Gastrointestinal (GI) disease is one of the most common diseases and primarily examined by GI endoscopy. Recently, deep learning (DL), in particular convolutional neural networks (CNNs) have made achievements in GI endoscopy image analysis. This review focuses on the applications of DL methods in the analysis of GI images. We summarized and compared the latest published literature related to the common clinical GI diseases and covers the key applications of DL in GI image detection, classification, segmentation, recognition, location, and other tasks. At the end, we give a discussion on the challenges and the research directions of GI image analysis based on DL in the future.
Purpose: Based on the previous 3 well-defined subtypes of gastric adenocarcinoma (invasive, proliferative and metabolic), we aimed to find potential biomarkers and biological features of each subtype.Methods: The genome-wide co-expression network of each subtype of gastric cancer was firstly constructed. Then, the functional modules in each genome-wide co-expression network were divided. Next, the key genes were screened from each functional module. Finally, the enrichment analysis was performed on the key genes to mine the biological features of each subtype. Comparative analysis between each pair of subtypes was performed to find the common and unique features among different subtypes.Results: A total of 207 key genes were identified in invasive, 215 key genes in proliferative, and 204 key genes in metabolic subtypes. Most key genes in each subtype were unique and new findings compared with that of the existing related researches. The GO and KEGG enrichment analyses for the key genes of each subtype revealed important biological features of each subtype.Conclusions: For a subtype, most identified key genes and important biological features were unique, which means that the key genes can be used as the potential biomarker of a subtype, and each subtype of gastric cancer might have different occurrence and development mechanisms. Thus, different diagnosis and therapy methods should be applied to the invasive, proliferative and metabolic subtypes of gastric cancer.
Background
Atrial fibrillation (AF) is the most common arrhythmia. Patients with valvular heart disease (VHD) frequently have AF. Growing evidence demonstrates that a specifically altered pattern of microRNA (miRNA) expression is related to valvular heart disease with atrial fibrillation (AF-VHD) processes. However, the combinatorial regulation by multiple miRNAs in inducing AF-VHD remains largely unknown.
Methods
The work identified AF-VHD-specific miRNAs and their combinations through mapping miRNA expression profile into differential co-expression network. The expressions of some dysregulated miRNAs were measured by quantitative reverse transcription polymerase chain reaction (qRT-PCR). The regulations of signaling pathways by the combinatorial miRNAs were predicted by enrichment analysis tools.
Results
Thirty-two differentially expressed (DE) miRNAs were identified to be AF-VHD-specific, some of which were new findings. These miRNAs interacted to form 5 combinations. qRT-PCR confirmed the different expression of several identified miRNAs, which illustrated the reliability and biomarker potentials of 32 dysregulation miRNAs. The biological characteristics of combinatorial miRNAs related to AF-VHD were highlighted. Twelve signaling pathways regulated by combinatorial miRNAs were predicted to be possibly associated with AF-VHD.
Conclusions
The AF-VHD-related signaling pathways regulated by combinatorial miRNAs may play an important role in the occurrence of AF-VHD. The work brings new insights into biomarkers and miRNA combination regulation mechanism in AF-VHD as well as further biological experiments.
The early diagnoses of esophageal cancer are of great significance in the clinic because they are critical for reducing mortality. At present, the diagnoses are mainly performed by artificial detection and annotations based on gastroscopic images. However, these procedures are very challenging to clinicians due to the large variability in the appearance of early cancer lesions. To reduce the subjectivity and fatigue in manual annotations and to improve the efficiency of diagnoses, computer-aided annotation methods are highly required. In this work, we proposed a novel method that utilized deep learning (DL) techniques to realize the automatic annotation of early esophageal cancer (EEC) lesions in gastroscopic images. The depth map of gastroscopic images was initially extracted by a DL network. Then, this additional depth information was fused with the original RGB gastroscopic images, which were then sent to another DL network to obtain precise annotations of EEC regions. In total, 4231 gastroscopic images of 732 patients were used to build and validate the proposed method. A total of 3190 of those images were EEC images, and the remaining 1041 were non-EEC images. The experimental results show that the combination of depth information and RGB information improved the annotation performance. The final EEC detection rate and mean Dice Similarity Coefficient (DSC) of our method were 97.54% and 74.43%, respectively. Compared with other state-of-the-art DL-based methods, the proposed method showed better annotation performances and fewer false positive outputs. Therefore, our method offers a good prospect in aiding the clinical diagnoses of EEC.INDEX TERMS Gastroscopic image, early esophageal cancer, lesion annotation, deep learning, depth map.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.