Dataset Information

Automated quantification of baseline imaging PET metrics on FDG PET/CT images of pediatric Hodgkin lymphoma patients

ABSTRACT:

Purpose

For pediatric lymphoma, quantitative FDG PET/CT imaging features such as metabolic tumor volume (MTV) are important for prognosis and risk stratification strategies. However, feature extraction is difficult and time-consuming in cases of high disease burden. The purpose of this study was to fully automate the measurement of PET imaging features in PET/CT images of pediatric lymphoma.

Methods

18F-FDG PET/CT baseline images of 100 pediatric Hodgkin lymphoma patients were retrospectively analyzed. Two nuclear medicine physicians identified and segmented FDG avid disease using PET thresholding methods. Both PET and CT images were used as inputs to a three-dimensional patch-based, multi-resolution pathway convolutional neural network architecture, DeepMedic. The model was trained to replicate physician segmentations using an ensemble of three networks trained with 5-fold cross-validation. The maximum SUV (SUVmax), MTV, total lesion glycolysis (TLG), surface-area-to-volume ratio (SA/MTV), and a measure of disease spread (Dmaxpatient) were extracted from the model output. Pearson’s correlation coefficient and relative percent differences were calculated between automated and physician-extracted features.

Results

Median Dice similarity coefficient of patient contours between automated and physician contours was 0.86 (IQR 0.78–0.91). Automated SUVmax values matched exactly the physician determined values in 81/100 cases, with Pearson’s correlation coefficient (R) of 0.95. Automated MTV was strongly correlated with physician MTV (R = 0.88), though it was slightly underestimated with a median (IQR) relative difference of ? 4.3% (? 10.0–5.7%). Agreement of TLG was excellent (R = 0.94), with median (IQR) relative difference of ? 0.4% (? 5.2–7.0%). Median relative percent differences were 6.8% (R = 0.91; IQR 1.6–4.3%) for SA/MTV, and 4.5% (R = 0.51; IQR ? 7.5–40.9%) for Dmaxpatient, which was the most difficult feature to quantify automatically.

Conclusions

An automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40658-020-00346-3.

SUBMITTER: Weisman A

PROVIDER: S-EPMC7736382 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Purpose:In the present study, we aimed to investigate whether the metabolic parameters on baseline 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) could be used to predict prognosis in peripheral T-cell lymphomas (PTCL). Methods:A total of 51 nodal PTCL patients who underwent baseline 18F-FDG PET/CT were retrospectively evaluated in the present study. Total metabolic tumor volume (TMTV), total lesion glycolysis (TLG), and maximum standardized uptake value (SUVmax) were also assessed. Besides, the National Comprehensive Cancer Network International Prognostic Index (NCCN-IPI) was also included. Log-rank test and Cox regression analysis were used to evaluate progression-free survival (PFS) and overall survival (OS). Results:The median follow-up was 18 months. Patients with low TLG, TMTV, and SUVmax levels had a significantly better clinical outcome than those with high TLG, TMTV, and SUVmax levels. The 2-year PFS rates of the high- and low-TMTV groups were 34.62% and 80%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (p < 0.001), whereas the corresponding 2-year OS rates were 46.15% and 84.00%, respectively (n = 10), intermediate-risk group with TMTV > 62.405 or NCCN-IPI score of 4-8 (2-year PFS and OS were 52.4% and 66.7%, respectively, n = 10), intermediate-risk group with TMTV > 62.405 or NCCN-IPI score of 4-8 (2-year PFS and OS were 52.4% and 66.7%, respectively, n = 10), intermediate-risk group with TMTV > 62.405 or NCCN-IPI score of 4-8 (2-year PFS and OS were 52.4% and 66.7%, respectively. Conclusions:Baseline TMTV and TLG were independent predictors of PFS and OS in PTCL patients, and SUVmax and NCCN-IPI scores were also independent predictors of OS. Moreover, the combination of TMTV and NCCN-IPI scores improved patient risk-stratification at the initial stage and might contribute to the adjustment of the therapeutic regime. This trial is registered with ChiCTR1900025526.

Project description:At present, 18F-fluorodesoxyglucose (18FDG) positron emission tomography (PET)/computed tomography (CT) cannot be used to omit a bone marrow biopsy (BMB) among initial staging procedures in follicular lymphoma (FL). The additional diagnostic value of skeletal textural features on baseline 18FDG-PET/CT in diffuse large B-cell lymphoma (DLBCL) patients has given promising results. The aim of this study is to evaluate the value of 18FDG-PET/CT radiomics for the diagnosis of bone marrow involvement (BMI) in FL patients. This retrospective bicentric study enrolled newly diagnosed FL patients addressed for baseline 18FDG PET/CT. For visual assessment, examinations were considered positive in cases of obvious bone focal uptakes. For textural analysis, the skeleton volumes of interest (VOIs) were automatically extracted from segmented CT images and analysed using LifeX software. BMB and visual assessment were taken as the gold standard: BMB -/PET - patients were considered as bone-NEGATIVE patients, whereas BMB +/PET -, BMB -/PET + and BMB +/PET + patients were considered bone-POSITIVE patients. A LASSO regression algorithm was used to select features of interest and to build a prediction model. Sixty-six consecutive patients were included: 36 bone-NEGATIVE (54.5%) and 30 bone-POSITIVE (45.5%). The LASSO regression found variance_GLCM, correlation_GLCM, joint entropy_GLCM and busyness_NGLDM to have nonzero regression coefficients. Based on ROC analysis, a cut-off equal to - 0.190 was found to be optimal for the diagnosis of BMI using PET pred.score. The corresponding sensitivity, specificity, PPV and NPV values were equal to 70.0%, 83.3%, 77.8% and 76.9%, respectively. When comparing the ROC AUCs with using BMB alone, visual PET assessment or PET pred.score, a significant difference was found between BMB versus visual PET assessments (p = 0.010) but not between BMB and PET pred.score assessments (p = 0.097). Skeleton texture analysis is worth exploring to improve the performance of 18FDG-PET/CT for the diagnosis of BMI at baseline in FL patients.

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: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.