scholarly journals Radiomics Analysis of PET and CT Components of 18F-FDG PET/CT Imaging for Prediction of Progression-Free Survival in Advanced High-Grade Serous Ovarian Cancer

2021 ◽  
Vol 11 ◽  
Author(s):  
Xihai Wang ◽  
Zaiming Lu
Keyword(s):  
Clinical Features ◽  
Cox Regression ◽  
Progression Free Survival ◽  
Predictive Performance ◽  
Ct Images ◽  
Metabolic Parameters ◽  
P Value ◽  
Free Survival ◽  
Pet Ct ◽  
Fdg Pet Ct

ObjectiveTo investigate radiomics features extracted from PET and CT components of 18F-FDG PET/CT images integrating clinical factors and metabolic parameters of PET to predict progression-free survival (PFS) in advanced high-grade serous ovarian cancer (HGSOC).MethodsA total of 261 patients were finally enrolled in this study and randomly divided into training (n=182) and validation cohorts (n=79). The data of clinical features and metabolic parameters of PET were reviewed from hospital information system(HIS). All volumes of interest (VOIs) of PET/CT images were semi-automatically segmented with a threshold of 42% of maximal standard uptake value (SUVmax) in PET images. A total of 1700 (850×2) radiomics features were separately extracted from PET and CT components of PET/CT images. Then two radiomics signatures (RSs) were constructed by the least absolute shrinkage and selection operator (LASSO) method. The RSs of PET (PET_RS) and CT components(CT_RS) were separately divided into low and high RS groups according to the optimum cutoff value. The potential associations between RSs with PFS were assessed in training and validation cohorts based on the Log-rank test. Clinical features and metabolic parameters of PET images (PET_MP) with P-value <0.05 in univariate and multivariate Cox regression were combined with PET_RS and CT_RS to develop prediction nomograms (Clinical, Clinical+ PET_MP, Clinical+ PET_RS, Clinical+ CT_RS, Clinical+ PET_MP + PET_RS, Clinical+ PET_MP + CT_RS) by using multivariate Cox regression. The concordance index (C-index), calibration curve, and net reclassification improvement (NRI) was applied to evaluate the predictive performance of nomograms in training and validation cohorts.ResultsIn univariate Cox regression analysis, six clinical features were significantly associated with PFS. Ten PET radiomics features were selected by LASSO to construct PET_RS, and 1 CT radiomics features to construct CT_RS. PET_RS and CT_RS was significantly associated with PFS both in training (P <0.00 for both RSs) and validation cohorts (P=0.01 for both RSs). Because there was no PET_MP significantly associated with PFS in training cohorts. Only three models were constructed by 4 clinical features with P-value <0.05 in multivariate Cox regression and RSs (Clinical, Clinical+ PET_RS, Clinical+ CT_RS). Clinical+ PET_RS model showed higher prognostic performance than other models in training cohort (C-index=0.70, 95% CI 0.68-0.72) and validation cohort (C-index=0.70, 95% CI 0.66-0.74). Calibration curves of each model for prediction of 1-, 3-year PFS indicated Clinical +PET_RS model showed excellent agreements between estimated and the observed 1-, 3-outcomes. Compared to the basic clinical model, Clinical+ PET_MS model resulted in greater improvement in predictive performance in the validation cohort.ConclusionPET_RS can improve diagnostic accuracy and provide complementary prognostic information compared with the use of clinical factors alone or combined with CT_RS. The newly developed radiomics nomogram is an effective tool to predict PFS for patients with advanced HGSOC.

Correlation between total lesion glycolysis in 18F-FDG PET/CT and KRAS mutation and clinical features in patients with resectable colon cancer.

2017 ◽  
Vol 35 (4_suppl) ◽  
pp. 555-555
Author(s):  
Ji Hyung Hong ◽  
Jae Ho Byun ◽  
Eun Kyoung Choi ◽  
Jin Kyoung Oh ◽  
Ji-Hun Kim ◽  
...  
Keyword(s):  
Colon Cancer ◽  
Clinical Features ◽  
Fdg Pet ◽  
Kras Mutation ◽  
Total Lesion Glycolysis ◽  
Metabolic Parameters ◽  
P Value ◽  
Pet Ct ◽  
Pre Treatment ◽  
Fdg Pet Ct

555 Background: Recently, novel metabolic parameters in 18F-FDG PET/CT such as total lesion glycolysis (TLG) and metabolic tumor volume (MTV) as well as maximum standardized uptake value (SUVmax) have been reported to be prognostic and be related with genomic aberration. We evaluated the prognostic role of these metabolic parameters and the correlation with clinical features in resected colon cancer. Methods: This study included 212 colon cancer patients who underwent surgical resection of stage II and III disease and conducted pre-treatment 18F-FDG PET/CT between February 2009 and December 2013. TLG, MTV of the primary tumors as well as SUVmax were analyzed according to clinical features including KRAS mutation, pre-treatment carcinoembryonic antigen (CEA) and recurrence free survival (RFS). Results: TLG was significantly higher in patients with right colon cancer than those with left colon cancer ( P = 0.015) and in patients with elevated CEA than those with normal range of CEA ( P = 0.034), while MTV and SUVmax were not correlated with cancer location and CEA level. KRAS mutation analysis using peptide nucleic acid-mediated real-time polymerase chain reaction clamping was conducted in 94 patients and forty-one (43.6%) patients showed KRAS mutation in tumor tissues. TLG was significantly higher in patients with mutated KRAS compared with in those with wild KRAS ( P = 0.021). CEA was significantly higher in patients with mutated KRAS than those with wild KRAS ( P-value = 0.024). CEA and TLG could predict KRAS mutation showing odds ratio 1.07 and 1.02 in the multivariate logistic analysis ( P-value = 0.024, 0.048). There was no difference of RFS between in patients with high TLG and in those with low TLG. Conclusions: Based on the result that TLG had a predictive role for KRAS mutation and was related with tumor location and CEA value, we suggested that TLG might reflect genomic alteration and other clinical features as well as tumor burden. It could be useful for differentiating different population of colon cancer and further study is clinically warranted.

scholarly journals Positron Emission Tomography for the Response Evaluation following Treatment with Chemotherapy in Patients Affected by Colorectal Liver Metastases: A Selected Review

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Alberto Zaniboni ◽  
Giordano Savelli ◽  
Claudio Pizzocaro ◽  
Pietro Basile ◽  
Valentina Massetti
Keyword(s):  
Liver Metastases ◽  
Fdg Pet ◽  
Therapy Response ◽  
Progression Free Survival ◽  
Free Survival ◽  
Positron Emission ◽  
Response To Chemotherapy ◽  
Pet Ct ◽  
Fdg Pet Ct ◽  
Ct And Mri

The aim of the present paper is to review the scientific literature concerning the usefulness of18F-FDG PET/CT in the evaluation of response to chemotherapy in patients affected by liver metastases from colorectal cancer.Material and Methods. Studies were identified by searching PubMed electronic databases. Both prospective and retrospective studies were included. Information regarding the figure of merit of PET for the evaluation of therapy response was extracted and analyzed.Results. Existing data suggests that18F-FDG PET/CT may have an outstanding role in evaluating the response. The sensitivity of PET in detecting therapy response seems to be greater than conventional imaging (CT and MRI). PET/CT response is strictly related to better overall survival and progression-free survival.Conclusions. PET/CT is more than a promising technique to assess the response to chemotherapy in colorectal and liver metastases. However, to be fully validated, this examination needs further studies by recruiting more patients.

FDG-PET/CT is Predictive of Progression-free Survival in Anal Cancer

2009 ◽  
Vol 75 (3) ◽  
pp. S258-S259
Author(s):  
W.W. Lien ◽  
A.R. Rao ◽  
J.S. Kaptein ◽  
M.A. Tome
Keyword(s):  
Anal Cancer ◽  
Fdg Pet ◽  
Progression Free Survival ◽  
Free Survival ◽  
Pet Ct ◽  
Fdg Pet Ct

scholarly journals Prediction of 5-year Progression-Free Survival in Advanced Nasopharyngeal Carcinoma with Pretreatment PET/CT using Multi-Modality Deep Learning-based Radiomics

2021 ◽  
Author(s):  
Bingxin Gu ◽  
Mingyuan Meng ◽  
Lei Bi ◽  
Jinman Kim ◽  
David Dagan Feng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Image Analysis ◽  
Progression Free Survival ◽  
Ct Images ◽  
Tnm Stage ◽  
Support Vector ◽  
Free Survival ◽  
Prognostic Performance ◽  
Pet Ct ◽  
Testing Error

Abstract Purpose Deep Learning-based Radiomics (DLR) has achieved great success on medical image analysis. In this study, we aimed to explore the capability of our proposed end-to-end multi-modality DLR model using pretreatment PET/CT images to predict 5-year Progression-Free Survival (PFS) in advanced NPC.Methods A total of 170 patients with pathological confirmed advanced NPC (TNM stage III or IVa) were enrolled in this study. A 3D Convolutional Neural Network (CNN), with two branches to process PET and CT separately, was optimized to extract deep features from pretreatment multi-modality PET/CT images and use the derived features to predict the probability of 5-year PFS. Optionally, TNM stage, as a high-level clinical feature, can be integrated into our DLR model to further improve prognostic performance. Results For a comparison between Conventional Radiomic (CR) and DLR, 1456 handcrafted features were extracted, and three top CR methods, Random Forest (RF) + RF (AUC = 0.796 ± 0.009, testing error = 0.267 ± 0.007), RF + Adaptive Boosting (AdaBoost) (AUC = 0.783 ± 0.011, testing error = 0.286 ± 0.009), and L1-Logistic Regression (L1-LOG) + Kernel Support Vector Machines (KSVM) (AUC = 0.769 ± 0.008, testing error = 0.298 ± 0.006), were selected as benchmarks from 54 combinations of 6 feature selection methods and 9 classification methods. Compared to the three CR methods, our multi-modality DLR models using both PET and CT, with or without TNM stage (named PCT or PC model), resulted in the highest prognostic performance (PCT model: AUC = 0.842 ± 0.034, testing error = 0.194 ± 0.029; PC model: AUC = 0.825 ± 0.041, testing error = 0.223 ± 0.035). Furthermore, the multi-modality PCT model outperformed single-modality DLR models using only PET and TNM stage (named PT model: AUC = 0.818 ± 0.029, testing error = 0.218 ± 0.024) or only CT and TNM stage (named CT model: AUC = 0.657 ± 0.055, testing error = 0.375 ± 0.048). Conclusion Our study identified potential radiomics-based prognostic model for survival prediction in advanced NPC, and suggests that DLR could serve as a tool for aiding in cancer management.

scholarly journals Post-transplantation Fluorine-18 Fluorodeoxyglucose Positron Emission Tomography in Patients with Lymphoblastic Lymphoma is an Independent Prognostic Factor with an Impact on Progression-Free Survival but not Overall Survival

2021 ◽  
Vol 20 ◽  
pp. 153303382110564
Author(s):  
Na Dai ◽  
Hang Liu ◽  
Shengming Deng ◽  
Shibiao Sang ◽  
Yiwei Wu
Keyword(s):  
Prognostic Factor ◽  
Fdg Pet ◽  
Progression Free Survival ◽  
Lymphoblastic Lymphoma ◽  
Emission Tomography ◽  
Free Survival ◽  
Positron Emission ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Purpose: In the present study, we mainly aimed to evaluate the prognostic value of 2-deoxy-2-[18F]fluoro-D-glucose ([18F]F-FDG) positron emission tomography (PET)/computed tomography (CT) after allogeneic stem cell transplantation (allo-SCT) in lymphoblastic lymphoma (LBL) patients using Deauville Scores (DS). Materials and Methods: A total of 63 LBL patients who benefited from 18F-FDG PET-CT after allo-SCT in our institution between April 2010 and August 2020 were enrolled in this retrospective study. These above-mentioned patients were divided into two groups based on the Deauville criteria. Diagnostic efficiency of 18F-FDG PET/CT and integrated CT in detecting lymphoma were calculated. Consistencies were evaluated by comparing 18F-FDG PET/CT and integrated CT results through kappa coefficient. Kaplan-Meier method was used in survival analysis, and the log-rank method was adopted in comparisons. Prognostic factor analysis was performed by the Cox regression model. Results: The sensitivity, specificity, positive predictive value, negative predictive value, accuracy of post-SCT 18F-FDG PET-CT were 100%(12/12), 92.2%(47/51), 75.0%(12/16), 100%(47/47) and 93.7%(59/63). The consistency of 18F-FDG PET-CT and integrated CT was moderate(Kappa = .702，P < .001). Positive post-SCT 18F-FDG PET-CT was associated with lower progression-free survival (PFS) but not overall survival (OS) (p = .000 and p = .056, respectively). The 3-year PFS of the PET-positive group and PET-negative group was 18.8% and 70.2%, respectively. Multivariate analysis showed that post-SCT PET-CT findings was an independent prognostic factor for PFS (p = .000; HR, 3.957; 95%CI, 1.839-8.514). Other factors independently affecting PFS were sex (p = .018; HR, 2.588; 95% CI, 1.181 − 5.670) and lactate dehydrogenase (LDH) (p = .005; HR, 3.246; 95% CI, 1.419 − 7.426). However, none of the above-mentioned factors were associated with OS. Conclusions: Collectively, we found that 18F-FDG PET-CT after allo-SCT was a strong indicator for PFS, but not OS, which might provide important evidence for the selection of subsequent treatment regimen for LBL patients. Trial registration number: ChiCTR2100046709.

scholarly journals Prognostic value of the baseline 18F-FDG PET/CT metabolic tumour volume (MTV) and further stratification in low-intermediate (L-I) and high-intermediate (H-I) risk NCCNIPI subgroup by MTV in DLBCL MTV predict prognosis in DLBCL

2020 ◽  
Author(s):  
Peng Zhao ◽  
Tao Yu ◽  
Zheng Pan
Keyword(s):  
Risk Stratification ◽  
Fdg Pet ◽  
Prognostic Value ◽  
B Cell Lymphoma ◽  
Risk Groups ◽  
Metabolic Parameters ◽  
Metabolic Tumour Volume ◽  
P Value ◽  
Pet Ct ◽  
Fdg Pet Ct

Abstract Introduction In the era of rituximab, the NCCNIPI is widely used in clinical practice as a tool for the prognosis and risk stratification of diffuse large B-cell lymphoma (DLBCL). In recent years, FDG PET/CT has also shown unique prognostic value. We try to further confirm the prognostic role of metabolic parameters in the overall and subgroups patients. Methods We retrospectively analysed 87 DLBCL patients who underwent baseline FDG PET/CT and followed the R-CHOP or R-CHOP-like strategy. The clinical parameters and PET-related metabolic parameters were evaluated. Results For all patients, the 2-year PFS rate was 65.5% and the 2-year OS rate was 66.7%. According to Cox multivariate analysis, a high NCCNIPI score (4–8 points) and an MTV greater than 64.1 cm3 (defined by ROC) were independent prognostic factors for PFS and OS. The patients were divided into low, low-intermediate, high-intermediate and high-risk groups by NCCNIPI score. The 2-year PFS rates in each group were 90.9%, 71.3%, 33.2% and 16.7%, and the 2-year OS rates were 100%, 81.6%, 48.4% and 16.7%. In the subsequent subgroup analysis by MTV, it could further stratified low-intermediate and high-intermediate NCCNIPI groups, the P value was 0.068 and 0.069 for PFS, 0.078 and 0.036 for OS. Conclusions MTV, as a tumor metabolic volume parameter, and the NCCNIPI score were independent predictors of prognosis in general DLBCL patients. In the low-intermediate and high-intermediate NCCNIPI subgroup, we further confirm the risk stratification abilities of MTV, which could add the prognostic value of NCCNIPI.

scholarly journals Metabolic Parameters as Predictors for Progression Free and Overall Survival of Patients with Metastatic Colorectal Cancer

2020 ◽  
Vol 26 (4) ◽  
pp. 2683-2691
Author(s):  
Zsuzsanna Nemeth ◽  
Wouter Wijker ◽  
Zsolt Lengyel ◽  
Erika Hitre ◽  
Katalin Borbely
Keyword(s):  
Colorectal Cancer ◽  
Overall Survival ◽  
Metastatic Colorectal Cancer ◽  
Metabolic Activity ◽  
Fdg Pet ◽  
Progression Free Survival ◽  
Metabolic Parameters ◽  
First Line ◽  
Pet Ct ◽  
Fdg Pet Ct

AbstractWe tested the prognostic relevance of metabolic parameters and their relative changes in patients with metastatic colorectal cancer (mCRC) treated with monoclonal antibody and chemotherapy. SUVmax (standardized uptake volume), SAM (standardized added metabolic activity) and TLG (total lesion glycolysis) are assessed with 18F-fluorodeoxyglucosepositron emission tomography and computed tomography (FDG-PET/CT) to evaluate total metabolic activity of malignant processes. Our purpose was to investigate the change of glucose metabolism in relation to PFS (progression free survival) and OS (overall survival). Fifty-three patients with mCRC with at least one measurable liver metastasis were included in this prospective, multi-center, early exploratory study. All patients were treated with first-line chemotherapy and targeted therapy. Metabolic parameters, like SUVmax, SAM, normalized SAM (NSAM) and TLG were assessed by FDG-PET/CT, carried out at baseline (scan-1) and after two therapeutic cycle (scan-2). Our results suggested neither SUVmax nor TLG have such prognostic value as NSAM in liver metastases of colorectal cancer. The parameters after the two cycles of chemotherapy proved to be better predictors of the clinical outcome. NSAM after two cycles of treatment has a statistically significant predictive value on OS, while SAM was predictive to the PFS. The follow up normalized SAM after 2 cycles of first line oncotherapy was demonstrated to be useful as prognostic biomarkers for OS in metastatic colorectal cancer. We should introduce this measurement in metastatic colorectal cancer if there is at least one metastasis in the liver.

Sign in / Sign up

Export Citation Format

Share Document