New Non-invasive Diagnostic Methods To Identify Benign And Malignant Gallbladder Tumors

It is difficult to early diagnose gallbladder cancer.It is very malignant and the prognosis is poor.Therefore,it is greatly significant to early diagnose gallbladder cancer.Now diagnosis of gallbladder cancer mainly depends on ultrasound,CT and tumor marker tests.but these means have low accuracy.Therefore,in this study we try to improve the diagnostic accuracy of gallbladder cancer by Computer-aided diagnosis of gallbladder polyps based on high resolution ultrasonography,dynamic contrastenhanced CT image assessment and detection of peripheral blood ct DNA mutations in benign and malignant gallbladder disease The first part: Computer-aided diagnosis of gallbladder polyps based on high resolution ultrasonographyObjective: Due to its easy accessibility and nonradioactive,ultrasonography is the mostly used preoperative diagnosis tool for gallbladder polyps.However,human image analysis depends greatly on levels of experience,which results in many overtreatment cases and undertreatment cases in clinics.Therefore,it is necessary to study the value of artificial intelligence in identifying gallbladder lesions in ultrasound images.Methods: In this study,we proposed an ultrasound image segmentation algorithm,combined with principal components analysis(PCA)and Ada Boost algorithms to construct a computer-aided diagnosis system for the differentiate diagnosis of neoplastic and non-neoplastic gallbladder polyps.Results: The proposed segmentation method achieved a high accuracy of 95% for outlining the gallbladder region.The accuracy,sensitivity,specificity for the proposed computer-aided diagnosis system based on the segmented images are 87.54%,85.62% and 89.40%,compared to 69.05%,67.86% and 70.17% based on the natural images.The diagnosis result is also slightly higher than the human eyes of sonologists(86.22%,85.19% and 89.18% as an average of four sonologists),while with a much faster diagnosis speed(0.02 s vs 3s).Conclusions: We proposed an efficient ultrasound image segmentation approach and a reliable system of automatic diagonals of neoplastic and non-neoplastic gallbladder polyps.The results show that the diagnosis accuracy is competitive to the expert sonologists while requires much less diagnosis time.The second part: Delayed enhancement in Dynamic Contrast-Enhanced CT scanning for neovascularization evaluation and pathological-type identification in gallbladder polypsObjective: The aim of this study was to improve the differentiability between cholesterol and neoplastic gallbladder polyps by dynamic contrast-enhanced CT scanning.Methods: A training cohort and a validation cohort were enrolled according to the inclusion criteria and exclusion criteria.The training cohort was 144 cases enrolled retrospectively,including 76 cases of cholesterol polyps and 68 cases of neoplastic polyps(29 cases with adenoma and 39 cases with adenocarcinoma).The validation cohort was78 cases recruited prospectively,including 30 cases of cholesterol polyps and 48 cases of neoplastic polyps(30 cases with adenoma and 18 cases with adenocarcinoma).The perception and Hounsfield units(HUs)of the polyps and gallbladder bile were detected and measured in the plain phase,arterial phase,portal phase and equilibrium phase by contrast-enhanced CT scan,and the polyp to bile ratio(PBR)was calculated.Receiver operating characteristic(ROC)curves and areas under the curve(AUCs)were used to analyse the diagnostic value of the CT parameters for neoplastic polyps.Angiogenic markers were detected by immunohistochemistry staining in polyp specimens,and CT image observations on the characteristics of polyp angiogenesis and pathological type identification were analysed.Results: In the training cohort,the proportion of perceived cholesterol polyps in the plain and arterial phases were 5.3% and 61.8%,respectively,which were significantly lower than those of neoplastic polyps in the plain and arterial phases(73.5%,P<0.001 and 97.1%,P<0.001,respectively).However,in the venous phase and the delayed phase,all cholesterol polyps and neoplastic polyps could be perceived.The median PBR values of the cholesterol polyps in the plain and arterial phases were 1.01 and 2.08,respectively,which were significantly lower than those of the neoplastic polyps(3.03,P<0.01 and 4.08 P<0.01,respectively).Similar results were observed in the validation group.In the training cohort,the ROC analysis showed that a polyp which the diameter(AUC=0.946,95% CI: 0.908–0.983)is larger than 12 mm and a plain phase PBR(AUC=0.840,95% CI:0.775–0.904)greater than 1.48 were the optimal cut-off values for the diagnosis of neoplastic polyps.A diameter larger than 12 mm combined with a plain-phase scan PBR greater than 1.48 could increase the specificity and positive likelihood ratio for the diagnosis of neoplastic polyps.The neovascularization density(CD31 staining),microvessel density(CD34 staining),and VEGF scores of the cholesterol polyps were significantly lower than those of the neoplastic polyps,and the diameter of the polyps and the PBR were positively correlated with neovascularization density,microvessel density,and VEGF scores in the training cohort.Conclusions: The delayed enhancement in contrast-enhanced CT scanning is an important signature for identifying cholesterol and neoplastic gallbladder polyps and is also associated with low levels of angiogenesis.Combining polyp diameter and PBR in the plain phase could improve the diagnostic specificity of neoplastic polyps.The third part: Study on peripheral blood ct DNA mutations in benign and malignant gallbladder diseaseObjective: To detect peripheral blood ct DNA mutations in gallbladder benign and malignant gallbladder disease,and to explore its clinical significance.Methods: PB ct DNA was extracted from 4 patients with malignant gallbladder tumor and 2 patients with gallbladder inflammation and detected by high throughput sequencing.Then the ct DNA mutations were analyzed.Results: There was no statistical difference in PB ct DNA mutations in benign and malignant gallbladder disease.Conclusions: The reason may be that the sample size is small and Gallbladder tumors are so different in size and stage that they cannot be compared to each other.But it is still worth our further research after expanding the sample size.