Dataset Information

Discovery of Pre-Treatment FDG PET/CT-Derived Radiomics-Based Models for Predicting Outcome in Diffuse Large B-Cell Lymphoma.

ABSTRACT: Approximately 30% of patients with diffuse large B-cell lymphoma (DLBCL) will have recurrence. The aim of this study was to develop a radiomic based model derived from baseline PET/CT to predict 2-year event free survival (2-EFS). Patients with DLBCL treated with R-CHOP chemotherapy undergoing pre-treatment PET/CT between January 2008 and January 2018 were included. The dataset was split into training and internal unseen test sets (ratio 80:20). A logistic regression model using metabolic tumour volume (MTV) and six different machine learning classifiers created from clinical and radiomic features derived from the baseline PET/CT were trained and tuned using four-fold cross validation. The model with the highest mean validation receiver operator characteristic (ROC) curve area under the curve (AUC) was tested on the unseen test set. 229 DLBCL patients met the inclusion criteria with 62 (27%) having 2-EFS events. The training cohort had 183 patients with 46 patients in the unseen test cohort. The model with the highest mean validation AUC combined clinical and radiomic features in a ridge regression model with a mean validation AUC of 0.75 ± 0.06 and a test AUC of 0.73. Radiomics based models demonstrate promise in predicting outcomes in DLBCL patients.

SUBMITTER: Frood R

PROVIDER: S-EPMC8997127 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Discovery of Pre-Treatment FDG PET/CT-Derived Radiomics-Based Models for Predicting Outcome in Diffuse Large B-Cell Lymphoma.

Frood Russell R Clark Matthew M Burton Cathy C Tsoumpas Charalampos C Frangi Alejandro F AF Gleeson Fergus F Patel Chirag C Scarsbrook Andrew F AF

Cancers 20220328 7

<h4>Background</h4>Approximately 30% of patients with diffuse large B-cell lymphoma (DLBCL) will have recurrence. The aim of this study was to develop a radiomic based model derived from baseline PET/CT to predict 2-year event free survival (2-EFS).<h4>Methods</h4>Patients with DLBCL treated with R-CHOP chemotherapy undergoing pre-treatment PET/CT between January 2008 and January 2018 were included. The dataset was split into training and internal unseen test sets (ratio 80:20). A logistic regre ...[more]

PMID: 35406482

Similar Datasets

Project description:BackgroundDiffuse large B-cell lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma in adults. Standard treatment includes chemoimmunotherapy with R-CHOP or similar regimens. Despite treatment advancements, many patients with DLBCL experience refractory disease or relapse. While baseline 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) parameters have shown promise in predicting survival, they may not fully capture lesion heterogeneity. This study aimed to assess the prognostic value of baseline 18F-FDG PET radiomics features in comparison with clinical factors and metabolic parameters for assessing 2-year progression-free survival (PFS) and 5-year overall survival (OS) in patients with DLBCL.ResultsA total of 201 patients with DLBCL were enrolled in this study, and 1328 radiomics features were extracted. The radiomics signatures, clinical factors, and metabolic parameters showed significant prognostic value for individualized prognosis prediction in patients with DLBCL. Radiomics signatures showed the lowest Akaike information criterion (AIC) value and highest Harrell's concordance index (C-index) value in comparison with clinical factors and metabolic parameters for both PFS (AIC: 571.688 vs. 596.040 vs. 576.481; C-index: 0.732 vs. 0.658 vs. 0.702, respectively) and OS (AIC: 339.843 vs. 363.671 vs. 358.412; C-index: 0.759 vs. 0.667 vs. 0.659, respectively). Statistically significant differences were observed in the area under the curve (AUC) values between the radiomics signatures and clinical factors for both PFS (AUC: 0.768 vs. 0.681, P = 0.017) and OS (AUC: 0.767 vs. 0.667, P = 0.023). For OS, the AUC of the radiomics signatures were significantly higher than those of metabolic parameters (AUC: 0.767 vs. 0.688, P = 0.007). However, for PFS, no significant difference was observed between the radiomics signatures and metabolic parameters (AUC: 0.768 vs. 0.756, P = 0.654). The combined model and the best-performing individual model (radiomics signatures) alone showed no significant difference for both PFS (AUC: 0.784 vs. 0.768, P = 0.163) or OS (AUC: 0.772 vs. 0.767, P = 0.403).ConclusionsRadiomics signatures derived from PET images showed the high predictive power for progression in patients with DLBCL. The combination of radiomics signatures, clinical factors, and metabolic parameters may not significantly improve predictive value beyond that of radiomics signatures alone.

Project description:ObjectivesRelapse occurs in ~20% of patients with classical Hodgkin lymphoma (cHL) despite treatment adaption based on 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography response. The objective was to evaluate pre-treatment FDG PET/CT-derived machine learning (ML) models for predicting outcome in patients with cHL.MethodsAll cHL patients undergoing pre-treatment PET/CT at our institution between 2008 and 2018 were retrospectively identified. A 1.5 × mean liver standardised uptake value (SUV) and a fixed 4.0 SUV threshold were used to segment PET/CT data. Feature extraction was performed using PyRadiomics with ComBat harmonisation. Training (80%) and test (20%) cohorts stratified around 2-year event-free survival (EFS), age, sex, ethnicity and disease stage were defined. Seven ML models were trained and hyperparameters tuned using stratified 5-fold cross-validation. Area under the curve (AUC) from receiver operator characteristic analysis was used to assess performance.ResultsA total of 289 patients (153 males), median age 36 (range 16-88 years), were included. There was no significant difference between training (n = 231) and test cohorts (n = 58) (p value > 0.05). A ridge regression model using a 1.5 × mean liver SUV segmentation had the highest performance, with mean training, validation and test AUCs of 0.82 ± 0.002, 0.79 ± 0.01 and 0.81 ± 0.12. However, there was no significant difference between a logistic model derived from metabolic tumour volume and clinical features or the highest performing radiomic model.ConclusionsOutcome prediction using pre-treatment FDG PET/CT-derived ML models is feasible in cHL patients. Further work is needed to determine optimum predictive thresholds for clinical use.Key points• A fixed threshold segmentation method led to more robust radiomic features. • A radiomic-based model for predicting 2-year event-free survival in classical Hodgkin lymphoma patients is feasible. • A predictive model based on ridge regression was the best performing model on our dataset.

Project description:PurposeThis study aimed to develop a novel analytic approach based on 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography/computed tomography ([18F]FDG PET/CT) radiomic signature (RS) and International Prognostic Index (IPI) to predict the progression-free survival (PFS) and overall survival (OS) of patients with diffuse large B-cell lymphoma (DLBCL).MethodsWe retrospectively enrolled 152 DLBCL patients and divided them into a training cohort (n = 100) and a validation cohort (n = 52). A total of 1245 radiomic features were extracted from the total metabolic tumor volume (TMTV) and the metabolic bulk volume (MBV) of pre-treatment PET/CT images. The least absolute shrinkage and selection operator (LASSO) algorithm was applied to develop the RS. Cox regression analysis was used to construct hybrid nomograms based on different RS and clinical variables. The performances of hybrid nomograms were evaluated using the time-dependent receiver operator characteristic (ROC) curve and the Hosmer-Lemeshow test. The clinical utilities of prediction nomograms were determined via decision curve analysis. The predictive efficiency of different RS, clinical variables, and hybrid nomograms was compared.ResultsThe RS and IPI were identified as independent predictors of PFS and OS, and were selected to construct hybrid nomograms. Both TMTV- and MBV-based hybrid nomograms had significantly higher values of area under the curve (AUC) than IPI in training and validation cohorts (all P < 0.05), while no significant difference was found between TMTV- and MBV-based hybrid nomograms (P > 0.05). The Hosmer-Lemeshow test showed that both TMTV- and MBV-based hybrid nomograms calibrated well in the training and validation cohorts (all P > 0.05). Decision curve analysis indicated that hybrid nomograms had higher net benefits than IPI.ConclusionThe hybrid nomograms combining RS with IPI could significantly improve survival prediction in DLBCL. Radiomic analysis on MBV may serve as a potential approach for prognosis assessment in DLBCL.Trial registrationNCT04317313. Registered March 16, 2020. Public site: https://clinicaltrials.gov/ct2/show/NCT04317313.

Project description:BackgroundDiffuse large B-cell lymphoma (DLBCL) is a highly aggressive lymphoma. Rituximab-based conventional chemotherapy still leads to drug resistance or relapse in 30-40% of patients. Therefore, early identification of high-risk patients and accurate assessment of prognosis are very important for clinical decision-making. The aim of this study is to investigate the value of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) of tumor metabolic, clinical and biological parameters in the prognostic risk stratification of DLBCL before treatment.MethodsWe retrospectively collected clinical data on 63 patients with newly diagnosed DLBCL admitted to Shanxi Bethune Hospital during the period from November 2016 to April 2020 who underwent 18F-FDG PET/CT prior to treatment in a cohort study. Metabolic, clinical, and biological parameters were analyzed by Cox regression. Kaplan-Meier curves of patient survival were compared by the log-rank test.ResultsThe median follow-up was 21 months. The 2-year progression-free survival (PFS) was 47.62%, and the overall survival (OS) was 53.97%. The subtype, double expression, Ann Abor stage, NCCN-IPI score, Ki-67, maximum standardized uptake value (SUVmax), bulk volume glycolysis (BVG), total lesion glycolysis (TLG), total metabolic tumor volume (TMTV) were the influencing factors for PFS and OS (P<0.050) in univariate analysis. BVG (PFS: HR =6.62, P<0.001; OS: HR =3.53, P=0.029), TLG (PFS: HR =8.56, P<0.001; OS: HR =5.20, P=0.004), TMTV (PFS: HR =12.02, P=0.001; OS: HR =5.05, P=0.033) and Ki-67 were found to be independent prognostic risk stratification parameters affecting PFS and OS by multivariate regression analysis. The 2-year PFS and OS rates for patients with high BVG (≥288.00 cm3), TLG (≥1,854.00 cm3), TMTV (≥103.00 cm3), and Ki-67 (≥85%) were 20% and 28.57%, 9.68% and 22.58%, 20.51%, and 30.77%, and 25% and 33.33%, respectively; and the 2-year PFS and OS rates for patients with low BVG (<288.00 cm3), TLG (<1,854.00 cm3), TMTV (<103.00 cm3), and Ki-67 (<85%) patients were 82.14% and 85.71%, 84.37% and 84.37%, 91.67% and 91.67%, and 61.54% and 66.67%, respectively. Patients with high BVG, TLG, TMTV, and Ki-67 had a worse 2-year PFS as well as OS rate (Ki-67: P=0.0018/P=0.0025; P<0.0001 for the rest of the groups).ConclusionsOur findings suggest that BVG, TLG, TMTV, and Ki-67 are independent prognostic indicators for survival in patients with pre-treatment DLBCL, especially BVG, which is a novel prognostic indicator that has to be validated in future research.

Dataset Information

Discovery of Pre-Treatment FDG PET/CT-Derived Radiomics-Based Models for Predicting Outcome in Diffuse Large B-Cell Lymphoma.

Publications

Discovery of Pre-Treatment FDG PET/CT-Derived Radiomics-Based Models for Predicting Outcome in Diffuse Large B-Cell Lymphoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets