The potential in artificial intelligence-driven radiomic signature to predict survival in patients with metastatic colorectal cancer treated with cetuximab-based therapy.

2020 ◽  
Vol 38 (4_suppl) ◽  
pp. 247-247
Author(s):  
Laurent Dercle ◽  
Lin Lu ◽  
Lawrence Howard Schwartz ◽  
Min Qian ◽  
Sabine Tejpar ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Cox Regression ◽  
Tumor Imaging ◽  
Roc Curves ◽  
Standard Of Care ◽  
Treatment Quality ◽  
Ct Scans ◽  
Imaging Features ◽  
Data Set ◽  
Mutational Status

247 Background: This analysis was undertaken to forecast survival and enhance treatment decisions for patients (pts) with colorectal cancer (CRC) with liver metastases sensitive to folinic acid, fluorouracil and irinotecan (FOLFIRI) alone [F] or in combination with cetuximab [FC] using simple quantitative radiomic changes between CT scans at baseline and 8 weeks. Methods: We retrospectively analyzed 667 pts with KRAS-unselected metastatic CRC in NCT00154102 treated with F and FC. CT quality was classified as high (HQ) or standard (SQ), and four data sets were created and named by treatment quality. Pts were randomly assigned 1:2 to training or validation sets: FCHQ, 38/78 pts; FCSQ, 62/124 pts; FHQ, 51/78 pts; FSQ, 78/158 pts. A machine-learning signature was trained using data set FCHQ to classify pts as treatment-sensitive or treatment-insensitive using just 4 of 3,499 potential radiomic imaging features. Performance was calibrated/validated using ROC curves. Hazard ratios (HRs) and Cox regression models were used to evaluate association with overall survival (OS). Results: The signature used decrease in tumor heterogeneity plus boundary infiltration to successfully predict sensitivity to FC (FCHQ: AUC, 0.80; FCSQ: AUC, 0.72) but failed with non-cetuximab regimens (FHQ: AUC, 0.59; FSQ: AUC, 0.55). The radiomic signature outperformed existing biomarkers ( KRAS mutational status and tumor shrinkage by RECIST 1.1) for sensitivity to cetuximab-based therapy and was strongly associated with OS in the cetuximab-containing sets FCHQ (HR, 44.3; p = 0.0001) and FCSQ (HR, 6.5; p = 0.005). Conclusions: This signature, derived from simple radiomic analysis of tumor imaging phenotype using only standard-of-care CT scans, appeared to be treatment-specific and was superior to all tested prognostic biomarkers. The signature provided early prediction of sensitivity and survival and could be used to guide treatment continuation decisions.

scholarly journals Radiomics Response Signature for Identification of Metastatic Colorectal Cancer Sensitive to Therapies Targeting EGFR Pathway

2020 ◽  
Vol 112 (9) ◽  
pp. 902-912 ◽  
Author(s):  
Laurent Dercle ◽  
Lin Lu ◽  
Lawrence H Schwartz ◽  
Min Qian ◽  
Sabine Tejpar ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Computed Tomography ◽  
Metastatic Colorectal Cancer ◽  
Cox Regression ◽  
Surrogate Marker ◽  
Treatment Quality ◽  
Imaging Biomarkers ◽  
Mutational Status ◽  
Radiomics Signature ◽  
Treatment Sensitivity

Abstract Background The authors sought to forecast survival and enhance treatment decisions for patients with liver metastatic colorectal cancer by using on-treatment radiomics signature to predict tumor sensitiveness to irinotecan, 5-fluorouracil, and leucovorin (FOLFIRI) alone (F) or in combination with cetuximab (FC). Methods We retrospectively analyzed 667 metastatic colorectal cancer patients treated with F or FC. Computed tomography quality was classified as high (HQ) or standard (SD). Four datasets were created using the nomenclature (treatment) – (quality). Patients were randomly assigned (2:1) to training or validation sets: FCHQ: 78:38, FCSD: 124:62, FHQ: 78:51, FSD: 158:78. Four tumor-imaging biomarkers measured quantitative radiomics changes between standard of care computed tomography scans at baseline and 8 weeks. Using machine learning, the performance of the signature to classify tumors as treatment sensitive or treatment insensitive was trained and validated using receiver operating characteristic (ROC) curves. Hazard ratio and Cox regression models evaluated association with overall survival (OS). Results The signature (area under the ROC curve [95% confidence interval (CI)]) used temporal decrease in tumor spatial heterogeneity plus boundary infiltration to successfully predict sensitivity to antiepidermal growth factor receptor therapy (FCHQ: 0.80 [95% CI = 0.69 to 0.94], FCSD: 0.72 [95% CI = 0.59 to 0.83]) but failed with chemotherapy (FHQ: 0.59 [95% CI = 0.44 to 0.72], FSD: 0.55 [95% CI = 0.43 to 0.66]). In cetuximab-containing sets, radiomics signature outperformed existing biomarkers (KRAS-mutational status, and tumor shrinkage by RECIST 1.1) for detection of treatment sensitivity and was strongly associated with OS (two-sided P < .005). Conclusions Radiomics response signature can serve as an intermediate surrogate marker of OS. The signature outperformed known biomarkers in providing an early prediction of treatment sensitivity and could be used to guide cetuximab treatment continuation decisions.

A five-gene signature for predicting the prognosis of colorectal cancer

2020 ◽  
Vol 20 ◽  
Author(s):  
Junfeng Hong ◽  
Xiangwu Lin ◽  
Xinyu Hu ◽  
Xiaolong Wu ◽  
Wenzheng Fang
Keyword(s):  
Colorectal Cancer ◽  
Predictive Model ◽  
Cox Regression ◽  
Predictive Performance ◽  
Roc Curves ◽  
Gene Signature ◽  
Differential Analysis ◽  
Data Set ◽  
Treatment Situation ◽  
Limma Package

Background: Colorectal cancer (CRC) is a kind of tumor with high incidence and its treatment situation is still very severe despite of the constant renewal and development of treatment methods. Objective: To assist the prognosis, monitoring and survival of CRC patients with a model. Methods: In this study, we established a new prognostic model for CRC. Four groups of CRC data were accessed from GEO database, and then differential analysis (logFoldChange>1, adjustP<0.05) was carried out by using limma package along with the RobustRankAggreg package used to identify the overlapping differentially expressed genes (DEGs). Univariate and multivariate Cox regression analyses were performed on the DEGs to screen the genes related to patient’s prognosis, and a five-gene prognostic prediction model (including RPX, CXCL13, MMP10, FABP4 and CLDN23) was constructed. Then, we further plotted ROC curves to evaluate the predictive performance of the five-gene prognostic signature in the TCGA data sets (the AUC values of 1, 3, 5-year survival were 0.68, 0.632, 0.675, respectively) and an external independent data set GSE2962 (the AUC values of 1, 3, 5-year survival were 0.689, 0.702, 0.631, respectively). Results: The results showed that the model could effectively predict the prognosis of CRC patients, which provides a robust predictive model for the prognosis of CRC patients. Conclusion: The model could effectively predict the prognosis of CRC patients, which provides a robust predictive model for the prognosis of CRC patients.

scholarly journals A novel predictor of clinical progression in patients on active surveillance for prostate cancer

2019 ◽  
Vol 13 (8) ◽  
Author(s):  
Guan Hee Tan ◽  
Antonio Finelli ◽  
Ardalan Ahmad ◽  
Marian Wettstein ◽  
Alexandre Zlotta ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Active Surveillance ◽  
Cox Regression ◽  
Area Under The Curve ◽  
Progression Free Survival ◽  
Roc Curves ◽  
Standard Of Care ◽  
Low Risk ◽  
Clinical Progression

Introduction: Active surveillance (AS) is standard of care in low-risk prostate cancer (PC). This study describes a novel total cancer location (TCLo) density metric and aims to determine its performance in predicting clinical progression (CP) and grade progression (GP).     Methods: This was a retrospective study of patients on AS after confirmatory biopsy (CBx). We excluded patients with Gleason ≥7 at CBx and <2 years follow-up. TCLo was the number of locations with positive cores at diagnosis (DBx) and CBx. TCLo density was TCLo / prostate volume (PV). CP was progression to any active treatment while GP occurred if Gleason ≥7 was identified on repeat biopsy or surgical pathology. Independent predictors of time to CP or GP were estimated with Cox regression. Kaplan-Meier analysis compared progression-free survival curves between TCLo density groups. Test characteristics of TCLo were explored with receiver operating characteristic (ROC) curves.     Results: We included 181 patients who had CBx between 2012-2015, and met inclusion criteria. The mean age of patients was 62.58 years (SD=7.13) and median follow-up was 60.9 months (IQR=23.4). A high TCLo density score (>0.05) was independently associated with time to CP (HR 4.70, 95% CI: 2.62-8.42, p<0.001), and GP (HR 3.85, 95% CI: 1.91-7.73, p<0.001). ROC curves showed TCLo density has greater area under the curve than number of positive cores at CBx in predicting progression.     Conclusion: TCLo density is able to stratify patients on AS for risk of CP and GP. With further validation, it could be added to the decision-making algorithm in AS for low-risk localized PC.

scholarly journals Development of an Immune Infiltration-Related Eight-Gene Prognostic Signature in Colorectal Cancer Microenvironment

2020 ◽  
Vol 2020 ◽  
pp. 1-43
Author(s):  
Beilei Wu ◽  
Lijun Tao ◽  
Daqing Yang ◽  
Wei Li ◽  
Hongbo Xu ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Risk Score ◽  
Immune Cells ◽  
Clinical Characteristics ◽  
Cox Regression ◽  
Roc Curves ◽  
Functional Enrichment ◽  
Cox Regression Analysis ◽  
Immune Genes ◽  
Score Model

Objective. Stromal cells and immune cells have important clinical significance in the microenvironment of colorectal cancer (CRC). This study is aimed at developing a CRC gene signature on the basis of stromal and immune scores. Methods. A cohort of CRC patients (n=433) were adopted from The Cancer Genome Atlas (TCGA) database. Stromal/immune scores were calculated by the ESTIMATE algorithm. Correlation between prognosis/clinical characteristics and stromal/immune scores was assessed. Differentially expressed stromal and immune genes were identified. Their potential functions were annotated by functional enrichment analysis. Cox regression analysis was used to develop an eight-gene risk score model. Its predictive efficacies for 3 years, 5 years, overall survival (OS), and progression-free survival interval (PFI) were evaluated using time-dependent receiver operating characteristic (ROC) curves. The correlation between the risk score and the infiltering levels of six immune cells was analyzed using TIMER. The risk score was validated using an independent dataset. Results. Immune score was in a significant association with prognosis and clinical characteristics of CRC. 736 upregulated and two downregulated stromal and immune genes were identified, which were mainly enriched into immune-related biological processes and pathways. An-eight gene prognostic risk score model was conducted, consisting of CCL22, CD36, CPA3, CPT1C, KCNE4, NFATC1, RASGRP2, and SLC2A3. High risk score indicated a poor prognosis of patients. The area under the ROC curves (AUC) s of the model for 3 years, 5 years, OS, and PFI were 0.71, 0.70, 0.73, and 0.66, respectively. Thus, the model possessed well performance for prediction of patients’ prognosis, which was confirmed by an external dataset. Moreover, the risk score was significantly correlated with immune cell infiltration. Conclusion. Our study conducted an immune-related prognostic risk score model, which could provide novel targets for immunotherapy of CRC.

scholarly journals Quantitative CT imaging features correlate with colorectal cancer liver metastases (CLM) mutational status

HPB ◽  
2018 ◽  
Vol 20 ◽  
pp. S56-S57
Author(s):  
R.M. Marcus ◽  
D.T. Fuentes ◽  
H.A. Lillemoe ◽  
A. Qayyum ◽  
T.A. Aloia
Keyword(s):  
Colorectal Cancer ◽  
Liver Metastases ◽  
Ct Imaging ◽  
Imaging Features ◽  
Quantitative Ct ◽  
Colorectal Cancer Liver Metastases ◽  
Mutational Status

scholarly journals Diagnostic Value of Initial Chest CT Findings for the Need of ICU Treatment/Intubation in Patients with COVID-19

Diagnostics ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 929 ◽  
Author(s):  
Laura Büttner ◽  
Annette Aigner ◽  
Florian Nima Fleckenstein ◽  
Christina Maria Hamper ◽  
Martin Jonczyk ◽  
...  
Keyword(s):  
Quantitative Method ◽  
Cox Regression ◽  
Roc Curves ◽  
Lung Parenchyma ◽  
Subjective Assessment ◽  
Diagnostic Value ◽  
Ct Scans ◽  
Diagnostic Ability ◽  
Icu Admission ◽  
Icu Treatment

Computed tomography (CT) plays an important role in the diagnosis of COVID-19. The aim of this study was to evaluate a simple, semi-quantitative method that can be used for identifying patients in need of subsequent intensive care unit (ICU) treatment and intubation. We retrospectively analyzed the initial CT scans of 28 patients who tested positive for SARS-CoV-2 at our Level-I center. The extent of lung involvement on CT was classified both subjectively and with a simple semi-quantitative method measuring the affected area at three lung levels. Competing risks Cox regression was used to identify factors associated with the time to ICU admission and intubation. Their potential diagnostic ability was assessed with receiver operating characteristic (ROC)/area under the ROC curves (AUC) analysis. A 10% increase in the affected lung parenchyma area increased the instantaneous risk of intubation (hazard ratio (HR) = 2.00) and the instantaneous risk of ICU admission (HR 1.73). The semi-quantitative measurement outperformed the subjective assessment diagnostic ability (AUC = 85.6% for ICU treatment, 71.9% for intubation). This simple measurement of the involved lung area in initial CT scans of COVID-19 patients may allow early identification of patients in need of ICU treatment/intubation and thus help make optimal use of limited ICU/ventilation resources in hospitals.

Utilization of imaging and outcomes of care among metastatic colorectal cancer (mCRC) patients (pts) receiving bevacizumab containing regimens.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e14011-e14011
Author(s):  
Afsaneh Barzi ◽  
Hanke Zheng ◽  
Jeffrey McCombs
Keyword(s):  
Colorectal Cancer ◽  
Ct Scan ◽  
Standard Of Care ◽  
Median Number ◽  
Ct Scans ◽  
P Value ◽  
First Line ◽  
Probability Of Survival ◽  
First Line Therapy ◽  
Line Therapy

e14011 Background: Chemotherapy combined with bevacizumab is the most commonly used treatment first line therapy in pts with mCRC. Decisions for continuation or change of chemotherapy are based on the findings of CT scan, the most commonly used from of imaging in this population. Modeled after clinical trials, CT scan every 2 months is adopted as a standard of care. Yet, patterns of utilization of CT scan in general population is unknown. We set to explore CT scan utilization and associated outcomes among pts with mCRC. Methods: The De-identified Clinformatics Data Mart (OptumInsight, Eden Prairie, MN) covering January 2008 to December 2016 was used for this analysis. Pts with two out-patient and/or one in-patient ICD codes for colorectal cancer were identified. Pts with at least 180 days of enrollment, no chemotherapy within 120 days prior to chemotherapy, and at least one claim for CT scan were eligible for analysis. Recipients of FOLFOX (CAPOX) or FOLFIRI (XILIRI) +bevacizumab were identified using HCPCS codes and the data of their 1sttreatment was registered as index date. The primary endpoint of the analysis was exposure to both FOLFIRI and FOLFOX, secondary endpoint was survival. SAS software was used for data processing and analysis. Results: A total of 3261 pts met the inclusion criteria 78% with oxaliplatin based regimens and 22% with irinotecan regimens. The median age of the population is 66 (19-89), and 58.3% of the identified pts were male. The median duration of first line therapy was 119 days. Median number of CT scan during first line was 2.3. The median and mean number of CT scan per 2 months were 0.82 and 0.94. There was no difference in age, gender, and comorbidities in those with less than 2 vs. 2 or more CT scans. Exposure to both regimens (measured with switching from one regimen to another) was 35% in pts with less than 2 CT scans and 44% in those with 2 or more CT scan (p-value < 0.0001). Probability of survival at 12 months was 83% for all patients regardless of the frequency of scans. Conclusions: In patients with mCRC more frequent scans is associated with higher probability of access to active agents. However, survival probability at 12 months was not different between the two groups.

MiR-485-5p as a potential biomarker and tumor suppressor in human colorectal cancer

2020 ◽  
Vol 14 (3) ◽  
pp. 239-248 ◽  
Author(s):  
Yuqin Pan ◽  
Jian Qin ◽  
Huiling Sun ◽  
Tao Xu ◽  
Shukui Wang ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Tumor Suppressor ◽  
Cox Regression ◽  
Roc Curves ◽  
Functional Study ◽  
Kaplan Meier ◽  
Potential Biomarker ◽  
Polymerase Chain

Aim: To investigate the role of miR-485-5p in colorectal cancer (CRC). Methodology: The level of miR-485-5p in serum and cell lines were measured by quantitative real-time polymerase chain reaction, and analyzed the diagnostic and prognostic value. Additionally, the biological effect of miR-485-5p on CRC cells was also explored in vitro. Results: The receiver operating characteristic (ROC) curves analysis revealed that miR-485-5p was a diagnostic candidate. Kaplan-Meier analyses demonstrated that patients with low serum miR-485-5p had shorter overall survival. In addition, the result of cox regression model indicated that miR-485-5p was not an independent risk factor for progression. Functional study revealed that overexpression of miR-485-5p could inhibit CRC cell proliferation, invasion and facilitates cell apoptosis. Conclusion: Our study revealed that miR-485-5p was a tumor suppressor and it could serve as a potential prognostic biomarker in CRC.

scholarly journals Early Postoperative Serum Carcinoembryonic Antigen Is a Stronger Independent Prognostic Factor for Stage II Colorectal Cancer Patients Than T4 Stage and Preoperative CEA

2022 ◽  
Vol 11 ◽  
Author(s):  
Du Fenqi ◽  
Liu Yupeng ◽  
Zhang Qiuju ◽  
Yuan Chao ◽  
Song Wenjie ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Sensitivity Analysis ◽  
Cox Regression ◽  
Roc Curves ◽  
Stage Ii ◽  
P Values ◽  
Cutoff Value ◽  
Absolute Value ◽  
Serum Carcinoembryonic Antigen ◽  
Before And After

BackgroundSerum carcinoembryonic antigen (CEA) is an important biomarker for diagnosis, prognosis, recurrence, metastasis monitoring, and the evaluation of the effect of chemotherapy in colorectal cancer (CRC). However, few studies have focused on the role of early postoperative CEA in the prognosis of stage II CRC.MethodsPatients with stage II CRC diagnosed between January 2007 and December 2015 were included. Receiver operating characteristic (ROC) curves were used to obtain the cutoff value of early postoperative CEA, CEA ratio and CEA absolute value. The areas under curves (AUCs) were used to estimate the predictive abilities of the CEA and T stage. The stepwise regression method was used to screen the factors included in the Cox regression analysis. Before and after propensity score (PS) - adjusted Cox regression and sensitivity analysis were used to identify the relationship between early postoperative CEA and prognosis. Meta-analysis was performed to verify the results. Kaplan-Meier survival curves were used to estimate the effects of CEA on prognosis.ResultsWe included 1081 eligible patients. ROC curves suggested that the cutoff value of early postoperative CEA was 3.66 ng/ml (P &lt;0.001) and the AUC showed early postoperative CEA was the most significant prognostic marker in stage II CRC (P = 0.0189). The Cox regression and sensitivity analysis before and after adjusting for PS both revealed elevated early postoperative CEA was the strongest independent prognostic factor of OS, DFS, and CSS (P &lt; 0.001). Survival analysis revealed that patients with elevated early postoperative CEA had lower OS (53.62% VS 84.16%), DFS (50.03% VS 86.75%), and CSS (61.77% VS 90.30%) than patients with normal early postoperative CEA (P &lt; 0.001). When the postoperative CEA was positive, the preoperative CEA level showed no significant effect on the patient’s prognosis (all P-values were &gt; 0.05). Patients with a CEA ratio ≤0.55 or CEA absolute value ≤-0.98 had a worse prognosis (all P-values were &lt; 0.001). Survival analysis suggested that adjuvant chemotherapy for stage II CRC patients with elevated early postoperative CEA may improve the CSS (P = 0.040).ConclusionsEarly postoperative CEA was a better biomarker for prognosis of stage II CRC patients than T stage and preoperative CEA, and has the potential to become a high-risk factor to guide the prognosis and treatment of stage II CRC patients.

Apparent diffusion coefficient (ADC) decrease to predict longer survival in glioblastoma patients treated by dendritic cell immunotherapy plus standard of care.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. 2065-2065
Author(s):  
Marica Eoli ◽  
Valeria Cuccarini ◽  
Domenico Aquino ◽  
Elena Anghileri ◽  
Maura Servida ◽  
...  
Keyword(s):  
Dendritic Cell ◽  
Cox Regression ◽  
Roc Curves ◽  
Standard Of Care ◽  
Quantitative Mri ◽  
Rank Test ◽  
Potential Contribution ◽  
Adc Value ◽  
Cell Immunotherapy ◽  
Apparent Diffusion

2065 Background: The MRI follow –up of patients affected by glioblastoma (GBM) and treated with immunotherapy may be difficult, as immune responses may mimic tumor progression. To explore the potential contribution of quantitative MRI to the identification of patients with clinical benefit benefit, we used advanced MRI to study GBM patients treated with dendritic cell (DC) immunotherapy added to standard treatment (surgery, radiotherapy with concomitant temozolomide (TMZ) followed by adjuvant TMZ; DENDR1 trial, EUDRACT N° 2008-005035-15). Methods: A retrospective analysis was performed on longitudinal MRIs obtained soon after radiotherapy, within two days before the first vaccination (basal MRI) and every two months, in 22 patients enrolled in DENDR1. The following parameters were collected: tumor volume of contrast–enhanced lesions, mean rCBV, maximal rCBV, mean ADC, minimal ADC, ADC skewness. Receiver Operating Characteristic (ROC) curves were used to determine optimal sensitivity and specificity in differentiating patients as responder or not responder. Association with PFS (as per RANO criteria) and OS was analyzed using log-rank test and Cox regression. Results: Ten patients with PFS > 12 months were defined as responders Their basal mean ADC was significantly higher than in non responders (1.34 ± 0.17 vs 1.14 ± 0.34, p = 0.03). After four DC vaccinations mean ADC significantly decreased in responders only from 1.34 ± 0.17 to 1.23 ±0.23 (p = 0.028); the decrease persisted during immunotherapy. A basal mean ADC value ≥ 1.07 and a decrease in mean ADC value ≥ 0.13 were significant predictors of longer PFS (15.4 vs 9 m p = 0.0006; 17.2 vs 10.2 p = 0.04) and OS (29 vs 12.5 mo p = 0.002; 33 vs 19.9 p = 0.04 No significant correlations between the other parameters and the outcome were observed. Conclusions: Association with prolonged survival may suggest that in DENDR1responders decreased ADC is partly contributed by immune cells infiltrating the tumor.

Sign in / Sign up

Export Citation Format

Share Document