ABSTRACT
Objective@#To examine the value and clinical application of convolutional neural network in pathological diagnosis of metastatic lymph nodes of gastric cancer.@*Methods@#Totally 124 patients with advanced gastric cancer who underwent radical gastrectomy plus D2 lymphadenectomy at Affiliated Hospital of Qingdao University from July 2016 to December 2018 were selected in the study. According to the chronological order, the first 80 cases were served as learning group. The remaining 44 cases were served as verification group. There were 45 males and 35 females in the study group, with average age of 57.6 years. There were 29 males and 15 females in the validation group, with average age of 9.2 years. The pre-training convolutional neural network architecture Resnet50 was trained and fine-tuned by 21 352 patches with cancer areas and 14 997 patches without cancer areas in the training group. A total of 78 whole-slide image served as a test dataset including positive (n=38) and negative (n=40) lymph nodes. The convolutional neural network computer-aided detection (CNN-CAD) system was used to analyze the ability of convolutional neural network system to screen metastatic lymph nodes at the level of slice by setting threshold, and evaluate the system′s classification accuracy by calculating its sensitivity, specificity, positive predictive value, negative predictive value and area under the receiver operating characteristic curve (AUC).@*Results@#The classification accuracy of CNN-CAD system at slice level was 100%.The AUC for the CNN-CAD system was 0.89. The sensitivity was 0.778, specificity was 0.995, overall accuracy was 0.989. Positive and negative predictive values were 0.822 and 0.994, respectively. The CNN-CAD system achieved the same classification results as pathologists.@*Conclusions@#The CNN-CAD system has been constructed to distinguished benign and malignant lymph node slides with high accuracy and specificity. It could achieve the similar classification results as pathologists.
ABSTRACT
Objective@#To investigate the clinical significance of high definition (HD) MRI rectal lymph node aided diagnostic system based on deep neural network.@*Methods@#The research selected 301 patients with rectal cancer who underwent pelvic HD MRI and reported pelvic lymph node metastasis from July 2016 to December 2017 in Affiliated Hospital of Qingdao University. According to the chronological order, the first 201 cases were used as learning group. The remaining 100 cases were used as verification group. There were 149 males (74.1%) and 52 females in the study group, with an average age of 58.8 years. There were 76 males (76.0%) and 24 females in the validation group, with an average age of 60.2 years. Firstly, Using deep learning technique, researchers trained the 12 060 HD MRI lymph nodes images data of learning group with convolution neural network to simulate the judgment process of radiologists, and established an artificial intelligence automatic recognition system for metastatic lymph nodes of rectal cancer. Then, 6 030 images of the validation group were clinically validated. Artificial intelligence and radiologists simultaneously diagnosed all cases of HD MRI images and made the diagnosis results of metastatic lymph node. Receiver operating characteristic (ROC) curve and area under curve (AUC) were used to compare the diagnostic level of them.@*Results@#After continuous iteration training of the learning group data, the loss function value of artificial intelligence decreased continuously, and the diagnostic error decreased continuously. Among the 6 030 images of verification group, 912 images were considered to exist metastatic lymph nodes in radiologists′ diagnosis and 987 in artificial intelligence diagnosis. There were 772 images having identical diagnostic results of lymph node location and number of metastases with the two methods. Compared with manual diagnosis, the AUC of the intelligent platform was 0.886 2, the diagnostic time of a single case was 10 s, but the average diagnostic time of doctors was 600 s.@*Conclusion@#The HD MRI lymph node automatic recognition system based on deep neural network has high accuracy and high efficiency, and has the clinical significance of auxiliary diagnosis.
ABSTRACT
Objective@#To observe the clinical course of children with juvenile-onset recurrent respiratory papillomatosis (JORRP) until 14 years old.@*Methods@#The clinical data of one hundred and twenty cases treated between Januray 1, 2002 and September 30, 2017 in Beijing Tongren Hospital were analyzed retrospectively. Excluding the deaths and the lost, patients who could be ≥ 5 years without recurrence, were defined as the cured group, and < 5 years with recurrence defined as the recurrent group. Furthermore, using statistical methods to analyze the differences of the age of initial operation, total number of operations, invasive lesion, HPV infection, tracheotomy, airway dissemination after tracheotomy and time of tube wear between the two groups.@*Results@#One hundred and three cases were followed up, except for the six deaths.Numbers of operations in eight cases were ≤2, and ≥3 in eighty nine cases.Peak of the primary surgical age were about 4.5 years old, while the self-healing trend occurred at nine years old. In the cured group, forty three cases were cured, with a curative rate of 41.7% (43/103), and there were all fifty four survivors in the recurrent group.The total number of operations, invasive cases, HPV positive cases and the G score of hoarseness in the recurrent group were higher than those in the cured group (F=13.02, χ2=13.04, χ2=17.37, Z=-4.59, P<0.05). The number of tracheal dissemination caused by tracheotomy in the recurrent group (66.7%, 27.8%)was more than that in the cured group (χ2=16.01, P<0.05). Compared with the time of wearing a tracheostomy tube in cured group, the recurrent group was longer ((3.4±3.1) years vs (8.3±6.7) years, χ2=7.19, P<0.05).@*Conclusions@#41.7% of the patients had no relapse for at least five years.There exsisted differences between the cured and recurrent group in the following aspects: the total numbers of surgery, the agression of the lesions, tracheal intratracheal dissemination after tracheotomy, the time of tracheotomy, the HPV typing and the G grading of hoarseness.
ABSTRACT
<p><b>OBJECTIVE</b>To investigate the relationship between extranodal tumor deposits and prognosis in patients with colorectal cancer.</p><p><b>METHODS</b>The literatures on extranodal tumor deposits and postoperative survival rate in patients with colorectal cancer published at home and abroad from 1990 to 2014 were retrieved in 15 English literature databases such as MEDLINE/PubMed, Web of Science, Directory of Open Access Journals(DOAJ), SpringerLink and Chinese literature databases such as Chinese Biomedical Literature Database CD-ROM, China National Knowledge Infrastructure (CNKI) Database with the internet platform of Yonsei University Library. After screening for inclusion, data extraction and quality assessment, meta-analysis was conducted by the Review Manager 5.3 software.</p><p><b>RESULTS</b>There were 10 studies meeting the inclusion criteria for meta-analysis. The total sample size of the studies was 4 068 cases with ENTD(+) 727 cases, while ENTD(-) 3 341 cases. Meta analysis showed that 5-year overall survival rate and 5-year relapse-free survival rate were significantly lower in ENTD(+) group than those in ENTD(-) group (OR 0.27, 0.23; 95% CI:0.18 to 0.43, 0.16 to 0.34 respectively, both P=0.000); the 5-year overall survival rates were both significantly lower in ENTD(+) group as compared to ENTD(-) group for patients with N0 and N(+) colorectal cancer (both P<0.05).</p><p><b>CONCLUSION</b>Extranodal tumor deposits is a poor prognostic factor of patients with colorectal cancer.</p>
Subject(s)
Humans , Colorectal Neoplasms , Diagnosis , Pathology , Disease-Free Survival , Neoplasm Recurrence, Local , Prognosis , Survival RateABSTRACT
OBJECTIVE:To establish the method for the determination of plasma concentration of magnesium isoglycyrrhiz-inate in portal vein and peripheral venous blood of patients underwent liver resection,to further validate and evaluate pharmacoki-netic characteristics,rational and safe use of drugs in the clinic. METHODS:31 patients underwent liver resection in our hospital during Oct. 2014-Mar. 2015 were given magnesium isoglycyrrhizinate intravenously at the beginning of surgery. Portal vein and pe-ripheral venous blood of patients were drawn at 1 hour after drug use,and HPLC-UV detection method was used to determine the plasma concentration of drug. RESULTS:The retention time of isoglycyrrhizinate magnesium was 4.5 min,which showed a good peak shape,and was not interfered with the determination by plasma endogenous peak. The plasma concentration ranged from 0.55 to 55.00 mg/L. The minimum quantitative concentration was 0.55 mg/L. The extraction recoveries were 84.7%-87.1%,and method recoveries were 101.2%-105.4%,and RSDs of intra-day and inter-day were less than 6%. Plasma concentration of magnesium iso-glycyrrhizinate in portal vein blood was significantly higher than in peripheral vein blood of patients underwent liver resection (close to 2 times);and plasma concentration was not affected by primary liver diseases and underlying diseases such as cirrhosis. CONCLUSIONS:The method is simple and has high recovery rate of extraction,high accuracy and high sensitivity. It can meet the needs of pharmacokinetic study. After the application of magnesium isoglycyrrhizinate during liver resection,there is higher blood concentration of magnesium isoglycyrrhizinate in portal vein,which is beneficial to protect liver cells and improve liver func-tion. It is suitable during perioperative period of liver.
ABSTRACT
Objective To investigate the effects of exenatide on insulin sensitivity in type 2 diabetics.Methods 42 diabetics of secondary failure of sulfonylurea were recruited in the study,and were distinguished to the exenatide group and the glargine group.Besides being treated with diabetic conventional and original treatments,the two groups were given respectively exenatide before breakfast and dinner,or glargine before sleeping by subcutaneous injection for five weeks.Insulin sensitivity of the two groups was elevated by euglycemic-hyperinsulinemic clamps before and after treatment.The metabolic indices were determined.Results Compared with baseline levels,after treatment the glucose metabolic rate was improved [(5.12 ± 0.35) vs (2.94 ± 0.41)] mg · kg-1 · min-1,P ＜ 0.05],the BMI and HMOA-IR was reduced[4.51 (1.32 ～ 6.12) vs 1.96 (1.32 ～ 6.12)],in the exenatide groups,which were better than the glargine group (P ＜ 0.05).Gastrointestinal adverse reactions,which were tolerable and decreased,were appeared in nearly 31.42％ of subjects.There were no severe hypoglycemic events in both groups.Conclusion Short-term treatment with exenatide could improve the insulin sensitivity of type 2 diabetics.