Background:Gallbladder carcinoma(GBC)is highly malignant,and its early diagnosis remains difficult.This study aimed to develop a deep learning model based on contrast-enhanced computed tomography(CT)images to assist r...Background:Gallbladder carcinoma(GBC)is highly malignant,and its early diagnosis remains difficult.This study aimed to develop a deep learning model based on contrast-enhanced computed tomography(CT)images to assist radiologists in identifying GBC.Methods:We retrospectively enrolled 278 patients with gallbladder lesions(>10 mm)who underwent contrast-enhanced CT and cholecystectomy and divided them into the training(n=194)and validation(n=84)datasets.The deep learning model was developed based on ResNet50 network.Radiomics and clinical models were built based on support vector machine(SVM)method.We comprehensively compared the performance of deep learning,radiomics,clinical models,and three radiologists.Results:Three radiomics features including LoG_3.0 gray-level size zone matrix zone variance,HHL firstorder kurtosis,and LHL gray-level co-occurrence matrix dependence variance were significantly different between benign gallbladder lesions and GBC,and were selected for developing radiomics model.Multivariate regression analysis revealed that age≥65 years[odds ratios(OR)=4.4,95%confidence interval(CI):2.1-9.1,P<0.001],lesion size(OR=2.6,95%CI:1.6-4.1,P<0.001),and CA-19-9>37 U/mL(OR=4.0,95%CI:1.6-10.0,P=0.003)were significant clinical risk factors of GBC.The deep learning model achieved the area under the receiver operating characteristic curve(AUC)values of 0.864(95%CI:0.814-0.915)and 0.857(95%CI:0.773-0.942)in the training and validation datasets,which were comparable with radiomics,clinical models and three radiologists.The sensitivity of deep learning model was the highest both in the training[90%(95%CI:82%-96%)]and validation[85%(95%CI:68%-95%)]datasets.Conclusions:The deep learning model may be a useful tool for radiologists to distinguish between GBC and benign gallbladder lesions.展开更多
AIM: To compare clinical presentation and ultrasound (US) and computed tomography (CT) sensitivity between intraluminal and inf iltrating gallbladder carcinoma (GBCA). METHODS: This retrospective study evaluated 65 ca...AIM: To compare clinical presentation and ultrasound (US) and computed tomography (CT) sensitivity between intraluminal and inf iltrating gallbladder carcinoma (GBCA). METHODS: This retrospective study evaluated 65 cases of GBCA that were categorized morphologically into the intraluminal-GBCA (n = 37) and infiltrating-GBCA(n = 28) groups. The clinical and laboratory fi ndings, presence of gallstones, gallbladder size, T-staging, nodal status, sensitivity of preoperative US and CT studies, and outcome were compared between the two groups.RESULTS: There were no signif icant differences between the two groups with respect to female predominance, presence of abdominal pain, serum aminotransferases level, T2-T4 staging, and regional metastatic nodes. Compared with the patients with intraluminal-GBCA, those with infiltrating-GBCA were significantly older (65.49 ± 1.51 years vs 73.07 ± 1.90 years), had a higher frequency of jaundice (3/37 patients vs 13/28 patients) and fever (3/37 patients vs 10/28 patients), higher alkaline phosphatase (119.36 ± 87.80 IU/L vs 220.68 ± 164.84 IU/L) and total bilirubin (1.74 ± 2.87 mg/L vs 3.50 ± 3.51 mg/L) levels, higher frequency of gallstones (12/37 patients vs 22/28 patients), smaller gallbladder size (length, 7.47 ± 1.70 cm vs 6.47 ± 1.83 cm; width, 4.21 ± 1.43 cm vs 2.67 ± 0.93 cm), and greater proportion of patients with < 12 mo survival (16/37 patients vs 18/28 patients). The sensitivity for diagnosing intraluminal-GBCA with and without gallstones was 63.6% and 91.3% by US, and 80% and 100% by CT, respectively. The sensitivity for diagnosing inf iltrating-GBCA with and without gallstones was 12.5% and 25% by US, and 71.4% and 75% by CT, respectively. CONCLUSION: In elderly women exhibiting small gallbladder and gallstones on US, especially those with jaundice, fever, high alkaline phosphatase and bilirubin levels, CT may reveal concurrent infi ltrating-GBCA.展开更多
Primary gallbladder carcinoma is the most common malignant tumor of the biliary system. There is a reduced likelihood for radical cure of primary gallbladder carcinomas because of the insidious onset.1 Spiral computed...Primary gallbladder carcinoma is the most common malignant tumor of the biliary system. There is a reduced likelihood for radical cure of primary gallbladder carcinomas because of the insidious onset.1 Spiral computed tomography （SCT） scanning is an important means for diagnosing lesions involving the gallbladder. We determined the expression of anti-metastasis protein nm23 and KAI1 using immunohistochemical method and analyzed the relationship between their expression and the pre-operatively SCT imaging findings, the histopathologic grade, clinical stage, 5-year survival rate in 35 cases of primary gallbladder cancer.展开更多
Cholecystocolic fistula secondary to gallbladder carcinoma is extremely rare and has been reported in very few studies. Most cholecystocolic fistulae are late complications of gallstone disease, but can also develop f...Cholecystocolic fistula secondary to gallbladder carcinoma is extremely rare and has been reported in very few studies. Most cholecystocolic fistulae are late complications of gallstone disease, but can also develop following carcinoma of the gallbladder when the necrotic tumor penetrates into the adjacent colon. Although no currently available imaging technique has shown great accuracy in recognizing cholecystocolic fistula, abdominopelvic computed tomography may show fistulous communication and anatomical details.Herein we report an unusual case of cholecystocolic fistula caused by gallbladder carcinoma, which was preoperatively misdiagnosed as hepatic flexure colon carcinoma.展开更多
目的:探讨增强电子计算机断层扫描(computer tomography,CT)在胆囊癌侵犯肝脏与肝癌累及胆囊病变中的鉴别诊断价值。方法:收集2012年2月到2022年2月重庆医科大学附属第一医院115例患者临床及影像学资料,其中胆囊癌侵犯肝脏病例69例,肝...目的:探讨增强电子计算机断层扫描(computer tomography,CT)在胆囊癌侵犯肝脏与肝癌累及胆囊病变中的鉴别诊断价值。方法:收集2012年2月到2022年2月重庆医科大学附属第一医院115例患者临床及影像学资料,其中胆囊癌侵犯肝脏病例69例,肝癌累及胆囊病例46例,记录性别、年龄、肿瘤大小、肿瘤边界、胆囊形态、肝硬化、胆管扩张、肿瘤内或胆管系统内高密度影、门静脉癌栓、强化方式、强化程度、淋巴结肿大及远处转移共13个观察指标,并进行统计学分析。结果:性别(P=0.007)、年龄(P=0.002)、肿瘤大小(P=0.003)、肝硬化(P<0.001)、肿瘤内或胆管系统内高密度影(P=0.013)、门静脉癌栓(P<0.001)、强化方式(P<0.001)及淋巴结肿大(P=0.034)有统计学差异。通过回归分析筛选出年龄(敏感度为0.812,特异度为0.457)、肿瘤大小(敏感度为0.630,特异度为0.696)、门静脉癌栓(敏感度为0.326,特异度为0.957)、淋巴结肿大(敏感度为0.681,特异度为0.522)为显著分类指标,联合4个观察指标的参数绘制受试者工作特征(receiver operating characteristic,ROC)曲线,曲线下面积(area under the curve,AUC)为0.770,敏感度为0.674,特异度为0.826。结论:增强CT在鉴别胆囊癌侵犯肝脏与肝癌累及胆囊病变时,性别、年龄、肿瘤大小、肝硬化、肿瘤内或胆管系统内高密度影、门静脉癌栓、强化方式及淋巴结肿大有鉴别价值,同时结合年龄、肿瘤大小、门静脉癌栓及淋巴结肿大有助于提高鉴别诊断能力。展开更多
基金the National Natural Science Foundation of China(81572975)Key Research and Devel-opment Project of Science and Technology Department of Zhejiang(2015C03053)+1 种基金Chen Xiao-Ping Foundation for the Development of Science and Technology of Hubei Province(CXPJJH11900009-07)Zhejiang Provincial Program for the Cultivation of High-level Innovative Health Talents.
文摘Background:Gallbladder carcinoma(GBC)is highly malignant,and its early diagnosis remains difficult.This study aimed to develop a deep learning model based on contrast-enhanced computed tomography(CT)images to assist radiologists in identifying GBC.Methods:We retrospectively enrolled 278 patients with gallbladder lesions(>10 mm)who underwent contrast-enhanced CT and cholecystectomy and divided them into the training(n=194)and validation(n=84)datasets.The deep learning model was developed based on ResNet50 network.Radiomics and clinical models were built based on support vector machine(SVM)method.We comprehensively compared the performance of deep learning,radiomics,clinical models,and three radiologists.Results:Three radiomics features including LoG_3.0 gray-level size zone matrix zone variance,HHL firstorder kurtosis,and LHL gray-level co-occurrence matrix dependence variance were significantly different between benign gallbladder lesions and GBC,and were selected for developing radiomics model.Multivariate regression analysis revealed that age≥65 years[odds ratios(OR)=4.4,95%confidence interval(CI):2.1-9.1,P<0.001],lesion size(OR=2.6,95%CI:1.6-4.1,P<0.001),and CA-19-9>37 U/mL(OR=4.0,95%CI:1.6-10.0,P=0.003)were significant clinical risk factors of GBC.The deep learning model achieved the area under the receiver operating characteristic curve(AUC)values of 0.864(95%CI:0.814-0.915)and 0.857(95%CI:0.773-0.942)in the training and validation datasets,which were comparable with radiomics,clinical models and three radiologists.The sensitivity of deep learning model was the highest both in the training[90%(95%CI:82%-96%)]and validation[85%(95%CI:68%-95%)]datasets.Conclusions:The deep learning model may be a useful tool for radiologists to distinguish between GBC and benign gallbladder lesions.
文摘AIM: To compare clinical presentation and ultrasound (US) and computed tomography (CT) sensitivity between intraluminal and inf iltrating gallbladder carcinoma (GBCA). METHODS: This retrospective study evaluated 65 cases of GBCA that were categorized morphologically into the intraluminal-GBCA (n = 37) and infiltrating-GBCA(n = 28) groups. The clinical and laboratory fi ndings, presence of gallstones, gallbladder size, T-staging, nodal status, sensitivity of preoperative US and CT studies, and outcome were compared between the two groups.RESULTS: There were no signif icant differences between the two groups with respect to female predominance, presence of abdominal pain, serum aminotransferases level, T2-T4 staging, and regional metastatic nodes. Compared with the patients with intraluminal-GBCA, those with infiltrating-GBCA were significantly older (65.49 ± 1.51 years vs 73.07 ± 1.90 years), had a higher frequency of jaundice (3/37 patients vs 13/28 patients) and fever (3/37 patients vs 10/28 patients), higher alkaline phosphatase (119.36 ± 87.80 IU/L vs 220.68 ± 164.84 IU/L) and total bilirubin (1.74 ± 2.87 mg/L vs 3.50 ± 3.51 mg/L) levels, higher frequency of gallstones (12/37 patients vs 22/28 patients), smaller gallbladder size (length, 7.47 ± 1.70 cm vs 6.47 ± 1.83 cm; width, 4.21 ± 1.43 cm vs 2.67 ± 0.93 cm), and greater proportion of patients with < 12 mo survival (16/37 patients vs 18/28 patients). The sensitivity for diagnosing intraluminal-GBCA with and without gallstones was 63.6% and 91.3% by US, and 80% and 100% by CT, respectively. The sensitivity for diagnosing inf iltrating-GBCA with and without gallstones was 12.5% and 25% by US, and 71.4% and 75% by CT, respectively. CONCLUSION: In elderly women exhibiting small gallbladder and gallstones on US, especially those with jaundice, fever, high alkaline phosphatase and bilirubin levels, CT may reveal concurrent infi ltrating-GBCA.
文摘Primary gallbladder carcinoma is the most common malignant tumor of the biliary system. There is a reduced likelihood for radical cure of primary gallbladder carcinomas because of the insidious onset.1 Spiral computed tomography （SCT） scanning is an important means for diagnosing lesions involving the gallbladder. We determined the expression of anti-metastasis protein nm23 and KAI1 using immunohistochemical method and analyzed the relationship between their expression and the pre-operatively SCT imaging findings, the histopathologic grade, clinical stage, 5-year survival rate in 35 cases of primary gallbladder cancer.
文摘Cholecystocolic fistula secondary to gallbladder carcinoma is extremely rare and has been reported in very few studies. Most cholecystocolic fistulae are late complications of gallstone disease, but can also develop following carcinoma of the gallbladder when the necrotic tumor penetrates into the adjacent colon. Although no currently available imaging technique has shown great accuracy in recognizing cholecystocolic fistula, abdominopelvic computed tomography may show fistulous communication and anatomical details.Herein we report an unusual case of cholecystocolic fistula caused by gallbladder carcinoma, which was preoperatively misdiagnosed as hepatic flexure colon carcinoma.
文摘目的:探讨增强电子计算机断层扫描(computer tomography,CT)在胆囊癌侵犯肝脏与肝癌累及胆囊病变中的鉴别诊断价值。方法:收集2012年2月到2022年2月重庆医科大学附属第一医院115例患者临床及影像学资料,其中胆囊癌侵犯肝脏病例69例,肝癌累及胆囊病例46例,记录性别、年龄、肿瘤大小、肿瘤边界、胆囊形态、肝硬化、胆管扩张、肿瘤内或胆管系统内高密度影、门静脉癌栓、强化方式、强化程度、淋巴结肿大及远处转移共13个观察指标,并进行统计学分析。结果:性别(P=0.007)、年龄(P=0.002)、肿瘤大小(P=0.003)、肝硬化(P<0.001)、肿瘤内或胆管系统内高密度影(P=0.013)、门静脉癌栓(P<0.001)、强化方式(P<0.001)及淋巴结肿大(P=0.034)有统计学差异。通过回归分析筛选出年龄(敏感度为0.812,特异度为0.457)、肿瘤大小(敏感度为0.630,特异度为0.696)、门静脉癌栓(敏感度为0.326,特异度为0.957)、淋巴结肿大(敏感度为0.681,特异度为0.522)为显著分类指标,联合4个观察指标的参数绘制受试者工作特征(receiver operating characteristic,ROC)曲线,曲线下面积(area under the curve,AUC)为0.770,敏感度为0.674,特异度为0.826。结论:增强CT在鉴别胆囊癌侵犯肝脏与肝癌累及胆囊病变时,性别、年龄、肿瘤大小、肝硬化、肿瘤内或胆管系统内高密度影、门静脉癌栓、强化方式及淋巴结肿大有鉴别价值,同时结合年龄、肿瘤大小、门静脉癌栓及淋巴结肿大有助于提高鉴别诊断能力。
