ABSTRACT
Objective To investigate the expression of PIK3CA,phosphorylated protein kinase B(p-AKT)and phosphatase and tensin homologue deleted on chromosome 10(PTEN)in sinonasal squamous cell carcinoma(SNSCC).Methods The expressions of PIK3CA and PTEN in head and neck squamous cell carci-noma(HNSCC)were analyzed through the data set of HNSCC in the cancer genome map of UCSC Xena data-base.The immunohistochemical SP method was used to measure the expression of PIK3CA,p-AKT and PTEN in 43 cases of SNSCC tissues,20 cases of normal inferior concha tissues.The relationship between the expressions of PIK3CA,p-AKT and PTEN protein with the clinicopathological features and prognosis of the patients with SNSCC was analyzed.Results The results of bioinformatic analysis showed that PIK3CA mR-NA expression in HNSCC tissues was higher than that in paracancerous tissues(P＜0.01),while the PTEN mRNA expression was lower than that in paracancerous tissues(P＜0.05).The immunohistochemical detec-tion results showed that the positive expressions rates of PIK3CA and p-AKT proteins in normal nasal mucosa tissues were significantly lower than those in SNSCC tissues,while the positive expression rate of PTEN pro-tein in SNSCC tissues was significantly higher than that in normal inferior nasal concha mucosa tissues,and the differences were statistically significant(P＜0.01).The expressions of PIK3CA and p-AKT protein were related to the clinical stage,differentiation degree and primary site(P＜0.05),but were not related to age,gender,smoking and drinking(P＞0.05);the PTEN protein expression was not related with the clinical stage,differentiation degree,primary site,age,smoking and drinking(P＞0.05).The Spearman analysis showed that the expression of PIK3CA in SNSCC tissues was positively correlated with p-AKT protein ex-pression(r=0.664,P＜0.01),and PIK3CA was negatively correlated with PTEN protein(r=-0.414,P＜0.01).The expression of p-AKT was negatively correlated with PTEN protein(r=-0.453,P＜0.01).The Kaplan-Meier analysis showed that the median survival time of the patients with PIK3CA and p-AKT protein positive expression was shorter than that of the patients with negative expression(P＜0.01).There was no statistically significant difference in median survival between the patients with PTEN protein positive expres-sion and those with negative expression.Conclusion The overexpressions of PIK3CA and p-AKT accompa-nied by the loss of PTEN expression participate in the development and progression of SNSCC,moreover the PIK3CA and p-AKT expressions are related to the poor prognosis of the patients.
ABSTRACT
Objective@#To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. @*Materials and Methods@#This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. @*Results@#A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. @*Conclusion@#Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists’ workload.
ABSTRACT
Objective To discuss the clinical value of image navigation technique in nasal endoscopic repair of cerebrospinal fluid rhinorrhea. Methods Retrospectively analyse the clinical data of 10 cases with cerebrospinal fluid rhinorrhea who underwent nasal endoscopic repair who were admitted to hospital from March 2014 to June 2017 and discussing the diagnosis of cerebrospinal fluid rhinorrhea, preoperative and intraoperative leakage location,repair effect,complications and other indicators. Results All cases were cured by one treatment under imaging-guided transnasal endoscopic repair without any complication and recurrence during the 0. 5 to 40 months of follow-up visits. Conclusion Image-guided system application is essential in the endoscopic repairment of cerebrospinal fluid rhinorrhea by exactly locating the rhinorrhea.