scholarly journals Deep Convolutional Neural Network-Based Lymph Node Metastasis Prediction for Colon Cancer Using Histopathological Images

2021 ◽  
Vol 10 ◽  
Author(s):  
Min Seob Kwak ◽  
Hun Hee Lee ◽  
Jae Min Yang ◽  
Jae Myung Cha ◽  
Jung Won Jeon ◽  
...  
Keyword(s):  
Neural Network ◽  
Colon Cancer ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Convolutional Neural Network ◽  
Deep Convolutional Neural Network ◽  
Cancer Tissue ◽  
Negative Group ◽  
Positive Group ◽  
Node Metastasis

BackgroundHuman evaluation of pathological slides cannot accurately predict lymph node metastasis (LNM), although accurate prediction is essential to determine treatment and follow-up strategies for colon cancer. We aimed to develop accurate histopathological features for LNM in colon cancer.MethodsWe developed a deep convolutional neural network model to distinguish the cancer tissue component of colon cancer using data from the tissue bank of the National Center for Tumor Diseases and the pathology archive at the University Medical Center Mannheim, Germany. This model was applied to whole-slide pathological images of colon cancer patients from The Cancer Genome Atlas (TCGA). The predictive value of the peri-tumoral stroma (PTS) score for LNM was assessed.ResultsA total of 164 patients with stages I, II, and III colon cancer from TCGA were analyzed. The mean PTS score was 0.380 (± SD = 0.285), and significantly higher PTS scores were observed in patients in the LNM-positive group than those in the LNM-negative group (P < 0.001). In the univariate analyses, the PTS scores for the LNM-positive group were significantly higher than those for the LNM-negative group (P < 0.001). Further, the PTS scores in lymphatic invasion and any one of perineural, lymphatic, or venous invasion were significantly increased in the LNM-positive group (P < 0.001 and P < 0.001).ConclusionWe established the PTS score, a simplified reproducible parameter, for predicting LNM in colon cancer using computer-based analysis that could be used to guide treatment decisions. These findings warrant further confirmation through large-scale prospective clinical trials.

scholarly journals The levels of NF-κB p50 and NF-κB p65 play a role in thyroid carcinoma malignancy in vivo

2018 ◽  
Vol 46 (10) ◽  
pp. 4092-4099 ◽  
Author(s):  
Fei Le ◽  
Jing-Yu Zhang ◽  
Wei Liu ◽  
Xian-Ming Huang ◽  
Wen-Zheng Luo
Keyword(s):  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Thyroid Carcinoma ◽  
Negative Group ◽  
Positive Group ◽  
Node Metastasis ◽  
Tumour Diameter ◽  
Tumour Characteristics ◽  
The Relationship

Background To investigate the relationship between the levels of nuclear factor (NF)-κB p50 and NF-κB p65 and tumour characteristics in patients with thyroid carcinoma. Methods This prospective study enrolled consecutive patients with thyroid carcinoma. Tumour samples were collected and the levels of NF-κB p50 and NF-κB p65 protein and mRNA were measured using immunohistochemistry and quantitative real-time reverse transcription–polymerase chain reaction (qRT–PCR). Results A total of 73 patients with thyroid carcinoma were included in the study (20 males; 53 females; mean ± SD age, 44.8 ± 12.7 years, range, 18–76 years). There were no significant differences in sex, age and pathological type between the NF-κB p50 positive group and the NF-κB p50 negative group, but tumour diameter and lymph node metastasis were significantly higher in the NF-κB p50 positive group compared with the NF-κB p50 negative group. Similar findings were observed for NF-κB p65. The levels of NF-κB p50 were positively correlated with NF-κB p65 in samples of thyroid carcinoma ( rs = 0.653). Conclusion The levels of NF-κB p50 and NF-κB p65 in samples of thyroid carcinoma were positively associated with tumour diameter and the presence of lymph node metastasis.

scholarly journals Clinicopathologic Significance of HIF-1α, CXCR4, and VEGF Expression in Colon Cancer

2010 ◽  
Vol 2010 ◽  
pp. 1-10 ◽  
Author(s):  
Yugang Wu ◽  
Min Jin ◽  
Huanbai Xu ◽  
Zhang Shimin ◽  
Songbing He ◽  
...  
Keyword(s):  
Colon Cancer ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Distant Metastasis ◽  
Disease Free Survival ◽  
High Expression ◽  
Cancer Tissue ◽  
Vegf Expression ◽  
Tissue Samples ◽  
Node Metastasis

We investigated the clinicopathologic significance of HIF-1, CXCR4, and VEGF expression using immumohistochemistry in human colon cancer. HIF-1, CXCR4, and VEGF high expression levels were correlated positively with TNM stage, lymph node involvement, and distant metastasis Furthermore, we found that combined high expression of any two of the three molecules (P=.028for HIF-1/CXCR4,P=.007for HIF-1/VEGF, andP=.004for CXCR4/VEGF) had stronger correlation with lymph node metastasis than did each alone. However, a relationship with distant metastasis is seen only with the combinations CXCR4/VEGF (P=.069for HIF-1/CXCR4,P=.062for HIF-1/VEGF, andP=.035for CXCR4/VEGF) as compared with those of single molecule high expression alone. Combined expression of all three molecules strongly correlates with lymph node metastasis and distant metastasis. The mRNA expression of HIF-1, CXCR4, and VEGF were quantified by real-time PCR in different colon cancer tissue samples, the experiment results shown that fresh colon tissue samples significantly overexpressed CXCR4 and VEGF mRNA compared with negative control. Therefore, the disease-free survival of all patients after curative resection can be considered in association with all three markers expression.

Sign in / Sign up

Export Citation Format

Share Document