In order to truly obtain the feature extraction of vibration signals under the strong background noise, the analysis and improvement of empirical mode decomposition （EMD） is carried on. After that, the improved EMD ...In order to truly obtain the feature extraction of vibration signals under the strong background noise, the analysis and improvement of empirical mode decomposition （EMD） is carried on. After that, the improved EMD is applied to the feature extraction of vehicle vibration signals. First, the multi-autocorrelation method is adopted in each input signal,so the noise is reduced effectively. Then, EMD is used to deal with these signals,and the intrinsic mode functions （IMFs） are obtained. Finally, for obtaining the feature information of these signals, the Hilbert transformation and the spectrum analysis are performed in some IMFs. Theoretical analysis and ex- periment verify the effectiveness of the method, which are valuable reference for the same engineering problems.展开更多
AIM To analyse the clinical features of patients with the serrated lesions in the upper gastrointestinal tract(UPGI) tract.METHODS Patients who underwent routine esophagogastroduodenoscopy(EGD) at the Digestive Endosc...AIM To analyse the clinical features of patients with the serrated lesions in the upper gastrointestinal tract(UPGI) tract.METHODS Patients who underwent routine esophagogastroduodenoscopy(EGD) at the Digestive Endoscopy Centre of General Hospital, Tianjin Medical University between january 2011 and December 2015 were consecutively recruited. Patients with UPGI serrated lesions were consecutively identified. The patients' demographics and histopathology were recorded. The colorectal findings for patients who underwent colonoscopy simultaneously or within six months were also extracted from the colonoscopy database. In addition, we analyseddifferences in colorectal neoplasia detection between the study patients and randomly selected patients matched for age and gender who did not exhibit serrated lesions and who also underwent colonoscopy in the same period.RESULTS A total of 21 patients out of 98746 patients(0.02%) who underwent EGD were confirmed to have serrated lesions with predominantly crenated, sawtooth-like configurations. The mean age of the 21 patients was(55.3 ± 17.2) years, and 11 patients were male(52.4%). In terms of the locations of the serrated lesions, 17 were found in the stomach(including 3 in the cardia, 9 in the corpus and 5 in the antrum), 3 were found in the duodenum, and 1 was found in the esophagus. Serrated lesions were found in different mucosal lesions, with 14 lesions were detected in polyps(8 hyperplastic polyps and 6 serrated adenomas with low grade dysplasia), 3 detected in Ménétrier gastropathy, 3 detected in an area of inflammation or ulcer, and 1 detected in the intramucosal carcinoma of the duodenum. In addition, colonoscopy data were available for 18 patients, and a significantly higher colorectal adenoma detection rate was observed in the UPGI serrated lesions group than in the randomly selected age- and gender-matched group without serrated lesions who also underwent colonoscopy in the same period(38.9% vs 11.1%, OR = 5.091, 95%CI: 1.534-16.890, P = 0.010). The detection rate of advanced adenoma was also higher in the UPGI serrated lesions group(22.2% vs 4.2%, OR = 6.571, 95%CI: 1.322-32.660, P = 0.028).CONCLUSION Serrated lesions in the UPGI were detected in various mucosal lesions with different pathological morphologies. Moreover colonoscopy is recommended for the detection of concurrent colorectal adenoma for these patients.展开更多
Automatic gastrointestinal(GI)tract disease recognition is an important application of biomedical image processing.Conventionally,microscopic analysis of pathological tissue is used to detect abnormal areas of the GI ...Automatic gastrointestinal(GI)tract disease recognition is an important application of biomedical image processing.Conventionally,microscopic analysis of pathological tissue is used to detect abnormal areas of the GI tract.The procedure is subjective and results in significant inter-/intraobserver variations in disease detection.Moreover,a huge frame rate in video endoscopy is an overhead for the pathological findings of gastroenterologists to observe every frame with a detailed examination.Consequently,there is a huge demand for a reliable computer-aided diagnostic system(CADx)for diagnosing GI tract diseases.In this work,a CADx was proposed for the diagnosis and classification of GI tract diseases.A novel framework is presented where preprocessing(LAB color space)is performed first;then local binary patterns(LBP)or texture and deep learning(inceptionNet,ResNet50,and VGG-16)features are fused serially to improve the prediction of the abnormalities in the GI tract.Additionally,principal component analysis(PCA),entropy,and minimum redundancy and maximum relevance(mRMR)feature selection methods were analyzed to acquire the optimized characteristics,and various classifiers were trained using the fused features.Open-source color image datasets(KVASIR,NERTHUS,and stomach ULCER)were used for performance evaluation.The study revealed that the subspace discriminant classifier provided an efficient result with 95.02%accuracy on the KVASIR dataset,which proved to be better than the existing state-of-the-art approaches.展开更多
BACKGROUND There is a lack of robust prognostic markers for upper gastrointestinal(GI)tract cancers,including esophageal,gastric,and esophagogastric junction cancers.T cell immunoglobulin and mucin-domain containing-3...BACKGROUND There is a lack of robust prognostic markers for upper gastrointestinal(GI)tract cancers,including esophageal,gastric,and esophagogastric junction cancers.T cell immunoglobulin and mucin-domain containing-3(TIM3)plays a key immunomodulatory role and is linked to the prognosis of various cancers.However,the significance of TIM3 in upper GI tract tumors is still uncertain.AIM To investigate the prognostic value of TIM3 expression in upper GI tract tumors.METHODS A literature search was conducted on the PubMed,Embase,and Web of Science databases for relevant studies published until June 2023.After screening and quality assessment,studies that met the criteria were included in the metaanalysis.Statistical methods were used for the pooled analysis to assess the association of TIM3 expression in upper GI tract tumors with the prognosis and clinicopathological parameters.The results were reported with the hazard ratio(HR)and 95%confidence interval(CI).RESULTS Nine studies involving 2556 patients with upper GI tract cancer were included.High TIM3 expression was associated with a worse prognosis in upper GI tract cancer(HR:1.17,95%CI:1.01-1.36).Positive expression of TIM3 in gastric cancer was correlated with the T and N stage,but the difference was not statistically significant.However,TIM3 overexpression was significantly correlated with the TNM stage(odds ratio:1.21,95%CI:0.63-2.33;P<0.05).TIM3 expression showed no association with the other clinicopathological parameters.CONCLUSION High expression of TIM3 in the upper GI tract cancer is associated with a worse prognosis and advanced T or N stages,indicating its potential value as a prognostic biomarker.These findings may provide a basis for the personalized treatment of upper GI tract cancers.展开更多
基金Supported by the Scientific Research Foundation for the Imported Talents(YKJ201014)~~
文摘In order to truly obtain the feature extraction of vibration signals under the strong background noise, the analysis and improvement of empirical mode decomposition （EMD） is carried on. After that, the improved EMD is applied to the feature extraction of vehicle vibration signals. First, the multi-autocorrelation method is adopted in each input signal,so the noise is reduced effectively. Then, EMD is used to deal with these signals,and the intrinsic mode functions （IMFs） are obtained. Finally, for obtaining the feature information of these signals, the Hilbert transformation and the spectrum analysis are performed in some IMFs. Theoretical analysis and ex- periment verify the effectiveness of the method, which are valuable reference for the same engineering problems.
基金Supported by the National Natural Science Foundation of China,No.81300272,No.81470796(to Cao HL)and No.81570478(to Wang BM)
文摘AIM To analyse the clinical features of patients with the serrated lesions in the upper gastrointestinal tract(UPGI) tract.METHODS Patients who underwent routine esophagogastroduodenoscopy(EGD) at the Digestive Endoscopy Centre of General Hospital, Tianjin Medical University between january 2011 and December 2015 were consecutively recruited. Patients with UPGI serrated lesions were consecutively identified. The patients' demographics and histopathology were recorded. The colorectal findings for patients who underwent colonoscopy simultaneously or within six months were also extracted from the colonoscopy database. In addition, we analyseddifferences in colorectal neoplasia detection between the study patients and randomly selected patients matched for age and gender who did not exhibit serrated lesions and who also underwent colonoscopy in the same period.RESULTS A total of 21 patients out of 98746 patients(0.02%) who underwent EGD were confirmed to have serrated lesions with predominantly crenated, sawtooth-like configurations. The mean age of the 21 patients was(55.3 ± 17.2) years, and 11 patients were male(52.4%). In terms of the locations of the serrated lesions, 17 were found in the stomach(including 3 in the cardia, 9 in the corpus and 5 in the antrum), 3 were found in the duodenum, and 1 was found in the esophagus. Serrated lesions were found in different mucosal lesions, with 14 lesions were detected in polyps(8 hyperplastic polyps and 6 serrated adenomas with low grade dysplasia), 3 detected in Ménétrier gastropathy, 3 detected in an area of inflammation or ulcer, and 1 detected in the intramucosal carcinoma of the duodenum. In addition, colonoscopy data were available for 18 patients, and a significantly higher colorectal adenoma detection rate was observed in the UPGI serrated lesions group than in the randomly selected age- and gender-matched group without serrated lesions who also underwent colonoscopy in the same period(38.9% vs 11.1%, OR = 5.091, 95%CI: 1.534-16.890, P = 0.010). The detection rate of advanced adenoma was also higher in the UPGI serrated lesions group(22.2% vs 4.2%, OR = 6.571, 95%CI: 1.322-32.660, P = 0.028).CONCLUSION Serrated lesions in the UPGI were detected in various mucosal lesions with different pathological morphologies. Moreover colonoscopy is recommended for the detection of concurrent colorectal adenoma for these patients.
基金This research was supported by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0012724,The Competency Development Program for Industry Specialist)and the Soonchunhyang University Research Fund.
文摘Automatic gastrointestinal(GI)tract disease recognition is an important application of biomedical image processing.Conventionally,microscopic analysis of pathological tissue is used to detect abnormal areas of the GI tract.The procedure is subjective and results in significant inter-/intraobserver variations in disease detection.Moreover,a huge frame rate in video endoscopy is an overhead for the pathological findings of gastroenterologists to observe every frame with a detailed examination.Consequently,there is a huge demand for a reliable computer-aided diagnostic system(CADx)for diagnosing GI tract diseases.In this work,a CADx was proposed for the diagnosis and classification of GI tract diseases.A novel framework is presented where preprocessing(LAB color space)is performed first;then local binary patterns(LBP)or texture and deep learning(inceptionNet,ResNet50,and VGG-16)features are fused serially to improve the prediction of the abnormalities in the GI tract.Additionally,principal component analysis(PCA),entropy,and minimum redundancy and maximum relevance(mRMR)feature selection methods were analyzed to acquire the optimized characteristics,and various classifiers were trained using the fused features.Open-source color image datasets(KVASIR,NERTHUS,and stomach ULCER)were used for performance evaluation.The study revealed that the subspace discriminant classifier provided an efficient result with 95.02%accuracy on the KVASIR dataset,which proved to be better than the existing state-of-the-art approaches.
基金Supported by the Science and Technology Research Project of Colleges and Universities of Hebei Province,No.QN2020234the Precision Medicine Joint Cultivation Fund Project of Natural Science Foundation of Hebei Province,No.H2021402007+1 种基金the Clinical Medicine Talent Cultivation Project of Health Commission of Hebei Province,No.2020the Medical Science Research Project of Health Commission of Hebei Province,No.20211392.
文摘BACKGROUND There is a lack of robust prognostic markers for upper gastrointestinal(GI)tract cancers,including esophageal,gastric,and esophagogastric junction cancers.T cell immunoglobulin and mucin-domain containing-3(TIM3)plays a key immunomodulatory role and is linked to the prognosis of various cancers.However,the significance of TIM3 in upper GI tract tumors is still uncertain.AIM To investigate the prognostic value of TIM3 expression in upper GI tract tumors.METHODS A literature search was conducted on the PubMed,Embase,and Web of Science databases for relevant studies published until June 2023.After screening and quality assessment,studies that met the criteria were included in the metaanalysis.Statistical methods were used for the pooled analysis to assess the association of TIM3 expression in upper GI tract tumors with the prognosis and clinicopathological parameters.The results were reported with the hazard ratio(HR)and 95%confidence interval(CI).RESULTS Nine studies involving 2556 patients with upper GI tract cancer were included.High TIM3 expression was associated with a worse prognosis in upper GI tract cancer(HR:1.17,95%CI:1.01-1.36).Positive expression of TIM3 in gastric cancer was correlated with the T and N stage,but the difference was not statistically significant.However,TIM3 overexpression was significantly correlated with the TNM stage(odds ratio:1.21,95%CI:0.63-2.33;P<0.05).TIM3 expression showed no association with the other clinicopathological parameters.CONCLUSION High expression of TIM3 in the upper GI tract cancer is associated with a worse prognosis and advanced T or N stages,indicating its potential value as a prognostic biomarker.These findings may provide a basis for the personalized treatment of upper GI tract cancers.
