Adaptive Frequency Learning Network With Anti-Aliasing Complex Convolutions for Colon Diseases Subtypes.

The automatic and dependable identification of colonic disease subtypes by colonoscopy is crucial. Once successful, it will facilitate clinically more in-depth disease staging analysis and the formulation of more tailored treatment plans. However, inter-class confusion and brightness imbalance are major obstacles to colon disease subtyping. Notably, the Fourier-based image spectrum, with its distinctive frequency features and brightness insensitivity, offers a potential solution. To effectively leverage its advantages to address the existing challenges, this article proposes a framework capable of thorough learning in the frequency domain based on four core designs: the position consistency module, the high-frequency self-supervised module, the complex number arithmetic model, and the feature anti-aliasing module. The position consistency module enables the generation of spectra that preserve local and positional information while compressing the spectral data range to improve training stability. Through band masking and supervision, the high-frequency autoencoder module guides the network to learn useful frequency features selectively. The proposed complex number arithmetic model allows direct spectral training while avoiding the loss of phase information caused by current general-purpose real-valued operations. The feature anti-aliasing module embeds filters in the model to prevent spectral aliasing caused by down-sampling and improve performance. Experiments are performed on the collected five-class dataset, which contains 4591 colorectal endoscopic images. The outcomes show that our proposed method produces state-of-the-art results with an accuracy rate of 89.82%.

DLGNet: A dual-branch lesion-aware network with the supervised Gaussian Mixture model for colon lesions classification in colonoscopy images.

Colorectal cancer is one of the malignant tumors with the highest mortality due to the lack of obvious early symptoms. It is usually in the advanced stage when it is discovered. Thus the automatic and accurate classification of early colon lesions is of great significance for clinically estimating the status of colon lesions and formulating appropriate diagnostic programs. However, it is challenging to classify full-stage colon lesions due to the large inter-class similarities and intra-class differences of the images. In this work, we propose a novel dual-branch lesion-aware neural network (DLGNet) to classify intestinal lesions by exploring the intrinsic relationship between diseases, composed of four modules: lesion location module, dual-branch classification module, attention guidance module, and inter-class Gaussian loss function. Specifically, the elaborate dual-branch module integrates the original image and the lesion patch obtained by the lesion localization module to explore and interact with lesion-specific features from a global and local perspective. Also, the feature-guided module guides the model to pay attention to the disease-specific features by learning remote dependencies through spatial and channel attention after network feature learning. Finally, the inter-class Gaussian loss function is proposed, which assumes that each feature extracted by the network is an independent Gaussian distribution, and the inter-class clustering is more compact, thereby improving the discriminative ability of the network. The extensive experiments on the collected 2568 colonoscopy images have an average accuracy of 91.50%, and the proposed method surpasses the state-of-the-art methods. This study is the first time that colon lesions are classified at each stage and achieves promising colon disease classification performance. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/DLGNet.

Coexpression Network Analysis-Based Identification of Critical Genes Differentiating between Latent and Active Tuberculosis.

Methods: Three Gene Expression Omnibus (GEO) microarray datasets (GSE19491, GSE98461, and GSE152532) were downloaded, with GSE19491 and GSE98461 then being merged to form a training dataset. Hub genes capable of differentiating between ATB and LTBI were then identified through differential expression analyses and a WGCNA analysis of this training dataset. Receiver operating characteristic (ROC) curves were then used to gauge to the diagnostic accuracy of these hub genes in the test dataset (GSE152532). Gene expression-based immune cell infiltration and the relationship between such infiltration and hub gene expression were further assessed via a single-sample gene set enrichment analysis (ssGSEA). Results: In total, 485 differentially expressed genes were analyzed, with the WGCNA approach yielding 8 coexpression models. Of these, the black module was the most closely correlated with ATB. In total, five hub genes (FBXO6, ATF3, GBP1, GBP4, and GBP5) were identified as potential biomarkers associated with LTBI progression to ATB based on a combination of differential expression and LASSO analyses. The area under the ROC curve values for these five genes ranged from 0.8 to 0.9 in the test dataset, and ssGSEA revealed the expression of these genes to be negatively correlated with lymphocyte activity but positively correlated with myeloid and inflammatory cell activity. Conclusion: The five hub genes identified in this study may play a novel role in tuberculosis-related immunopathology and offer value as novel biomarkers differentiating LTBI from ATB.

Application of endoscopic ultrasonography for detecting esophageal lesions based on convolutional neural network.

BACKGROUND: A convolutional neural network (CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition. AIM: To automatically identify the invasion depth and origin of esophageal lesions based on a CNN. METHODS: A total of 1670 white-light images were used to train and validate the CNN system. The method proposed in this paper included the following two parts: (1) Location module, an object detection network, locating the classified main image feature regions of the image for subsequent classification tasks; and (2) Classification module, a traditional classification CNN, classifying the images cut out by the object detection network. RESULTS: The CNN system proposed in this study achieved an overall accuracy of 82.49%, sensitivity of 80.23%, and specificity of 90.56%. In this study, after follow-up pathology, 726 patients were compared for endoscopic pathology. The misdiagnosis rate of endoscopic diagnosis in the lesion invasion range was approximately 9.5%; 41 patients showed no lesion invasion to the muscularis propria, but 36 of them pathologically showed invasion to the superficial muscularis propria. The patients with invasion of the tunica adventitia were all treated by surgery with an accuracy rate of 100%. For the examination of submucosal lesions, the accuracy of endoscopic ultrasonography (EUS) was approximately 99.3%. Results of this study showed that EUS had a high accuracy rate for the origin of submucosal lesions, whereas the misdiagnosis rate was slightly high in the evaluation of the invasion scope of lesions. Misdiagnosis could be due to different operating and diagnostic levels of endoscopists, unclear ultrasound probes, and unclear lesions. CONCLUSION: This study is the first to recognize esophageal EUS images through deep learning, which can automatically identify the invasion depth and lesion origin of submucosal tumors and classify such tumors, thereby achieving good accuracy. In future studies, this method can provide guidance and help to clinical endoscopists.

Acetyl-11-keto-ß-boswellic acid inhibits proliferation and induces apoptosis of gastric cancer cells through the phosphatase and tensin homolog /Akt/ cyclooxygenase-2 signaling pathway.

BACKGROUND: Gastric cancer is one of the most common malignant tumors of the digestive system worldwide, posing a serious danger to human health. Cyclooxygenase (COX)-2 plays an important role in the carcinogenesis and progression of gastric cancer. Acetyl-11-keto-ß-boswellic acid (AKBA) is a promising drug for cancer therapy, but its effects and mechanism of action on human gastric cancer remain unclear. AIM: To evaluate whether the phosphatase and tensin homolog (PTEN)/Akt/COX-2 signaling pathway is involved in the anti-tumor effect of AKBA in gastric cancer. METHODS: Human poorly differentiated BGC823 and moderately differentiated SGC7901 gastric cancer cells were routinely cultured in Roswell Park Memorial Institute 1640 medium supplemented with 10% fetal bovine serum and 1% penicillin/streptomycin. Gastric cancer cell proliferation was determined by methyl thiazolyl tetrazolium colorimetric assay. Apoptosis was measured by flow cytometry. Cell migration was assessed using the wound-healing assay. Expression of Bcl-2, Bax, proliferating cell nuclear antigen, PTEN, p-Akt, and COX-2 were detected by Western blot analysis. A xenograft nude mouse model of human gastric cancer was established to evaluate the anti-cancer effect of AKBA in vivo. RESULTS: AKBA significantly inhibited the proliferation of gastric cancer cells in a dose- and time-dependent manner, inhibited migration in a time-dependent manner, and induced apoptosis in a dose-dependent manner in vitro; it also inhibited tumor growth in vivo. AKBA up-regulated the expression of PTEN and Bax, and down-regulated the expression of proliferating cell nuclear antigen, Bcl-2, p-Akt, and COX-2 in a dose-dependent manner. The PTEN inhibitor bpv (Hopic) reversed the high expression of PTEN and low expression of p-Akt and COX-2 that were induced by AKBA. The Akt inhibitor MK2206 combined with AKBA down- regulated the expression of p-Akt and COX-2, and the combined effect was better than that of AKBA alone. CONCLUSION: AKBA inhibits the proliferation and migration and promotes the apoptosis of gastric cancer cells through the PTEN/Akt/COX-2 signaling pathway.

Myrrh induces the apoptosis and inhibits the proliferation and migration of gastric cancer cells through down-regulating cyclooxygenase-2 expression.

OBJECTIVE: The present study is designed to evaluate the anti-tumor effects of myrrh on human gastric cancer both in vitro and in vivo. METHODS: The gastric cancer cell proliferation was determined by MTT assay. Apoptosis was measured by flow cytometry and Hoechst 33342 staining. Wound healing was performed to evaluate the effects of myrrh on the migration. COX-2, PCNA, Bcl-2, and Bax expressions were detected by Western blot analysis. A xenograft nude mice model of human gastric cancer was established to evaluate the anti-cancer effect of myrrh in vivo. RESULTS: Myrrh significantly inhibited cellular proliferation, migration, and induced apoptosis in vitro as well as inhibited tumor growth in vivo. In addition, myrrh inhibited the expression of PCNA, COX-2, and Bcl-2 as well as increased Bax expression in gastric cancer cells. CONCLUSION: Myrrh may inhibit the proliferation and migration of gastric cancer cells, as well as induced their apoptosis by down-regulating the expression of COX-2.

Automatic classification of esophageal lesions in endoscopic images using a convolutional neural network.

BACKGROUND: Using deep learning techniques in image analysis is a dynamically emerging field. This study aims to use a convolutional neural network (CNN), a deep learning approach, to automatically classify esophageal cancer (EC) and distinguish it from premalignant lesions. METHODS: A total of 1,272 white-light images were adopted from 748 subjects, including normal cases, premalignant lesions, and cancerous lesions; 1,017 images were used to train the CNN, and another 255 images were examined to evaluate the CNN architecture. Our proposed CNN structure consists of two subnetworks (O-stream and P-stream). The original images were used as the inputs of the O-stream to extract the color and global features, and the pre-processed esophageal images were used as the inputs of the P-stream to extract the texture and detail features. RESULTS: The CNN system we developed achieved an accuracy of 85.83%, a sensitivity of 94.23%, and a specificity of 94.67% after the fusion of the 2 streams was accomplished. The classification accuracy of normal esophagus, premalignant lesion, and EC were 94.23%, 82.5%, and 77.14%, respectively, which shows a better performance than the Local Binary Patterns (LBP) + Support Vector Machine (SVM) and Histogram of Gradient (HOG) + SVM methods. A total of 8 of the 35 (22.85%) EC lesions were categorized as premalignant lesions because of their slightly reddish and flat lesions. CONCLUSIONS: The CNN system, with 2 streams, demonstrated high sensitivity and specificity with the endoscopic images. It obtained better detection performance than the currently used methods based on the same datasets and has great application prospects in assisting endoscopists to distinguish esophageal lesion subclasses.

Pre-clinical characterization of PKC412, a multi-kinase inhibitor, against colorectal cancer cells.

The potential effect of PKC412, a small molecular multi-kinase inhibitor, in colorectal cancer (CRC) cells was evaluated here. We showed that PKC412 was cytotoxic and anti-proliferative against CRC cell lines (HT-29, HCT-116, HT-15 and DLD-1) and primary CRC cells. PKC412 provoked caspase-dependent apoptotic death, and induced G2-M arrest in the CRC cells. AKT activation was inhibited by PKC412 in CRC cells. Reversely, expression of constitutively-active AKT1 (CA-AKT1) decreased the PKC412's cytotoxicity against HT-29 cells. We propose that Bcl-2 could be a primary resistance factor of PKC412. ABT-737, a Bcl-2 inhibitor, or Bcl-2 siRNA knockdown, dramatically potentiated PKC412's lethality against CRC cells. Forced Bcl-2 over-expression, on the other hand, attenuated PKC412's cytotoxicity. Significantly, PKC412 oral administration suppressed AKT activation and inhibited HT-29 tumor growth in nude mice. Mice survival was also improved with PKC412 administration. These results indicate that PKC412 may have potential value for CRC treatment.

Gastrin acting on the cholecystokinin2 receptor induces cyclooxygenase-2 expression through JAK2/STAT3/PI3K/Akt pathway in human gastric cancer cells.

Gastrin, cholecystokinin2 receptor (CCK2R), and cyclooxygenase-2 (COX-2) have been implicated in the carcinogenesis and progression of gastric cancer. Our study demonstrated that antagonist or siRNA against CCK2R blocked amidated gastrin (G17)-induced activation of STAT3 and Akt in gastric cancer cell lines. G17-increased COX-2 expression and cell proliferation were effectively blocked by CCK2R antagonist and inhibitors of JAK2 and PI3K. In addition, knockdown of STAT3 expression significantly attenuated G17-induced PI3K/Akt activation, COX-2 expression, and cell proliferation. These results suggest that CCK2R-mediated COX-2 up-regulation via JAK2/STAT3/PI3K/Akt pathway is involved in the proliferative effect of G17 on human gastric cancer cells.

Downregulation of miR-101 in gastric cancer correlates with cyclooxygenase-2 overexpression and tumor growth.

Cyclooxygenase-2 (COX-2) plays an important role in the carcinogenesis and progression of gastric cancer. It has been demonstrated that COX-2 overexpression depends on different cellular pathways, involving both transcriptional and post-transcriptional regulation. MicroRNAs (miRNAs) are small, noncoding RNAs that function as post-transcriptional regulators. Here, we characterize miR-101 expression and its role in the regulation of COX-2 expression, which in turn, will provide us with additional insights into the potential therapeutic benefits of exogenous miR-101 for treatment of gastric cancer. Our results showed that miR-101 levels in gastric cancer tissues were significantly lower than those in the matched normal tissue (P < 0.01). Furthermore, lower levels of miR-101 were associated with increased tumor invasion and lymph node metastasis (P < 0.05). We also found an inverse correlation between miR-101 and COX-2 expression in both gastric cancer specimens and cell lines. Significant decreases in COX-2 mRNA and COX-2 levels were observed in the pre-miR-101-infected gastric cancer cells. One possible mechanism of interaction is that miR-101 inhibited COX-2 expression by directly binding to the 3'-UTR of COX-2 mRNA. Overexpression of miR-101 in gastric cancer cell lines also inhibited cell proliferation and induced apoptosis in vitro, as well as inhibiting tumor growth in vivo. These results collectively indicate that miR-101 may function as a tumor suppressor in gastric cancer, with COX-2 as a direct target.