Esophageal cancer is a serious threat to the health of Chinese people. The key to solve this problem is early diagnosis and early treatment, and the most important method is endoscopic screening. The rapid development of artificial intelligence (AI) technology makes its application and research in the field of digestive endoscopy growing, and it is expected to become the "right-hand man" for endoscopists in the early diagnosis of esophageal cancer. Currently, the application of multimodal and multifunctional AI systems has achieved good performance in the diagnosis of superficial esophageal squamous cell carcinoma and precancerous lesions. This study summarized and reviewed the research progress of AI in the diagnosis of superficial esophageal squamous cell carcinoma and precancerous lesions, and also explored its development direction in the future.
ObjectiveTo analyze the tumor characteristics of colorectal cancer in the current version of Database from Colorectal Cancer (DACCA).MethodsThe DACCA version was the updated version on September 26, 2019. The data items included: date of surgery, precancerous lesions, cancer family, tumor site, distance to the dentate line, morphology of tumor, size, position, happening and origination, differentiation, pathology of tumor, Ki-67 of protein, complications (included obstruction, intussusception, perforation, pain, edema, and hemorrhage) were analyzed for the characteristics of each selected data item.ResultsA total of 11 898 analyzable data rows were obtained by screening the DACCA database. Among the 11 898 pieces of data, the effective data of precancerous lesions was 1 275, including 541 (42.4%) with precancerous lesions, and 734 (57.6%) without precancerous lesions. There were 1 116 valid data on cancer families, and 761 (6.4%) had a family history of cancer. The Ki-67 index had a total of 1 893 valid data, which ranged form 0 to 95% [(59.0±20.1) %]. According to the classification of tumor occurrence, the primary colorectal cancer accounted for the vast majority (92.8%), and the metastatic colorectal cancer was the least (0.3%). According to the primary and multiple primary, respectively analysis of tumor site, distance to the dentate line, morphology of tumor, size, position, differentiation, and pathology of tumor showed that, most tumor’s position were in the rectum (76.9%, 41.9%), the most common morphology was ulcers (42.4%, 51.5%), the most tumors were located around the wall of intestine (44.6%, 35.0%), the degree of differentiation was mostly moderate (65.4%, 61.3%), most of the tumor pathologies were adenocarcinoma (77.8%, 64.0%).ConclusionA more accurate and detailed analysis of colorectal cancer tumor characteristics by the DACCA database is helpful for determining the diagnosis and treatment plan in clinical work, judging the prognosis, and so on.
Objective To evaluate the diagnostic accuracy of human papillomavirus test for cervical neoplasia. Methods The Cochrane Library (Issue 2, 2010), Cochrane Central Register of Controlled Trials (Issue 2, 2010), and the following databases as CBMdisc, CNKI, MEDLINE, PubMed, and EMbase were all searched from their establishment to June 2010 to get all the randomized control trials (RCTs), and the relevant magazines and the references of the included studies were also searched. The screening, data extraction and quality assessment were conducted in accordance with the inclusion and exclusion criteria by two reviewers independently. The software Metadisc 1.4 was used to perform meta-analyses, and the forest plots and SROC curves were drewn with the RevMan 5.0 software. Results A total of 7 RCTs involving 171 604 subjects were included. The meta-analyses showed, the sensitivity of the HPV test for detecting cervical neoplasia (CIN) was higher than that of the conventional cytology test; the difference in sensitivity for detecting CIN in or above second grade was only found between the test of HPV combined with cervical cytology and the test of conventional cytology (Plt;0.00001), but the HPV test obviously lowered its diagnostic specificity. Among the following three tests for diagnosing CIN, such as, the single test of HPV, the combined test of HPV and cervical cytology, and the test of HPV followed by cytology shunting, the statistic differences compared with the conventional cytology test were found (Plt;0.01) except the last test (P=0.41) which had no difference in diagnosing CIN in or above the first grade. Conclusion The current evidence indicates that, compared with the conventional cytology test, the HPV combined with the cytology test can improve the sensitivity for diagnosing CIN in or above the second grade, but the HPV test cannot improve the specificity for cervical neoplasia. The application of human papillomavirus test for detecting cervical neoplasia needs to be further studied.
The DNA content, cellular ultrastructure and the expression of blood group Y antigen and immunosuppressive acidic protein-2(IAP-2) were observed in normal breast, cystic hyperplasia of breast and breast cancer. The results showed: the results observed in the cells of cystic hyperplasia with epithelial proliferation grade Ⅰ were similar to those in normal breast cells. The DNA content increased, the hypoplasia and dedifferentiation features in some structures of cellular membrane and nucleus were observed, and the abnormal antigens expressed in part of the atypical hyperplasic cells. The DNA content and ultrastructure in a part of cells with aypical hyperplasia grade Ⅲ were similar to those in the cells of breast cancer grade Ⅰ. The results indicated that in the couse of atypical hyperplasia, the biological abnormalities and its extent of those cells were closely related to the differentiation extent, the developing tendency and the risk of canceration of the cystic hyperplasia of breast.
Esophageal cancer is an aggressive malignancy with high morbidity and poor prognosis. Symptoms of early esophageal cancer are insidious and difficult to detect, while advanced esophageal obstruction, lesion infiltration and metastasis seriously affect patients’ quality of life. Early detection and treatment can help to increase the survival chance of patients. Recently, artificial intelligence (AI) has shown remarkable success in diagnosis of esophageal cancer, highlighting the great potential of new AI-assisted diagnostic modalities. This paper aims to review recent progress of AI in the diagnosis of esophageal cancer and to prospect its clinical application.
Objective To investigate the variety of telomerase activity in the course of liver cancer development, and the possibility of using telomerase as a marker of HCC. Methods Human liver specimens, comprising 22 HCC and adjacent peritumoral tissues, 12 liver cirrhosistissues, 6 nodulat regenerative hyperplasia (NRH) tissues and 10 normal liver tissues, were examined for telomerase activity by TRAP assay based on PCR. Results Twenty of 22 HCC and 14 of 22 adjacent tissue specimens were positive for telomerase activity with a positive rate of 90.9% and 63.6% respectively. Ten of 12 liver cirrhosis tissues were positive with a positive rate of 83.3%. 5 of 6 NRH were positive with a positive rate of 83.3%. Telomerase activity was negative in 10 normal liver tissues. Conclusion Telomerase may occur in the progress of hepatocarcinogenesis. Telomerase can be used as a tumor marker of HCC.
Autofluorescence has great advantage on detecting premalignant lesions and early cancers which are not detectable by conventional white light endoscopy (WLE). In this review, the recent advances in autofluorescence for diagnosis of precancerous lesions and early cancers are presented. Varieties of endogenous fluorophores in biological tissues, the potential mechanisms of the autofluorescence differences between normal and abnormal tissues, the selection of light source and optimal excitation wavelengths, and effective algorithms for processing autofluorescence data are highlighted. Finally, the shortages and improvement directions of autofluorescence technique for the diagnosis of precancerous lesions and early cancers are briefly discussed.
目的 探讨贵州地区进行宫颈癌机会性筛查的价值。 方法 回顾性分析2010年11月－2011年10月贵州省人民医院妇科门诊及住院进行宫颈癌机会性筛查的1 842例患者资料，筛查方法包括液基细胞学技术、宫颈刮片、人乳头瘤病毒（HPV）分型检测、HPV第2代捕获杂交法检测、阴道镜检查，以病理确诊宫颈癌前病变及宫颈癌。 结果 贵州地区女性人群的HPV平均感染率为21.87%。共检出宫颈癌前病变39例（2.12%），宫颈癌2例（0.11%）。 结论 医院内就诊女性宫颈病变检出率高，应高度重视其机会性筛查，有助于早期干预治疗。