morbidity. In genetically susceptible hosts, chronic intestinal inflammation targeting the resident intestinal microbiota develops, but the microbial signature of the terminal ileum is poorly studied. To improve understanding of the mechanisms underlying the high prevalence of terminal ileum inflammation, we used 16S rRNA sequencing to analyse the mucosa-associated microbiota of the terminal ileum under intestinal homeostasis and inflammation conditions. Mucosal biopsy is the most commonly used sampling technique for assessing microbial communities associated with the intestinal mucosa. Thirty patients (15 with terminal ileum inflammation and 15 controls) underwent colonoscopy and biopsies were taken from the terminal ileum. Diagnosis depended on a combination of endoscopic and histological factors. To determine the composition and diversity of the microbiota, the 16S rRNA was analysed, and a variety of bioinformatics analyses were performed. Among the patients, composition analysis showed that the most abundant phyla identified in the terminal ileum samples were Fusobacteria, Proteobacteria, Firmicutes, Bacteroidetes, and Actinobacteria. At the phylum level, the relative proportion of Bacteroidetes was lower in patients with inflammation than in control patients. In addition, there was an increase in the abundance of the phyla Proteobacteria and Lentisphaerae in patients with inflammation. The abundances of the dominant microbes in the terminal ileum were not significantly different between patients in an inflammatory state and controls. These results confirm that partial dysbiosis of the intestinal mucosa-associated microbiota composition is associated with terminal ileum inflammation.

Dihydroartemisinin inhibits the growth and invasion of gastric cancer cells by regulating cyclin D1-CDK4-Rb signaling.

BACKGROUND: Dihydroartemisinin (DHA), a semisynthetic derivative of artemisinin, has a broad range of biological properties, including antitumor activity. However, the mechanisms by which DHA affects the tumorigenesis of gastric carcinoma (GC) are poorly understood. MATERIAL AND METHODS: The targets of DHA were identified by network pharmacology, and the association of CDK4 with clinicopathological characteristics and prognosis in patients with GC was analyzed by using TCGA data. CCK8, Transwell and flow cytometric analyses, as well as a tumor xenograft model, were used to assess the effects of DHA on the growth and migration of GC cells. qRT-PCR and Western blot analyses were used to determine the effects of DHA on the cyclin D1-CDK4-Rb signaling pathway. RESULTS: We identified 13 DHA targets and measured their expression of whichCDK4 expression levels were substantially higher in GC tissues than those in adjacent normal tissues, and high CDK4 expression acted as an independent prognostic factor of poor survival in patients with GC. DHA suppressed cell proliferation, migration and invasion in vitro and in vivo and induced G1 phase cell cycle arrest in a dose-dependent manner by regulating cyclin D1-CDK4-Rb signaling. CONCLUSIONS: DHA inhibits the tumorigenesis and invasion of GC by regulating cyclin D1-CDK4-Rb signaling and may provide therapeutic strategies for the treatment of GC.

Long-term effects of methamphetamine exposure in adolescent mice on the future ovarian reserve in adulthood.

Currently, there is an increasing prevalence of adolescent exposure to methamphetamine (MA). However, there is a paucity of information concerning the long-term impact of early exposure to MA upon female fertility and ovarian reserve. The aim of this study was to investigate the effect of long-term MA exposure in adolescents on their ovarian reserve in adulthood. Adolescent mice received intraperitoneal injections of MA (5mg/kg, three times per week) or saline from the 21st postnatal day for an 8 week period. Morphological, histological, biochemical, hormonal and ethological parameters were evaluated. An impaired ovarian reserve and vitality was found in the group treated with MA, manifesting in morphological-apparent mitochondrial damage, an activated apoptosis pathway in the ovarian tissue, a downward expression of ovarian anti-Mullerian hormone (AMH), a decreased number of primordial and growing follicles, an increased number of atretic follicles, and a depressed secretion of AMH, estradiol and progesterone from granulosa cells. However, no significant difference was noticed regarding the estrous cycle, the mating ability and the fertility outcome in the reproductive age of the mice after a period of non-medication. The present results confirmed that a long term exposure to methamphetamine in adolescent mice does have an adverse impact on their ovarian reserve, which indicates that such an early abuse of MA might influence the fertility lifespan of the female mouse.

Silencing of MAP4K4 by short hairpin RNA suppresses proliferation, induces G1 cell cycle arrest and induces apoptosis in gastric cancer cells.

Gastric cancer (GC) is the second most common cause of cancer­associated mortality worldwide. Previous studies suggest that mitogen­activated protein kinase kinase kinase kinase isoform 4 (MAP4K4) is involved in cancer cell growth, apoptosis and migration. In the present study, bioinformatics analysis and reverse transcription­quantitative polymerase chain reaction were performed to determine if MAP4K4 was overexpressed in GC. The knockdown of MAP4K4 by RNA interference in GC cells markedly inhibited cell proliferation, which may be mediated by cell cycle arrest in the G1 phase. The silencing of MAP4K4 also induced cell apoptosis by increasing the ratio of Bax/Bcl­2. In addition, Notch signaling was markedly reduced by MAP4K4 silencing. The results of the present study suggested that inhibition of MAP4K4 may be a therapeutic strategy for GC.

Effect of RTKN on progression and metastasis of colon cancer in vitro.

Like many epithelial-derived cancers, colon cancer results from a multistep tumorigenic process. However, the detailed mechanisms involved in colon cancer formations are poorly characterized. In the present study, we investigated the role of RTKN in colon cancer and explored underlying mechanisms. The results showed that RTKN expression was significantly increased in colon cancer tissues when compared with the adjacent tissues of patients in Shanghai People's hospital and in TCGA independent dataset. Furthermore, silencing of RTKN inhibited cell proliferation, migration, invasion, and arrested cell cycle at G1 phase in LOVO cells. Bioinformatics analysis demonstrated that DNA replication and cell cycle were involved in the regulation of RTKN. MCM2/3/5, CDK1/2 and PCNA expression had a direct relationship with the reduction of RTKN. RTKN could affect the proliferation and metastasis of colon cancer by reducing expression of MCM2/3/5, CDK1/2 and PCNA, suggesting that RTKN was a potential target for treating colon cancer.

Ponicidin induces apoptosis via JAK2 and STAT3 signaling pathways in gastric carcinoma.

Ponicidin has a variety of biological effects such as immunoregulatory and anti-inflammatory functions as well as anti-viral functions especially in the upper respiratory tract infection. This study was aimed to elucidate the antitumor effect of ponicidin in gastric carcinoma MKN28 cells and the possible molecular mechanism involved. Cell viability was measured by the Cell Count Kit-8 (CCK8). Cell apoptosis was assessed by flow cytometry as well as cell cycle and reactive oxygen species (ROS) analysis. Western blot analysis was used to detect the active form of caspase-3 as well as Bax and B-cell lymphoma-2 (Bcl-2) expressions after cells were treated with different concentrations of ponicidin. The results revealed that ponicidin could inhibit the growth of MKN28 cells significantly in both a time- and dose-dependent manner. The cell cycle was blocked and ROS generation was increased after the cells were treated with ponicidin. Bcl-2 expression was down-regulated remarkably while Bax expression and the active form of caspase-3 were increased after apoptosis occurred. We therefore conclude that ponicidin exhibited significant growth inhibition of gastric carcinoma cell line MKN28 and induced apoptosis of MKN28 cells via the signaling pathway regulated by Janus kinase 2 (JAK2) and signal transducers and activators of transcription 3 (STAT3). Ponicidin may serve as a potential therapeutic agent for gastric carcinoma.