Objective:To develop and validate artificial intelligence (AI) models based on deep learning for precise boundary identification of early gastric cancer (EGC) in narrow-band imaging (NBI) and near focus narrow-band imaging (NF-NBI) endoscopic images.Methods:Endoscopic submucosal dissection (ESD) images from 282 patients diagnosed as having EGC by postoperative pathology at the Department of Gastroenterology, the First Affiliated Hospital of Soochow University were retrospectively collected from February 2016 to June 2024. The images were randomly divided into the training set and the validation set at an approximate 8∶2 ratio. In the NBI modality, 980 images from 171 patients were used for training, 235 images from 61 patients were used for validation. In the NF-NBI modality, 1 273 images from 128 patients were used for training, and 373 images from 35 patients were used for validation. This study trained a total of six convolutional neural network (CNN) models: two independent CNN1 models, two independent CNN2 models, and two fused CNN3 models. Using expert-delineated EGC boundaries based on post-ESD pathological findings as the gold standard, the intersection over union (IOU) value of the CNN3 models was compared against junior (<5 years experience), mid-level (5-10 years), and senior (>10 years) endoscopists.Results:In NBI validation set, the IOU value of CNN3 model was significantly higher than that of junior (0.732 VS 0.489, Z=11.528, P<0.001) and mid-level endoscopists (0.732 VS 0.521, Z=11.184, P<0.001). However, no significant difference was observed between CNN3 model and senior endoscopists (0.732 VS 0.739, Z=0.593, P=0.554). Similarly, in NF-NBI validation set, CNN3 model outperformed junior (0.757 VS 0.537, Z=15.944, P<0.001) and mid-level endoscopists (0.757 VS 0.597, Z=9.722, P<0.001), while matching senior endoscopists (0.757 VS 0.769, Z=0.854, P=0.394). Conclusion:The fused CNN3 model achieves senior expert-level accuracy in delineating EGC boundaries in both NBI and NF-NBI images, demonstrating potential to assist less-experienced endoscopists in precise identification of EGC boundaries.

Objective:To develop and validate artificial intelligence (AI) models based on deep learning for precise boundary identification of early gastric cancer (EGC) in narrow-band imaging (NBI) and near focus narrow-band imaging (NF-NBI) endoscopic images.Methods:Endoscopic submucosal dissection (ESD) images from 282 patients diagnosed as having EGC by postoperative pathology at the Department of Gastroenterology, the First Affiliated Hospital of Soochow University were retrospectively collected from February 2016 to June 2024. The images were randomly divided into the training set and the validation set at an approximate 8∶2 ratio. In the NBI modality, 980 images from 171 patients were used for training, 235 images from 61 patients were used for validation. In the NF-NBI modality, 1 273 images from 128 patients were used for training, and 373 images from 35 patients were used for validation. This study trained a total of six convolutional neural network (CNN) models: two independent CNN1 models, two independent CNN2 models, and two fused CNN3 models. Using expert-delineated EGC boundaries based on post-ESD pathological findings as the gold standard, the intersection over union (IOU) value of the CNN3 models was compared against junior (<5 years experience), mid-level (5-10 years), and senior (>10 years) endoscopists.Results:In NBI validation set, the IOU value of CNN3 model was significantly higher than that of junior (0.732 VS 0.489, Z=11.528, P<0.001) and mid-level endoscopists (0.732 VS 0.521, Z=11.184, P<0.001). However, no significant difference was observed between CNN3 model and senior endoscopists (0.732 VS 0.739, Z=0.593, P=0.554). Similarly, in NF-NBI validation set, CNN3 model outperformed junior (0.757 VS 0.537, Z=15.944, P<0.001) and mid-level endoscopists (0.757 VS 0.597, Z=9.722, P<0.001), while matching senior endoscopists (0.757 VS 0.769, Z=0.854, P=0.394). Conclusion:The fused CNN3 model achieves senior expert-level accuracy in delineating EGC boundaries in both NBI and NF-NBI images, demonstrating potential to assist less-experienced endoscopists in precise identification of EGC boundaries.

The five core indicators(the case mix index, the proportion of level-4 surgery, the proportion of technical service income in medical income, the proportion of personnel expenditure in business expenditure, and the proportion of fixed part in personnel salary) and target values determined by the pilot goal of high-quality development of high-level public hospitals jointly built by National Health Commission and Provincial Government had become the core indicators for evaluating the quality and efficiency of public hospital development. The authors proposed the optimization and improvement measures for the five core indicators one by one from the internal reform and innovation in hospitals, as well as the synergetic development and governance of " insurance-medical-medicine linkage", combined with the current situation of a pilot hospital. The authors also proposed the starting points and driving force for promoting the high-quality development of public hospitals through the synergetic development and governance of " insurance-medical-medicine linkage", including implementing government investment responsibilities, streamlining the price evaluation of medical services, deepening the reform of medical insurance payment, accelerating the expansion of drug and consumable procurement, and promoting the application of advanced technologies and products, in order to provide reference for the in-depth promotion of high-quality development of public hospitals.

Objective:To compare the differences in the detection rates of cytomegalovirus (CMV) infection between the left and right colons for guiding endoscopic biopsy-sites.Methods:The cases of colonic CMV infection confirmed by histology at the Peking Union Medical College Hospital from July 2015 to July 2018 were collected and analyzed. Splenic curvature was used as the dividing point between the left and right colons. The CMV inclusions were identified histologically, and the CMV infected cells were detected using immunohistochemistry (EnVision method). The numbers of infected cells in the left and right colons were compared by histological and immunohistochemical results. A total of 731 patients were identified. Ten of the 731 patients had histological specimens of both left and right colons and were confirmed with CMV EnVision immunohistochemical study. There were 25 biopsy or resection specimens. Seven patients were male and 3 were female, and their ages ranged from 29 to 66 years, with a median age of 55 years. All of the 10 patients were also diagnosed with ulcerative colitis.Results:The number of the cells infected with CMV in the left colon was 115 (1-41), while that in the right colon was 76 (0-51). In 8/10 cases, the number of CMV infected cells in the left colon was more than that in the right colon.Conclusions:The study on the biopsies and resection specimens suggests that CMV infection is mostly present in the left colon. The left colon thus might be an important endoscopic biopsy-site for the cases with suspicion of CMV infection.

OBJECTIVETo explore the molecular basis of an individual with A subtype of the ABO blood group.

METHODSThe ABO antigen and serum antibody of the proband and his parents and sister were detected by a serological method. The whole coding regions of the ABO gene were amplified by PCR and subjected to bidirectional sequencing.

RESULTSRed blood cells of the proband showed mixed field agglutination with anti-A but did not agglutinate with anti-B, and his serum did not agglutinate with A and O cells but with B cells. The proband was identified as an Aw phenotype. Heterozygous status of 1A/G, 106G/T, 188A/G, 189C/T, 220C/T, 261G/del, 297A/G, 467C/T, 646A/T, and 681A/G of the coding region of the ABO gene were identified by directly sequencing of the proband. The serological characteristics and nucleotide sequences of the mother were similar to those of the proband. However, the ABO genotypes of his father and sister were B101/O02 and O02/O02. The proband therefore has carried an O02 allele and a novel allele. Compared with A102, the novel allele contains 1A>G, which resulted in translation-initiator code change and was nominated as Aw43 by dbRBC of NCBI.

CONCLUSIONAn Aw43 subtype has been identified for the first time, which may be attributed to the 1A>G and 467C>T variants on the α1,3-N-acetyl-galactosaminyltransferase gene.

ABO Blood-Group System ; genetics ; Adult ; Alleles ; Female ; Genetic Variation ; genetics ; Genotype ; Humans ; Male

OBJECTIVETo study the effects of intense electromagnetic pulse(EMP) on the biological effects of mitochondrial membrane.

METHODRat liver mitochondrial suspension was exposed to EMP at 60 kV/m level. The changes of membrane lipid fluidity and membrane protein mobility were detected by ESR and spin label technique. Malondialdehyde(MDA) was detected by spectrophotometer.

RESULTSThe mobility of membrane protein decreased significantly(P < 0.05). Correlation time (tau c) of control group was (0.501 +/- 0.077) x 10(-9)s, and tau c of EMP group was (0.594 +/- 0.049) x 10(-9)s, indicating that the mobility of protein was restricted. The fluidity of mitochondrial membrane increased significantly(P < 0.05) at the same time. Order parameter(S) of mitochondrial membrane lipid in control group was 0.63 +/- 0.01, while S of EMP group was 0.61 +/- 0.01(P < 0.05). MDA decreased significantly.

CONCLUSIONThe mobility and lipid peroxidation of mitochondrial membrane may be disturbed after EMP exposure.

Animals ; Electromagnetic Phenomena ; Lipid Peroxidation ; radiation effects ; Membrane Fluidity ; radiation effects ; Mitochondria, Liver ; metabolism ; radiation effects ; Mitochondrial Membranes ; metabolism ; radiation effects ; Rats