Application of Artificial Intelligence in a Real-World Research for Predicting the Risk of Liver Metastasis in T1 Colorectal Cancer

2021 ◽  
Author(s):  
Tenghui Han ◽  
Jun Zhu ◽  
Dong Xu ◽  
Rujie Chen ◽  
Shuai Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Colorectal Cancer ◽  
Liver Metastasis ◽  
Predictive Model ◽  
Tumor Size ◽  
Area Under The Curve ◽  
Subsequent Treatment ◽  
Tumor Type ◽  
Discriminative Ability ◽  
N Stage

Abstract Background: The liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. However, there is still no effective model to predict the risk of LM in T1 CRC patients and we aim to develop a novel and accurate predictive model.Methods: We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER) and Xijing hospital. Artificial intelligence (AI) and machine learning methods were adopted to establish the predictive model.Results: A total of 16785 and 326 T1 CRC patients from SEER database and our hospital were incorporated respectively in the study. We found that age, gender, married status, primary site, tumor size, carcinoembryonic antigen (CEA), tumor type, grade, N stage and perineural invasion were significant independent factors for predicting the presence of LM, among which tumor size is the most important. The stacking bagging model showed the best predictive capability, achieving a sensitivity of 0.8452, a specificity of 0.9566, and an area under the curve of 0.9631. In addition, the stacking model had an excellent discriminative ability and accurately screened out eight LM cases from 326 T1 patients in the outer validation cohort. Ultimately, we authenticated the prognostic value of the stacking model, which is consistent with the predictive result of LM.Conclusion: We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in our dataset.

scholarly journals Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer

2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Tenghui Han ◽  
Jun Zhu ◽  
Xiaoping Chen ◽  
Rujie Chen ◽  
Yu Jiang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Colorectal Cancer ◽  
Liver Metastasis ◽  
Predictive Model ◽  
Area Under The Curve ◽  
Predictive Ability ◽  
Subsequent Treatment ◽  
Training Dataset ◽  
Discriminative Ability ◽  
Fundamental Parameters

Abstract Background Liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. Nevertheless, there is still no effective model to predict the risk of LM in T1 CRC patients. Hence, we aim to construct an accurate predictive model and an easy-to-use tool clinically. Methods We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER, training dataset) and Xijing hospital (testing dataset). Artificial intelligence (AI) and machine learning (ML) methods were adopted to establish the predictive model. Results A total of 16,785 and 326 T1 CRC patients from SEER database and Xijing hospital were incorporated respectively into the study. Every single ML model demonstrated great predictive capability, with an area under the curve (AUC) close to 0.95 and a stacking bagging model displaying the best performance (AUC = 0.9631). Expectedly, the stacking model exhibited a favorable discriminative ability and precisely screened out all eight LM cases from 326 T1 patients in the outer validation cohort. In the subgroup analysis, the stacking model also demonstrated a splendid predictive ability for patients with tumor size ranging from one to50mm (AUC = 0.956). Conclusion We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in the external dataset. Ultimately, we designed a novel and easy-to-use decision tree, which only incorporated four fundamental parameters and could be successfully applied in clinical practice.

Toward an Optimized Staging System for Pancreatic Ductal Adenocarcinoma: A Clinically Interpretable, Artificial Intelligence–Based Model

2021 ◽  
pp. 1220-1231
Author(s):  
Dimitris Bertsimas ◽  
Georgios Antonios Margonis ◽  
Yifei Huang ◽  
Nikolaos Andreatos ◽  
Holly Wiberg ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Tumor Size ◽  
Area Under The Curve ◽  
Staging System ◽  
Nodal Status ◽  
Ductal Adenocarcinoma ◽  
Risk Of Death ◽  
Staging Systems ◽  
N Stage

PURPOSE The American Joint Committee on Cancer (AJCC) eighth edition schema for pancreatic ductal adenocarcinoma treats T and N stage as independent factors and uses positive lymph nodes (PLNs) to define N stage, despite data favoring lymph node ratio (LNR). We used artificial intelligence–based techniques to compare PLN with LNR and investigate interactions between tumor size and nodal status. METHODS Patients who underwent pancreatic ductal adenocarcinoma resection between 2000 and 2017 at six institutions were identified. LNR and PLN were compared through shapley additive explanations (SHAP) analysis, with the best predictor used to define nodal status. We trained optimal classification trees (OCTs) to predict 1-year and 3-year risk of death, incorporating only tumor size and nodal status as variables. The OCTs were compared with the AJCC schema and similarly trained XGBoost models. Variable interactions were explored via SHAP. RESULTS Two thousand eight hundred seventy-four patients comprised the derivation and 1,231 the validation cohort. SHAP identified LNR as a superior predictor. The OCTs outperformed the AJCC schema in the derivation and validation cohorts (1-year area under the curve: 0.681 v 0.603; 0.638 v 0.586, 3-year area under the curve: 0.682 v 0.639; 0.675 v 0.647, respectively) and performed comparably with the XGBoost models. We identified interactions between LNR and tumor size, suggesting that a negative prognostic factor partially overrides the effect of a concurrent favorable factor. CONCLUSION Our findings highlight the superiority of LNR and the importance of interactions between tumor size and nodal status. These results and the potential of the OCT methodology to combine them into a powerful, visually interpretable model can help inform future staging systems.

DNA methylation signatures predicting liver metastasis of colorectal cancer: A proof-of-concept pilot study.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e16080-e16080
Author(s):  
Jianming Ying ◽  
Weihua Li ◽  
Kaihua Liu ◽  
Cong Xiao ◽  
Shuyu Wu ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Liver Metastasis ◽  
Early Detection ◽  
Predictive Model ◽  
Primary Tumor ◽  
Metastatic Tumor ◽  
Training Data ◽  
Training Dataset ◽  
Tissue Samples ◽  
Normal Tissues

e16080 Background: Liver metastasis (LIM) is the leading cause of death in colorectal cancer (CRC) patients. Early detection of LIM may improve outcome in CRC patients. The aim of this study was to evaluate the feasibility of predicting LIM of CRC using methylation profiles. Methods: We performed Roche targeted (~5.5 million methylation sites) bisulfite sequencing of matched primary, metastatic and their adjacent normal tissue samples from 5 CRC patients with LIM, 5 patients with lung metastasis (LUM) and 8 patients without metastasis in the training cohort (n = 48 samples). Differential methylation regions (DMR) of LUM were identified and a predictive model was developed. The model was further validated in primary tumor sample from nine patients (6 with LIM). Results: By comparing primary tumor vs adjacent normal tissues and metastatic tumor vs adjacent normal tissues in CRC patients with LIM, we identified 28954 common DMRs which indicating the methylation characteristic of CRC with LIM. Similarly, 16187 DMRs were identified in patients with LUM. 9179 DMRs are shared in both LIM and LUM comparisons which should be the common characteristic of CRC tumor tissue regardless of the location of metastasis. 7008 DMRs are LUM specific and 19775 DMRs are LIM specific. In order to predict LIM in primary, early changes in LIM specific DMRs should be identified. Hence, we further selected 4134 DMRs by chossing significantly differentically methylated regions between LIM primary tissues and LUM primary tissues. To increase the ability of distinguishing LIM from other normal tissues and non-matastasis CRC tumors, 1215 DMRs were finally selected which also showed increasing or decreasing trend of methylation level through the progression of CRC. The final 1215 biomarkers were used to construct a random forest model using methlylation profile of 5 CRC patients with LIM as positive training data and 5 CRC patients with LUM as well as 8 patients without metastasis as negative training data. Through the feature recursive elimination method, one methylation site (chr8.72468901-72469000) was identified with ROC of 0.9 in the training dataset. The predictive model was validated in an independent dataset which is composed of 6 patients with LIM and 3 patients without metastasis, and achieved an AUC of 0.87. Conclusions: Our findings demonstrate the utility of methylation biomarkers for the molecular characterization of metastatic precursors, with implications for prediction and early detection of liver metastasis in CRC.

scholarly journals Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Gang Yu ◽  
Kai Sun ◽  
Chao Xu ◽  
Xing-Hua Shi ◽  
Chong Wu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Colorectal Cancer ◽  
Deep Learning ◽  
Supervised Learning ◽  
Area Under The Curve ◽  
Patient Level ◽  
Significant Difference ◽  
The Mean ◽  
Whole Slide Images ◽  
Better Than

AbstractMachine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

scholarly journals Three-Dimensional Length from the Center of the Liver is a Prognostic Factor of Colorectal Cancer with Liver Metastasis: A Retrospective Analysis

2020 ◽  
Author(s):  
Jun Woo Bong ◽  
Yeonuk Ju ◽  
Jihyun Seo ◽  
Sang Hee Kang ◽  
Pyoung-Jae Park ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Risk Factors ◽  
Overall Survival ◽  
Liver Metastasis ◽  
Neoadjuvant Chemotherapy ◽  
Resection Margin ◽  
Characteristic Curve ◽  
Significant Risk ◽  
Area Under The Curve ◽  
Positive Resection Margin

Abstract Background Resectability of liver metastasis is important to establish a treatment strategy for colorectal cancer patients. We aimed to evaluate the effect of distance from metastasis to the center of the liver on the resectability and patient outcomes after hepatectomy. Methods Clinical data of a total of 124 patients who underwent hepatectomy for colorectal cancer with liver metastasis were retrospectively reviewed. We measured the minimal length from metastasis to the bifurcation of the portal vein at the primary branch of the Glissonean tree and defined it as “Centrality”. Predictive effects on positive resection margin and overall survival of centrality were statistically analyzed. Results The value as a predictive factor for the positive resection margin of centrality was analyzed by the receiver operating characteristic curve (area under the curve = 0.72, P<0.001). In multivariate analysis, total number of metastases ≥ 3 and centrality ≤ 1.5 cm were significant risk factors of overall survival. Patients with these two risk factors (n=21) had worse 5-year overall survival (10.7%) than patients with one (n=35, 58.3%) or no risk factor (n=68, 69.2%). In subgroups analysis, neoadjuvant chemotherapy improved overall survival in patients with these two risk factors. Conclusion Centrality was related with a positive resection margin and had a negative effect on survival. By combining the total number of metastases with centrality, we could determine disease prognosis and neoadjuvant chemotherapy indications for advanced colorectal cancer with liver metastasis.

scholarly journals Nomogram for Predicting Occurrence of Synchronous Liver Metastasis in Colorectal Cancer: A Single-center Retrospective Study Based on Pathological Factors

2021 ◽  
Author(s):  
Yunxiao Liu ◽  
Yuliuming Wang ◽  
Hao Zhang ◽  
Mingyu Zheng ◽  
Chunlin Wang ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Liver Metastasis ◽  
Calibration Curve ◽  
Roc Curves ◽  
Logistic Regression Models ◽  
Actual Observation ◽  
N Stage ◽  
Medical University ◽  
Development And Validation ◽  
Observation Results

Abstract PurposeThe purpose of this study was to explore the risk factors for liver metastasis (LM) of colorectal cancer (CRC) and to construct a nomogram for predicting the occurrence of synchronous LM based on baseline and pathological information.MethodsThe baseline and pathological information of 3190 CRC patients from the Department of Colorectal Surgery, the Second Affiliated Hospital of Harbin Medical University between 2012 and 2020 were included. All patients were divided into development and validation cohorts with the 1:1 ratio. Univariate and multivariate logistic regression models were utilized to identify the potential predictors of LM in CRC patients. Using the R tool to create a predictive nomogram. In addition, receiver operating characteristic (ROC) curves was calculated to describe the discriminability of the nomogram. A calibration curve was plotted to compare the predicted and observed results of the nomogram. Decision-making curve analysis (DCA) was used to evaluate the clinical effect of nomogram.ResultsThe nomogram consisted of six features including tumor site, vascular invasion (VI), T stage, N stage, preoperative CEA and CA-199 level. ROC curves for the LM nomogram indicated good discrimination in the development cohort (AUC = 0.885, 95% CI 0.854-0.916) and the validation cohort (AUC = 0.857, 95% CI 0.821-0.893). The calibration curve showed that the prediction results of the nomogram was in good agreement with the actual observation results. Moreover, the DCA curves determined the clinical application value of predictive nomogram.ConclusionsThe pathologic-based nomogram could help clinicians to predict the occurrence of synchronous LM in postoperative CRC patients and provide a reference to perform appropriate metastatic screening plans and rational therapeutic options for the special population.

PET-CT Standard uptake value predict bevacizumab-containing chemotherapy response and prognosis for unresectable colorectal cancer liver metastasis

2019 ◽  
Author(s):  
Yang Lv ◽  
QingYang Feng ◽  
WenTao Tang ◽  
YuQiu Xu ◽  
SongBin Lin ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Liver Metastasis ◽  
Tumor Size ◽  
Metastatic Tumor ◽  
Standard Uptake Value ◽  
Primary Lesion ◽  
First Line ◽  
Colorectal Cancer Liver Metastasis ◽  
Pet Ct ◽  
Line Chemotherapy

Abstract Background: Standard uptake value (SUV) of PET-CT is an indicator of tumor metabolic response. In this paper, we aim to explore the clinical value of SUV on the unresectable colorectal cancer liver metastasis (CRLM) patients receiving bevacizumab-containing chemotherapy. Method: This study was performed retrospectively. A total of 185 CRLM patients between April 2011 to December 2015 with complete clinical data were included in this study. All the enrolled patients were assigned into two treatment cohorts (bevacizumab plus first-line chemotherapy cohort and chemotherapy only cohort). A blindly, independent radiologist evaluated images for RECIST and morphologic response. All clinical variables, and various PET/CT parameters were statistically compared with progression-free survival (PFS) and overall survival (OS). Primary and Metastatic tumor SUV were selected for analysis. Results: Among the 185 patients, 101 patients received first line chemotherapy plus bevacizumab (beva cohort), 84 patients only received first-line chemotherapy (CMT cohort). Baseline characteristics of two cohorts showed no statistical difference (P>0.05). Primary SUV level was correlated with primary tumor size, while metastatic SUV was statistically correlated with metastatic tumor number and tumor size (P=0.000). Primary lesion, metastatic lesion SUV and elevation of SUV demonstrated prognostic role for OS (P<0.05). SUV gap were statistically associated with optimal response in bevacizumab cohort (P=0.03) and no-PD status in chemotherapy cohort (P=0.019), respectively. After multivariate analysis, elevated SUV is an independent risk factor for OS (P=0.000). Besides, elevation of SUV between metastatic and primary lesion can be a predictive factor for bevacizumab survival benefit. Conclusion: PET-CT scan is important for CRLM patients. Our study demonstrated that an elevation of SUV was a better prognostic and predictive marker for CRLM patients.

scholarly journals Targeted UPLC-MS Metabolic Analysis of Human Faeces Reveals Novel Low-Invasive Candidate Markers for Colorectal Cancer

Cancers ◽  
2018 ◽  
Vol 10 (9) ◽  
pp. 300 ◽  
Author(s):  
Joaquin Cubiella ◽  
Marc Clos-Garcia ◽  
Cristina Alonso ◽  
Ibon Martinez-Arranz ◽  
Miriam Perez-Cormenzana ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Predictive Model ◽  
Precancerous Lesions ◽  
Tumour Progression ◽  
Haemoglobin Concentration ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Ultra Performance Liquid Chromatography ◽  
Advanced Neoplasia ◽  
Flight Mass Spectrometry

Low invasive tests with high sensitivity for colorectal cancer and advanced precancerous lesions will increase adherence rates, and improve clinical outcomes. We have performed an ultra-performance liquid chromatography/time-of-flight mass spectrometry (UPLC-(TOF) MS)-based metabolomics study to identify faecal biomarkers for the detection of patients with advanced neoplasia. A cohort of 80 patients with advanced neoplasia (40 advanced adenomas and 40 colorectal cancers) and 49 healthy subjects were analysed in the study. We evaluated the faecal levels of 105 metabolites including glycerolipids, glycerophospholipids, sterol lipids and sphingolipids. We found 18 metabolites that were significantly altered in patients with advanced neoplasia compared to controls. The combinations of seven metabolites including ChoE(18:1), ChoE(18:2), ChoE(20:4), PE(16:0/18:1), SM(d18:1/23:0), SM(42:3) and TG(54:1), discriminated advanced neoplasia patients from healthy controls. These seven metabolites were employed to construct a predictive model that provides an area under the curve (AUC) median value of 0.821. The inclusion of faecal haemoglobin concentration in the metabolomics signature improved the predictive model to an AUC of 0.885. In silico gene expression analysis of tumour tissue supports our results and puts the differentially expressed metabolites into biological context, showing that glycerolipids and sphingolipids metabolism and GPI-anchor biosynthesis pathways may play a role in tumour progression.

scholarly journals Circulating miRNA as Biomarkers for Colorectal Cancer Diagnosis and Liver Metastasis

Diagnostics ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 341
Author(s):  
Farah J. Nassar ◽  
Zahraa S. Msheik ◽  
Maha M. Itani ◽  
Remie El Helou ◽  
Ruba Hadla ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Liver Metastasis ◽  
Diagnostic Accuracy ◽  
Area Under The Curve ◽  
Stage Iv ◽  
Screening Tests ◽  
Operating Characteristics ◽  
Diagnostic Biomarkers ◽  
Circulating Mirna ◽  
Non Invasive

Colorectal cancer (CRC) is the second leading cause of cancer deaths worldwide. Stage IV CRC patients have poor prognosis with a five-year survival rate of 14%. Liver metastasis is the main cause of mortality in CRC patients. Since current screening tests have several drawbacks, effective stable non-invasive biomarkers such as microRNA (miRNA) are needed. We aim to investigate the expression of miRNA (miR-21, miR-19a, miR-23a, miR-29a, miR-145, miR-203, miR-155, miR-210, miR-31, and miR-345) in the plasma of 62 Lebanese Stage IV CRC patients and 44 healthy subjects using RT-qPCR, as well as to evaluate their potential for diagnosis of advanced CRC and its liver metastasis using the Receiver Operating Characteristics (ROC) curve. miR-21, miR-145, miR-203, miR-155, miR-210, miR-31, and miR-345 were significantly upregulated in the plasma of surgery naïve CRC patients when compared to healthy individuals. We identified two panels of miRNA that could be used for diagnosis of Stage IV CRC (miR-21 and miR-210) with an area under the curve (AUC) of 0.731 and diagnostic accuracy of 69% and liver metastasis (miR-210 and miR-203) with an AUC = 0.833 and diagnostic accuracy of 72%. Panels of specific circulating miRNA, which require further validation, could be potential non-invasive diagnostic biomarkers for CRC and liver metastasis.

scholarly journals Development of a Novel Prognostic Model for Predicting Lymph Node Metastasis in Early Colorectal Cancer: Analysis Based on the Surveillance, Epidemiology, and End Results Database

2021 ◽  
Vol 11 ◽  
Author(s):  
Ji Hyun Ahn ◽  
Min Seob Kwak ◽  
Hun Hee Lee ◽  
Jae Myung Cha ◽  
Hyun Phil Shin ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Predictive Model ◽  
Tumor Size ◽  
Prediction Models ◽  
Early Colorectal Cancer ◽  
Support Vector ◽  
Node Metastasis ◽  
End Results

BackgroundIdentification of a simplified prediction model for lymph node metastasis (LNM) for patients with early colorectal cancer (CRC) is urgently needed to determine treatment and follow-up strategies. Therefore, in this study, we aimed to develop an accurate predictive model for LNM in early CRC.MethodsWe analyzed data from the 2004-2016 Surveillance Epidemiology and End Results database to develop and validate prediction models for LNM. Seven models, namely, logistic regression, XGBoost, k-nearest neighbors, classification and regression trees model, support vector machines, neural network, and random forest (RF) models, were used.ResultsA total of 26,733 patients with a diagnosis of early CRC (T1) were analyzed. The models included 8 independent prognostic variables; age at diagnosis, sex, race, primary site, histologic type, tumor grade, and, tumor size. LNM was significantly more frequent in patients with larger tumors, women, younger patients, and patients with more poorly differentiated tumor. The RF model showed the best predictive performance in comparison to the other method, achieving an accuracy of 96.0%, a sensitivity of 99.7%, a specificity of 92.9%, and an area under the curve of 0.991. Tumor size is the most important features in predicting LNM in early CRC.ConclusionWe established a simplified reproducible predictive model for LNM in early CRC that could be used to guide treatment decisions. These findings warrant further confirmation in large prospective clinical trials.

Sign in / Sign up

Export Citation Format

Share Document