Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy.

BACKGROUND: Small intestinal vascular malformations (angiodysplasias) are common causes of small intestinal bleeding. While capsule endoscopy has become the primary diagnostic method for angiodysplasia, manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload, which affects the accuracy of diagnosis. AIM: To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine, achieve automatic disease detection, and shorten the capsule endoscopy (CE) reading time. METHODS: A convolutional neural network semantic segmentation model with a feature fusion method, which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour, thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions, was proposed. Resnet-50 was used as the skeleton network to design the fusion mechanism, fuse the shallow and depth features, and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia. The training set and test set were constructed and compared with PSPNet, Deeplab3+, and UperNet. RESULTS: The test set constructed in the study achieved satisfactory results, where pixel accuracy was 99%, mean intersection over union was 0.69, negative predictive value was 98.74%, and positive predictive value was 94.27%. The model parameter was 46.38 M, the float calculation was 467.2 G, and the time length to segment and recognize a picture was 0.6 s. CONCLUSION: Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

Saccharomyces cerevisiae may serve as a probiotic in colorectal cancer by promoting cancer cell apoptosis.

OBJECTIVES: Shotgun metagenomic sequencing of human fecal samples has shown that Saccharomyces cerevisiae (S. cerevisiae) is significantly suppressed in colorectal cancer (CRC) and probably plays an important role in CRC progression. However, these results need to be validated. Here we aimed to confirm the results of high-throughput sequencing and demonstrate the mechanisms mediating the effect of S. cerevisiae on progression from colorectal adenoma (CRA) to CRC. METHODS: We used a quantitative polymerase chain reaction (qPCR) assay to examine the relative abundance of S. cerevisiae in 281 fecal samples collected from 106 healthy controls, 108 patients with CRA and 67 with CRC. C57BL/6 and APCMin/+ mouse models and in vitro cell assays were subsequntly used for additional analyses. The mouse models were treated or not treated with broad-spectrum antibiotics and given an S. cerevisiae gavage for 8 weeks. Western blot, 16S rRNA sequencing, qPCR, immunohistochemistry, RNA sequencing, cell counting kit-8 assay, colony formation assay and flow cytometry were performed. RESULTS: S. cerevisiae was 2.68-fold and 3.94-fold less abundant in patients with CRA and CRC, respectively, than in the controls. In vivo experiments showed that S. cerevisiae reduced colorectal tumor progression by promoting epithelial cell apoptosis and modulated gut microbial structure and intestinal immunity. S. cerevisiae downregulated nuclear factor kappa light chain enhancer of activated B cells and the mechanistic target of rapamycin signaling pathways. Cell assays confirmed the pro-apoptotic effect of S. cerevisiae. CONCLUSIONS: S. cerevisiae may play a probiotic role in CRC by promoting cancer cell apoptosis. It can reduce CRC progression by modulating the mucosal microbial structure.