超声引导下甲状腺结节细针穿刺术的个人学习曲线初步研究

目的探讨超声引导下无负压甲状腺细针穿刺细胞学（US-FNAC）的学习曲线规律及其影响因素。 方法收集分析2017年6月至2018年月6月西安交通大学医学院附属陕西省肿瘤医院由同一医师完成的135例US-FNAC患者的操作耗时及临床病例资料，将患者按手术先后分9组（A~I组），每组15例定为一手术阶段后进行两两对比分析，比较各阶段的操作耗时、并发症及操作无效率。根据得出结果将135例患者分为前、中、后（X、Y、Z）3组，比较组间差异，进一步验证结果。 结果在A组至I组进行两两对比统计学分析得出，在A~D组间操作耗时均存在统计学差异（均P<0.05），在D组与E组间出现转折即两组比较差异无统计学意义（P=0.561），而E~I组间差异均无统计学意义（均P>0.05）。X、Y、Z 3组比较中，X组操作耗时明显长于Y组和Z组［分别为（6.23±1.38）min、（3.47±0.45）min、（3.21±0.45）min］，X组与Y组和Z组差异均有统计学意义（t=18.07、23.15，均P<0.05），Y、Z两组对比无显著差异（t=1.92，P=0.067）。随着操作例数的增加，并发症及无效操作的发生率逐渐降低。 结论对于期望熟练掌握US-FNAC技术的超声医师，遵循对操作的全面认知和科学操作步骤，在指导下开展45例左右的US-FNAC后，可望快速安全越过学习曲线转折点。     

甲状腺结核临床误诊探讨

目的 通过对甲状腺结核流行病学特点、临床及病理分型、临床表现、辅助检查提高对甲状腺结核的认识,提高该病的术前诊断率.方法回顾性分析2012年12月四川大学华西医院西藏成办分院收治的1例甲状腺结核患者的临床资料.结果 手术行甲状腺右叶峡部切除+左叶近全切除术.术后病理证实为甲状腺结核.结论 甲状腺结核发病率低,临床罕见,提高临床医师对甲状腺结核的认知度是避免误诊的关键.细针穿刺细胞学检查(FNAB),抗酸染色及活检组织培养,这是目前术前诊断甲状腺结核最准确和最有效的方法.     

Colorectal mucus non‐invasively collected from patients with inflammatory bowel disease and its suitability for diagnostic cytology

Colorectal mucus is a key component of the protective gut barrier which is altered in inflammatory bowel disease (IBD). We aimed to cytologically characterize colorectal mucus non‐invasively collected from IBD patients using our new sampling technique. Colorectal mucus was self‐collected by 58 IBD patients comprising 31 ulcerative colitis (UC) and 27 Crohn's disease (CD) cases. The samples were examined cytologically, and immunocytochemically. Large numbers of well‐preserved granulocytes were typically detected (neutrophils undergoing degradation were observed as well). Plasma cells and erythrophagocytosis were present in 18.2% and 29.1% of cases, respectively, predominantly in patients with UC and distal CD. Immunocytochemical visualization of calprotectin in neutrophils, eosinophil‐derived neurotoxin in eosinophils and tumour necrosis factor‐α in macrophages was also achieved. Correct cytological diagnosis was made in 61.8% of analysed IBD cases. Our new method of colorectal mucus sampling provides highly informative material for cytology. Findings of the presence of plasmocytes and erythrophagocytosis in colorectal mucus are unique and may reflect previously unknown mechanisms of IBD pathogenesis. Immunocytochemical detection of inflammation biomarkers demonstrates the suitability of this material for biomarker quantification. These promising results suggest a potential role for colorectal mucus cytology in the non‐invasive diagnosis of IBD.     

Comparison of Fine-Tuned Deep Convolutional Neural Networks for the Automated Classification of Lung Cancer Cytology Images with Integration of Additional Classifiers

Objective: It is essential to accurately diagnose and classify histological subtypes into adenocarcinoma (ADC), squamous cell carcinoma (SCC), and small cell lung carcinoma (SCLC) for the appropriate treatment of lung cancer patients. However, improving the accuracy and stability of diagnosis is challenging, especially for non-small cell carcinomas. The purpose of this study was to compare multiple deep convolutional neural network (DCNN) technique with subsequent additional classifiers in terms of accuracy and characteristics in each histology. Methods: Lung cancer cytological images were classified into ADC, SCC, and SCLC with four fine-tuned DCNN models consisting of AlexNet, GoogLeNet (Inception V3), VGG16 and ResNet50 pretrained by natural images in ImageNet database. For more precise classification, the figures of 3 histological probabilities were further applied to subsequent machine learning classifiers using Naïve Bayes (NB), Support vector machine (SVM), Random forest (RF), and Neural network (NN). Results: The classification accuracies of the AlexNet, GoogLeNet, VGG16 and ResNet50 were 74.0%, 66.8%, 76.8% and 74.0%, respectively. Well differentiated typical morphologies were tended to be correctly judged by all four architectures. However, poorly differentiated non-small cell carcinomas lacking typical structures were inclined to be misrecognized in some DCNNs. Regarding the histological types, ADC were best judged by AlexNet and SCC by VGG16. Subsequent machine learning classifiers of NB, SVV, RF, and NN improved overall accuracies to 75.1%, 77.5%, 78.2%, and 78.9%, respectively. Conclusion: Fine-tuning DCNNs in combination with additional classifiers improved classification of cytological diagnosis of lung cancer, although classification bias could be indicated among DCNN architectures.