Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
1.
Chinese Medical Journal ; (24): 821-828, 2021.
Article in English | WPRIM | ID: wpr-878109

ABSTRACT

BACKGROUND@#Colorectal cancer is harmful to the patient's life. The treatment of patients is determined by accurate preoperative staging. Magnetic resonance imaging (MRI) played an important role in the preoperative examination of patients with rectal cancer, and artificial intelligence (AI) in the learning of images made significant achievements in recent years. Introducing AI into MRI recognition, a stable platform for image recognition and judgment can be established in a short period. This study aimed to establish an automatic diagnostic platform for predicting preoperative T staging of rectal cancer through a deep neural network.@*METHODS@#A total of 183 rectal cancer patients' data were collected retrospectively as research objects. Faster region-based convolutional neural networks (Faster R-CNN) were used to build the platform. And the platform was evaluated according to the receiver operating characteristic (ROC) curve.@*RESULTS@#An automatic diagnosis platform for T staging of rectal cancer was established through the study of MRI. The areas under the ROC curve (AUC) were 0.99 in the horizontal plane, 0.97 in the sagittal plane, and 0.98 in the coronal plane. In the horizontal plane, the AUC of T1 stage was 1, AUC of T2 stage was 1, AUC of T3 stage was 1, AUC of T4 stage was 1. In the coronal plane, AUC of T1 stage was 0.96, AUC of T2 stage was 0.97, AUC of T3 stage was 0.97, AUC of T4 stage was 0.97. In the sagittal plane, AUC of T1 stage was 0.95, AUC of T2 stage was 0.99, AUC of T3 stage was 0.96, and AUC of T4 stage was 1.00.@*CONCLUSION@#Faster R-CNN AI might be an effective and objective method to build the platform for predicting rectal cancer T-staging.@*TRIAL REGISTRATION@#chictr.org.cn: ChiCTR1900023575; http://www.chictr.org.cn/showproj.aspx?proj=39665.


Subject(s)
Humans , Artificial Intelligence , Magnetic Resonance Imaging , Neoplasm Staging , Neural Networks, Computer , Rectal Neoplasms/pathology , Retrospective Studies
2.
Chinese Journal of Gastrointestinal Surgery ; (12): 898-901, 2013.
Article in Chinese | WPRIM | ID: wpr-256894

ABSTRACT

<p><b>OBJECTIVE</b>To explore the clinical significance of protein expression and gene amplification of HER2 in gastric cancer.</p><p><b>METHODS</b>Immunohistochemistry (IHC) and chromogenic in situ hybridization (CISH) method were used to detect protein expression and gene amplification of HER2 in 80 specimens of gastric cancer patients.</p><p><b>RESULTS</b>Protein expression of HER2 was negative in 51 cases, (+) in 12 cases, (++) in 12 cases, (+++) in 5 cases, and the positive expression rate was 21.3% (17/80). Seven (8.8%) cases had gene amplification of HER2, including gene critical amplification in 3 (3.8%) cases. The result of IHC was positively correlated with CISH (P<0.05), and the coincidence rate was 85.0% (68/80). HER2 positive expression rate was higher in the gastroesophageal junction carcinoma, poorly differentiated and stage III-IIII gastric cancer (all P<0.05).</p><p><b>CONCLUSION</b>The gastric cancer tissue has high positive rate of protein expression and gene amplification of HER2, which is closely correlated to the development of gastric cancer.</p>


Subject(s)
Adult , Aged , Female , Humans , Male , Middle Aged , Gene Amplification , Receptor, ErbB-2 , Genetics , Metabolism , Stomach Neoplasms , Genetics , Metabolism , Pathology
3.
Chinese Journal of Gastrointestinal Surgery ; (12): 1199-1202, 2013.
Article in Chinese | WPRIM | ID: wpr-256832

ABSTRACT

<p><b>OBJECTIVE</b>To investigate the expression of ZBTB8A (zinc finger and BTB domain containing 8A) in gastric cancer tissues and its clinical significance.</p><p><b>METHODS</b>Level of ZBTB8A mRNA in human normal gastric cell line GES-1, human gastric cancer cell line SGC7901 and MGC803 was detected by real-time PCR. Levels of ZBTB8A mRNA and protein in cancer tissues, adjacent cancer tissues from 104 cases with primary gastric cancer and normal gastric mucosal tissues from 40 cases without malignant gastric diseases were detected by RT-PCR and immunohistochemistry, respectively. Association between ZBTB8A expression and clinicopathology was analyzed.</p><p><b>RESULTS</b>ZBTB8A mRNA expressions in SGC7901, MGC803 and GES-1 cells were 0.00138±0.00015, 0.00158±0.00021, 0.00036±0.000055, respectively, and differences among SGC7901, MGC803 and GES-1 were significant respectively (all P<0.05). ZBTB8A mRNA expression was significantly up-regulated in cancer tissues as compared to adjacent cancer tissues and normal tissues (0.0152±0.0126 vs. 0.0070±0.0061 and 0.0079±0.0036, all P>0.05), while no significant difference was found between adjacent cancer tissues and normal tissues (P>0.05). ZBTB8A expression was significantly associated with invasive depth, lymph node metastasis, tumor stage, and degree of adenocarcinoma differentiation (all P<0.05), but not with age, gender, histological type,gross type (all P>0.05).</p><p><b>CONCLUSION</b>ZBTB8A may be a potential carcinogenic factor in gastric carcinoma, and may also be involved in gastric adenocarcinoma cell differentiation, cancer invasion and metastasis.</p>


Subject(s)
Female , Humans , Male , Middle Aged , Adenocarcinoma , Metabolism , Cell Line, Tumor , Kruppel-Like Transcription Factors , Metabolism , Lymphatic Metastasis , RNA, Messenger , Genetics , Stomach Neoplasms , Metabolism
SELECTION OF CITATIONS
SEARCH DETAIL