Identification Of Gastric Cancer Research Articles

Evaluation of the detection rate of high‑grade gastric intraepithelial neoplasia using linked color imaging and white light imaging.

As an endoscopic technology for the enhancement of images, linked color imaging (LCI) performs well when used for the early detection and diagnosis of gastrointestinal cancer. However, literature data are lacking for LCI in the detection of high-grade gastric intraepithelial neoplasia. Therefore, the aim of the present study was to investigate the efficacy of LCI compared with traditional white light imaging (WLI) in the detection of high-grade gastric intraepithelial neoplasia via the comparison of detection rates between senior and junior endoscopists using both techniques. Overall, 84 lesions from 81 patients with high-grade gastric intraepithelial neoplasia diagnosed between January 2017 and December 2017 were considered. Following the exclusion of three patients with two lesions, 78 patients who had only one lesion were enrolled. The two types of endoscopy, WLI and LCI, were performed in the same patients under the same conditions. Four senior and four junior endoscopists retrospectively compared the images. The detection rate of high-grade gastric intraepithelial neoplasia was significantly higher with LCI than with WLI when performed by senior and junior endoscopists. With WLI, the detection rate obtained by senior endoscopists was significantly higher than that obtained by junior endoscopists. However, for LCI, the detection rates for junior and senior endoscopists were comparable. Interobserver agreement was good to satisfactory. These findings indicate that LCI is superior to WLI in the detection and identification of gastric cancer and provides highly accurate diagnostic results from endoscopic examinations, regardless of the experience of the endoscopist. LCI may be used to narrow the gap in the detection rate of high-grade gastric intraepithelial neoplasia between junior and senior endoscopists.

Abdominal Computed Tomography Enhanced Image Features under an Automatic Segmentation Algorithm in Identification of Gastric Cancer and Gastric Lymphoma.

To analyze the application value of CT-enhanced scanning based on artificial intelligence algorithm in the diagnosis of gastric cancer and gastric lymphoma, the CT images of 80 patients with Borrmann type IV gastric cancer or primary gastric lymphoma diagnosed by endoscopic pathology were retrospectively collected. Meanwhile, a lymph node recognition algorithm based on OTSU threshold segmentation was proposed for CT image processing. The results showed that the missed diagnosis rate of suspected lymph nodes and the missed lymph node detection rate of this algorithm were substantially lower than those of other algorithms (P < 0.05). The probability of gastric wall motility disappearance, perigastric fat infiltration, and type A enhancement pattern in the Borrmann type IV gastric cancer group was higher than that in the gastric lymphoma group, with remarkable differences (P < 0.05). There was no remarkable difference between the Borrmann type IV gastric cancer group and the gastric lymphoma group in the probability of swollen lymph nodes under the renal hilum (P > 0.05). In addition, 5the sensitivity (83.17%), specificity (95.52%), and accuracy (93.08%) of the combined detection of the three CT signs (stomach wall motility, perigastric fat infiltration, and enhancement mode) were substantially improved compared with those of a single sign (P < 0.05). To sum up, the lymph node recognition algorithm based on OTSU threshold segmentation had better performance in detecting gastric lymph nodes than traditional algorithms. The CT image characteristics of gastric wall motility, perigastric fat infiltration, and enhancement pattern based on artificial intelligence algorithms were effective indicators for distinguishing gastric cancer and gastric lymphoma.

Identification of gastric cancer with convolutional neural networks: a systematic review.

The identification of diseases is inseparable from artificial intelligence. As an important branch of artificial intelligence, convolutional neural networks play an important role in the identification of gastric cancer. We conducted a systematic review to summarize the current applications of convolutional neural networks in the gastric cancer identification. The original articles published in Embase, Cochrane Library, PubMed and Web of Science database were systematically retrieved according to relevant keywords. Data were extracted from published papers. A total of 27 articles were retrieved for the identification of gastric cancer using medical images. Among them, 19 articles were applied in endoscopic images and 8 articles were applied in pathological images. 16 studies explored the performance of gastric cancer detection, 7 studies explored the performance of gastric cancer classification, 2 studies reported the performance of gastric cancer segmentation and 2 studies analyzed the performance of gastric cancer delineating margins. The convolutional neural network structures involved in the research included AlexNet, ResNet, VGG, Inception, DenseNet and Deeplab, etc. The accuracy of studies was 77.3 – 98.7%. Good performances of the systems based on convolutional neural networks have been showed in the identification of gastric cancer. Artificial intelligence is expected to provide more accurate information and efficient judgments for doctors to diagnose diseases in clinical work.

Application of Computed Tomography Imaging in Diagnosis of Endocrine Nerve of Gastric Cancer and Nursing Intervention Effect

In this article, some parameters and characteristics of computed tomography (CT) images in patients with gastric cancer are analyzed and the application of CT images in the diagnosis of gastric cancer endocrine nerves and the impact of nursing intervention on the quality and mental state of CT images of patients with gastric cancer are discussed. First, all patients were scanned with CT, and the CT values of the normal stomach wall and all lesions at different single-energy levels were recorded separately. Second, the improved back propagation network model was applied to realize the diagnosis of gastric cancer through the analysis of various features of CT images. The effect of nursing intervention on the image quality and mental state of CT imaging of patients with gastric cancer was studied. The results show that the energy spectrum curve of CT images and the improved back propagation network model are helpful for the initial diagnosis and identification of gastric cancer. Nursing intervention has a good influence on the clinical examination, image diagnosis, and psychological state of patients with gastric cancer, and it is easy for patients to undergo image diagnosis and examination according to correct operating procedures.

基于微阵列数据的胃癌相关核心基因的挖掘和鉴定分析

基于微阵列数据的胃癌相关核心基因的挖掘和鉴定分析

Feasibility Study on Discrimination of Neo-plastic and Non-Neoplastic Gastric Tissues Using Spark Discharge Assisted Laser Induced Breakdown Spectroscopy.

Introduction: The present work is a novel in vitro study that evaluated the possibility of diagnosing neoplastic from nonneoplastic gastric tissues using spark discharge assisted laser induced breakdown spectroscopy (SD-LIBS) method. Methods: In these experiments, the low energy laser pulses ablated a tiny amount of tissue surface leading to plasma formation. Then, a spark discharge was applied to plasma in order to intensify the plasma radiation. Light emission from plasma was recorded as spectra which were analyzed. Gastric tissues of 5 people were studied through this method. Results: The SD-LIBS technique had the potential to discriminate normal and cancerous tissues based on the significant differences in the intensities of some particular elements. The comparison of normalized calcium (Ca) and magnesium (Mg) peaks of neoplastic and nonneoplastic gastric tissues could be viewed as a practical measure for tissue discrimination since Ca and Mg peaks in spectra of neoplastic were noticeably higher than nonneoplastic. Conclusion: Considering the identification of gastric cancer, the applied method in these experiments seems quite fast, noninvasive and cost-effective with respect to other conventional methods. The significant increment of specific Ca and Mg lines of neoplastic gastric tissues in comparison to the nonneoplastic ones can be considered as valuable information that might bring about tissue classification. The number of samples in this work, however, was not sufficient for a decisive conclusion and further researches is needed to generalize this idea.

Identification of Gastric Cancer from Speckle Patterns

Speckle technique is based on the light intensity distribution randomly formed when a laser light is reflected on a rough surface, creating a pattern of illuminated grains (constructively) and dark (destructive) on scales of 1 μm. When the samples are displaced or deformed, the speckle pattern is altered. In this paper we present speckle patterns obtained from samples of gastric mucosa that is physically altered for the carcinogenesis process. Biopsies were studied with different diagnoses and were grouped according to the characteristics of speckle patterns. Speckle patterns were obtained by illuminating the samples with green laser. Morphological parameters of the speckle patterns reveal existence of 3 descriptors: the average grain size, hydraulic radius and the radio of the Weddel disc, which showed a high, intermediate and low value. The comparison shows agreement between the histopathological diagnosis and the values obtained by the speckle technique, making this technique emerge as a new classification system for quantitative diagnosis of precancerous lesions.

S1928 Reprimo: A Novel Non-Invasive Biomarker for Gastric Cancer Detection

Although gastric cancer is one of the highest mortality cancers in the world, no methods for non-invasive diagnosis have been described. Aberrant hypermethylation, an epigenetic mechanism of inactivation of tumor suppressor genes, is an emerging approach to noninvasive diagnosis of gastric cancer. We have previously shown high prevalence of aberrant hypermethylation of Reprimo (RPRM) a novel tumor suppressor gene, in plasma from gastric cancer but not in plasma from healthy donors (Clin Cancer Res. 2008;14:6264-9). This finding suggested that RPRM promoter methylation could be a sensitive and specific biomarker for the non-invasive detection of gastric cancer. Here we explore in a prospective and blind fashion specificity and sensitivity of RPRM for non-invasive diagnoses of gastric cancer. Methods. We prospectively collect 83 gastric cancer patients from two hospitals and 223 healthy donors from corresponding blood banks. Detection of RPRM was perform by methylation specific PCR (MSP). We perform endoscopy in healthy donors that were RPRM(+) in plasma. Results. Aberrant hypermethylation of RPRM was identified in 67/74 (90.5%) and 75/79 (94.9%) of tumor and plasma from gastric cancer patients, respectively. Among healthy donors, methylation of RPRM was identified in 29.1% (65 of 223) of tested cases. These differences were statistically significant (p< 0.001 by Fisher's exact test). The sensibility and specificity of RPRM detection in plasma were 89% (95% CI: 81%-98%) and 67% (95% CI: 58%-75%) respectively. We perform endoscopy in 5 RPRM positive healthy donors, and no cancer was found. Only one healthy donor was diagnosed with chronic gastritis. Discussion. Our data indicate that detection of RPRM promoter methylation in cell free plasma DNA is a promissory method for non-invasive detection of gastric cancer. RPRM could be included in the serologic biopsy along with pepsinogen and gastrin 17 not only for the identification of gastric atrophy, the precursor lesion of gastric cancer but also for direct identification of gastric cancer. Supported by FONDECYT grant 1080563 from Government of Chile