Early diagnosis of breast cancer,the most common disease among women around the world,increases the chance of treatment and is highly important.Nuclear atypia grading in histopathological images plays an important rol...Early diagnosis of breast cancer,the most common disease among women around the world,increases the chance of treatment and is highly important.Nuclear atypia grading in histopathological images plays an important role in the final diagnosis and grading ofbreast cancer.Grading images by pathologists is a time consuming and subjective task.Therefore,the existence of a computer-aided system for nuclear atypia grading is very useful and necessary;In this stud%two automatic systems for grading nuclear atypia in breast cancer histopathological images based on deep learning methods are proposed.A patch-based approach is introduced due to the large size of the histopathological images and restriction of the training data.In the proposed system I,the most important patches in the image are detected first and then a three-hidden-layer convolutional neural network(CNN)is designed and trained for feature extraction and to classify the patches individually.The proposed system II is based on a combination of the CNN for feature extraction and a two-layer Long short-term memoty(LSTM)network for classification.The LSTM network is utilised to consider all patches of an image simultaneously for image grading.The simulation results show the efficiency of the proposed systems for automatic nuclear atypia grading and outperform the current related studies in the literature.展开更多
AIM: To study the long-term effects of endoscopic sphincterotomy on biliary epithelium. METHODS: This is a prospective case-control study. A total of 25 patients with a median age of 71 years (range 49-89 years) and p...AIM: To study the long-term effects of endoscopic sphincterotomy on biliary epithelium. METHODS: This is a prospective case-control study. A total of 25 patients with a median age of 71 years (range 49-89 years) and prior endoscopic sphincterotomy (ES) for benign disease formed the fi rst group. The median time from ES was 42 mo (range 8-144 mo). Another 25 patients with a median age of 76 years (range 44-94 mo) and similar characteristics who underwent current endoscopic retrograde cholangio-pancreatography (ERCP) and ES for benign disease formed the second group (control group). Brush cytology of the biliary tree with p53 immunocytology was performed in all patients of both groups. ERCPs and recruitment were conducted at the Endoscopic Unit of Aretaieion University Hospital and Tzaneio Hospital, Athens, from October 2006 to June 2010. RESULTS: No cases were positive or suspicious for malignancy. Epithelial atypia was higher in the first group (32% vs 8% in the second group, P = 0.034). Acute cholangitis and previous biliary operation rates were also higher in the fi rst group (acute cholangitis, 60% vs 24% in the second group, P = 0.01; previous biliary operation, 76% vs 24% in the second group, P = 0.001). Subgroup analysis showed that previous ES was the main causal factor for atypia, which was not related to the time interval from the ES (P = 0.407). Two patients (8%) with atypia in the fi rst group were p53-positive. CONCLUSION: ES causes biliary epithelial atypia that represents mostly reactive/proliferative rather than premalignant changes. The role of p53 immunoreactivity in biliary atypia needs to be further studied.展开更多
文摘Early diagnosis of breast cancer,the most common disease among women around the world,increases the chance of treatment and is highly important.Nuclear atypia grading in histopathological images plays an important role in the final diagnosis and grading ofbreast cancer.Grading images by pathologists is a time consuming and subjective task.Therefore,the existence of a computer-aided system for nuclear atypia grading is very useful and necessary;In this stud%two automatic systems for grading nuclear atypia in breast cancer histopathological images based on deep learning methods are proposed.A patch-based approach is introduced due to the large size of the histopathological images and restriction of the training data.In the proposed system I,the most important patches in the image are detected first and then a three-hidden-layer convolutional neural network(CNN)is designed and trained for feature extraction and to classify the patches individually.The proposed system II is based on a combination of the CNN for feature extraction and a two-layer Long short-term memoty(LSTM)network for classification.The LSTM network is utilised to consider all patches of an image simultaneously for image grading.The simulation results show the efficiency of the proposed systems for automatic nuclear atypia grading and outperform the current related studies in the literature.
基金Supported by GC Medical Hellas who offered us free cytology brushes
文摘AIM: To study the long-term effects of endoscopic sphincterotomy on biliary epithelium. METHODS: This is a prospective case-control study. A total of 25 patients with a median age of 71 years (range 49-89 years) and prior endoscopic sphincterotomy (ES) for benign disease formed the fi rst group. The median time from ES was 42 mo (range 8-144 mo). Another 25 patients with a median age of 76 years (range 44-94 mo) and similar characteristics who underwent current endoscopic retrograde cholangio-pancreatography (ERCP) and ES for benign disease formed the second group (control group). Brush cytology of the biliary tree with p53 immunocytology was performed in all patients of both groups. ERCPs and recruitment were conducted at the Endoscopic Unit of Aretaieion University Hospital and Tzaneio Hospital, Athens, from October 2006 to June 2010. RESULTS: No cases were positive or suspicious for malignancy. Epithelial atypia was higher in the first group (32% vs 8% in the second group, P = 0.034). Acute cholangitis and previous biliary operation rates were also higher in the fi rst group (acute cholangitis, 60% vs 24% in the second group, P = 0.01; previous biliary operation, 76% vs 24% in the second group, P = 0.001). Subgroup analysis showed that previous ES was the main causal factor for atypia, which was not related to the time interval from the ES (P = 0.407). Two patients (8%) with atypia in the fi rst group were p53-positive. CONCLUSION: ES causes biliary epithelial atypia that represents mostly reactive/proliferative rather than premalignant changes. The role of p53 immunoreactivity in biliary atypia needs to be further studied.
