scholarly journals Computed Tomography-Based Radiomics Model to Preoperatively Predict Microsatellite Instability Status in Colorectal Cancer: A Multicenter Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Zhi Li ◽  
Qi Zhong ◽  
Liang Zhang ◽  
Minhong Wang ◽  
Wenbo Xiao ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Feature Selection ◽  
Clinical Characteristics ◽  
External Validation ◽  
Training Set ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Auc Value ◽  
Validation Set

ObjectivesTo establish and validate a combined radiomics model based on radiomics features and clinical characteristics, and to predict microsatellite instability (MSI) status in colorectal cancer (CRC) patients preoperatively.MethodsA total of 368 patients from four hospitals, who underwent preoperative contrast-enhanced CT examination, were included in this study. The data of 226 patients from a single hospital were used as the training dataset. The data of 142 patients from the other three hospitals were used as an independent validation dataset. The regions of interest were drawn on the portal venous phase of contrast-enhanced CT images. The filtered radiomics features and clinical characteristics were combined. A total of 15 different discrimination models were constructed based on a feature selection strategy from a pool of 3 feature selection methods and a classifier from a pool of 5 classification algorithms. The generalization capability of each model was evaluated in an external validation set. The model with high area under the curve (AUC) value from the training set and without a significant decrease in the external validation set was final selected. The Brier score (BS) was used to quantify overall performance of the selected model.ResultsThe logistic regression model using the mutual information (MI) dimensionality reduction method was final selected with an AUC value of 0.79 for the training set and 0.73 for the external validation set to predicting MSI. The BS value of the model was 0.12 in the training set and 0.19 in the validation set.ConclusionThe established combined radiomics model has the potential to predict MSI status in CRC patients preoperatively.

scholarly journals Prediction models for clear cell renal cell carcinoma ISUP/WHO grade: comparison between CT radiomics and conventional contrast-enhanced CT

2020 ◽  
Vol 93 (1114) ◽  
pp. 20200131
Author(s):  
Dong Han ◽  
Yong Yu ◽  
Nan Yu ◽  
Shan Dang ◽  
Hongpei Wu ◽  
...  
Keyword(s):  
Prediction Model ◽  
Prediction Models ◽  
Statistical Significance ◽  
Net Benefit ◽  
Cell Renal Cell Carcinoma ◽  
Who Grade ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Validation Set

Objective: Comparing the prediction models for the ISUP/WHO grade of clear cell renal cell carcinoma (ccRCC) based on CT radiomics and conventional contrast-enhanced CT (CECT). Methods: The corticomedullary phase images of 119 cases of low-grade (I and II) and high-grade (III and IV) ccRCC based on 2016 ISUP/WHO pathological grading criteria were analyzed retrospectively. The patients were randomly divided into training and validation set by stratified sampling according to 7:3 ratio. Prediction models of ccRCC differentiation were constructed using CT radiomics and conventional CECT findings in the training setandwere validated using validation set. The discrimination, calibration, net reclassification index (NRI) and integrated discrimination improvement index (IDI) of the two prediction models were further compared. The decision curve was used to analyze the net benefit of patients under different probability thresholds of the two models. Results: In the training set, the C-statistics of radiomics prediction model was statistically higher than that of CECT (p < 0.05), with NRI of 9.52% and IDI of 21.6%, both with statistical significance (p < 0.01).In the validation set, the C-statistics of radiomics prediction model was also higher but did not show statistical significance (p = 0.07). The NRI and IDI was 14.29 and 33.7%, respectively, both statistically significant (p < 0.01). Validation set decision curve analysis showed the net benefit improvement of CT radiomics prediction model in the range of 3–81% over CECT. Conclusion: The prediction model using CT radiomics in corticomedullary phase is more effective for ccRCC ISUP/WHO grade than conventional CECT. Advances in knowledge: As a non-invasive analysis method, radiomics can predict the ISUP/WHO grade of ccRCC more effectively than traditional enhanced CT.

18F-FDG-PET (PET) and contrast-enhanced CT-scan (CT) in the evaluation of liver metastases from colorectal cancer after chemotherapy

2005 ◽  
Vol 23 (16_suppl) ◽  
pp. 3710-3710
Author(s):  
C. Carnaghi ◽  
A. Chiti ◽  
K. Marzo ◽  
M. Rodari ◽  
L. Rimassa ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Liver Metastases ◽  
Ct Scan ◽  
Fdg Pet ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
18F Fdg

18 F-FDG PET/contrast enhanced CT in the standard surveillance of high risk colorectal cancer patients

2014 ◽  
Vol 83 (12) ◽  
pp. 2224-2230 ◽  
Author(s):  
Germán Andrés Jiménez Londoño ◽  
Ana María García Vicente ◽  
Victoria Sánchez Pérez ◽  
Fátima Jiménez Aragón ◽  
Alberto León Martin ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
High Risk ◽  
Cancer Patients ◽  
Fdg Pet ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Colorectal Cancer Patients

Contrast-enhanced CT radiomics for predicting calcification in metastatic colorectal cancer: Based on machine learning.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e16095-e16095
Author(s):  
Yuwen Zhou ◽  
Qiu Meng
Keyword(s):  
Colorectal Cancer ◽  
Metastatic Colorectal Cancer ◽  
Validation Dataset ◽  
Textural Features ◽  
Slice Thickness ◽  
Invasive Approach ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Radiomics Signature

e16095 Background: In patients with metastatic colorectal cancer (mCRC), calcification is a predictive factor and associated with a better prognosis. This study was aimed to estimate the textural features performance derived from contrast-enhanced CT in prediction of calcification in mCRC. Methods: Four hundred fifty patients from a single center with pathologically diagnosed colorectal adenocarcinoma (training dataset, n = 159; validation dataset, n = 31) were enrolled in our retrospective study. A three-dimensional region of interest (ROI) around the margin of the lesion was manually assessed by two radiologists on the basis of CT scans, and all textural parameters were retrieved from the ROI. The least absolute shrinkage and selection operator (LASSO) method was applied to select the textural feature. The differential diagnostic capabilities of textural features, morphological features, and their combination were analyzed by receiver operating characteristic (ROC). AUC was used as the main indicator. Results: Twenty-one radiomics features extracted from contrast-enhanced CT were screened as a calcification-associated radiomics signature of mCRC. They were able to predict calcification in both the training group (slice thickness of 5 mm, sensitivity 0.84, specificity 0.71, accuracy 0.81, AUC 0.916, 95%CI 0.87-0.97) and the validation group (slice thickness of 5 mm, sensitivity 1.00, specificity 0.88, accuracy 0.77, AUC 0.964, 95%CI 0.904-1.0). Conclusions: In summary, a noninvasive radiomics signature derived from contrast-enhanced CT images was conveniently used for the prediction of calcification in mCRC before therapy, which might be a non-invasive approach in clinical practice to determine whether surgery is needed. However, multi-center studies with larger sample size are needed to confirm these results.

Comparison of Contrast-Enhanced CT and [18F]FDG PET/CT Analysis Using Kurtosis and Skewness in Patients with Primary Colorectal Cancer

2017 ◽  
Vol 19 (5) ◽  
pp. 795-803 ◽  
Author(s):  
Franca Wagner ◽  
Yahya Ali Hakami ◽  
Geoffrey Warnock ◽  
Gabriel Fischer ◽  
Martin W. Huellner ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Fdg Pet ◽  
Primary Colorectal Cancer ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Pet Ct ◽  
Enhanced Ct ◽  
Ct Analysis ◽  
18F Fdg ◽  
Fdg Pet Ct

We Should Desist Using RECIST, at Least in GIST

2007 ◽  
Vol 25 (13) ◽  
pp. 1760-1764 ◽  
Author(s):  
Robert S. Benjamin ◽  
Haesun Choi ◽  
Homer A. Macapinlac ◽  
Michael A. Burgess ◽  
Shreyaskumar R. Patel ◽  
...  
Keyword(s):  
Evaluation Criteria ◽  
Response Criteria ◽  
Training Set ◽  
Data Set ◽  
Contrast Enhanced Ct ◽  
Positron Emission ◽  
Contrast Enhanced ◽  
Choi Criteria ◽  
Enhanced Ct ◽  
Response Group

Purpose Response Evaluation Criteria in Solid Tumors (RECIST) are insensitive in evaluating imatinib-treated gastrointestinal stromal tumors (GISTs). Response by Choi criteria, a 10% decrease in size or a 15% decrease in density on contrast-enhanced CT, correlated well in a small training set of patients who showed response as measured by positron emission tomography, and was more predictive of time to tumor progression (TTP) than response by RECIST. This study was designed to validate these observations in an independent data set. Patients and Methods Fifty-eight patients with imatinib-treated GISTs were evaluated by RECIST and Choi criteria. TTP was compared with TTP in the training set. Patients were analyzed initially with follow-up to 28 months, extended to 60 months for survival analysis. Results Patients who met Choi response criteria on CT at 2 months had significantly better TTP than those who did not (P = .0002), whereas response group by RECIST was not significantly correlated with TTP. Even when the 98 patients from both sets were analyzed together, the response group by RECIST did not correlate significantly with TTP, whereas response group by Choi criteria did correlate significantly with TTP. Disease-specific survival (DSS) was also significantly correlated with response group by Choi criteria (P = .04), but not with response group by RECIST. Conclusion Choi response criteria are reproducible, more sensitive, and more precise than RECIST in assessing the response of GISTs to imatinib mesylate. Response by Choi criteria, unlike response by RECIST, correlates significantly with TTP and DSS. Response by Choi criteria should be incorporated routinely into future studies of GIST therapy. We should desist using RECIST, at least in GIST.

Sign in / Sign up

Export Citation Format

Share Document