Automated Segmentation of Baseline Metabolic Total Tumor Burden in Diffuse Large B-Cell Lymphoma: Which Method Is Most Successful? A Study on Behalf of the PETRA Consortium

Comparing lesion and feature selections to predict progression in newly diagnosed DLBCL patients with FDG PET/CT radiomics features

PURPOSE

Biomarkers that can accurately predict outcome in DLBCL patients are urgently needed. Radiomics features extracted from baseline [¹⁸F]-FDG PET/CT scans have shown promising results. This study aims to investigate which lesion- and feature-selection approaches/methods resulted in the best prediction of progression after 2 years.

METHODS

A total of 296 patients were included. 485 radiomics features (n = 5 conventional PET, n = 22 morphology, n = 50 intensity, n = 408 texture) were extracted for all individual lesions and at patient level, where all lesions were aggregated into one VOI. 18 features quantifying dissemination were extracted at patient level. Several lesion selection approaches were tested (largest or hottest lesion, patient level [all with/without dissemination], maximum or median of all lesions) and compared to the predictive value of our previously published model. Several data reduction methods were applied (principal component analysis, recursive feature elimination (RFE), factor analysis, and univariate selection). The predictive value of all models was tested using a fivefold cross-validation approach with 50 repeats with and without oversampling, yielding the mean cross-validated AUC (CV-AUC). Additionally, the relative importance of individual radiomics features was determined.

RESULTS

Models with conventional PET and dissemination features showed the highest predictive value (CV-AUC: 0.72-0.75). Dissemination features had the highest relative importance in these models. No lesion selection approach showed significantly higher predictive value compared to our previous model. Oversampling combined with RFE resulted in highest CV-AUCs.

CONCLUSION

Regardless of the applied lesion selection or feature selection approach and feature reduction methods, patient level conventional PET features and dissemination features have the highest predictive value. Trial registration number and date: EudraCT: 2006-005174-42, 01-08-2008.

Combatting the effect of image reconstruction settings on lymphoma [18F]FDG PET metabolic tumor volume assessment using various segmentation methods

Background

[¹⁸F]FDG PET-based metabolic tumor volume (MTV) is a promising prognostic marker for lymphoma patients. The aim of this study is to assess the sensitivity of several MTV segmentation methods to variations in image reconstruction methods and the ability of ComBat to improve MTV reproducibility.

Methods

Fifty-six lesions were segmented from baseline [¹⁸F]FDG PET scans of 19 lymphoma patients. For each scan, EARL1 and EARL2 standards and locally clinically preferred reconstruction protocols were applied. Lesions were delineated using 9 semiautomatic segmentation methods: fixed threshold based on standardized uptake value (SUV), (SUV = 4, SUV = 2.5), relative threshold (41% of SUVmax [41M], 50% of SUVpeak [A50P]), majority vote-based methods that select voxels detected by at least 2 (MV2) and 3 (MV3) out of the latter 4 methods, Nestle thresholding, and methods that identify the optimal method based on SUVmax (L2A, L2B). MTVs from EARL2 and locally clinically preferred reconstructions were compared to those from EARL1. Finally, different versions of ComBat were explored to harmonize the data.

Results

MTVs from the SUV4.0 method were least sensitive to the use of different reconstructions (MTV ratio: median = 1.01, interquartile range = [0.96–1.10]). After ComBat harmonization, an improved agreement of MTVs among different reconstructions was found for most segmentation methods. The regular implementation of ComBat (‘Regular ComBat’) using non-transformed distributions resulted in less accurate and precise MTV alignments than a version using log-transformed datasets (‘Log-transformed ComBat’).

Conclusion

MTV depends on both segmentation method and reconstruction methods. ComBat reduces reconstruction dependent MTV variability, especially when log-transformation is used to account for the non-normal distribution of MTVs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13550-022-00916-9.

Proposed New Dynamic Prognostic Index for Diffuse Large B-Cell Lymphoma: International Metabolic Prognostic Index

PURPOSE

Baseline metabolic tumor volume (MTV) is a promising biomarker in diffuse large B-cell lymphoma (DLBCL). Our aims were to determine the best statistical relationship between MTV and survival and to compare MTV with the International Prognostic Index (IPI) and its individual components to derive the best prognostic model.

METHODS

PET scans and clinical data were included from five published studies in newly diagnosed diffuse large B-cell lymphoma. Transformations of MTV were compared with the primary end points of 3-year progression-free survival (PFS) and overall survival (OS) to derive the best relationship for further analyses. MTV was compared with IPI categories and individual components to derive the best model. Patients were grouped into three groups for survival analysis using Kaplan-Meier analysis; 10% at highest risk, 30% intermediate risk, and 60% lowest risk, corresponding with expected clinical outcome. Validation of the best model was performed using four studies as a test set and the fifth study for validation and repeated five times.

RESULTS

The best relationship for MTV and survival was a linear spline model with one knot located at the median MTV value of 307.9 cm3. MTV was a better predictor than IPI for PFS and OS. The best model combined MTV with age as continuous variables and individual stage as I-IV. The MTV-age-stage model performed better than IPI and was also better at defining a high-risk group (3-year PFS 46.3% v 58.0% and 3-year OS 51.5% v 66.4% for the new model and IPI, respectively). A regression formula was derived to estimate individual patient survival probabilities.

CONCLUSION

A new prognostic index is proposed using MTV, age, and stage, which outperforms IPI and enables individualized estimates of patient outcome.

Proposed New Dynamic Prognostic Index for Diffuse Large B-Cell Lymphoma: International Metabolic Prognostic Index

PURPOSE

Baseline metabolic tumor volume (MTV) is a promising biomarker in diffuse large B-cell lymphoma (DLBCL). Our aims were to determine the best statistical relationship between MTV and survival and to compare MTV with the International Prognostic Index (IPI) and its individual components to derive the best prognostic model.

METHODS

PET scans and clinical data were included from five published studies in newly diagnosed diffuse large B-cell lymphoma. Transformations of MTV were compared with the primary end points of 3-year progression-free survival (PFS) and overall survival (OS) to derive the best relationship for further analyses. MTV was compared with IPI categories and individual components to derive the best model. Patients were grouped into three groups for survival analysis using Kaplan-Meier analysis; 10% at highest risk, 30% intermediate risk, and 60% lowest risk, corresponding with expected clinical outcome. Validation of the best model was performed using four studies as a test set and the fifth study for validation and repeated five times.

RESULTS

The best relationship for MTV and survival was a linear spline model with one knot located at the median MTV value of 307.9 cm³. MTV was a better predictor than IPI for PFS and OS. The best model combined MTV with age as continuous variables and individual stage as I-IV. The MTV-age-stage model performed better than IPI and was also better at defining a high-risk group (3-year PFS 46.3% v 58.0% and 3-year OS 51.5% v 66.4% for the new model and IPI, respectively). A regression formula was derived to estimate individual patient survival probabilities.

CONCLUSION

A new prognostic index is proposed using MTV, age, and stage, which outperforms IPI and enables individualized estimates of patient outcome.

SAKK 35/15: a phase 1 trial of obinutuzumab in combination with venetoclax in patients with previously untreated follicular lymphoma

This phase 1 study evaluated safety, tolerability, and preliminary efficacy of obinutuzumab in combination with venetoclax in patients with previously untreated grade 1-3a follicular lymphoma in need of systemic therapy. Two DLs of venetoclax were evaluated with an expansion cohort at the recommended phase 2 dose. Twenty-five patients were enrolled. The recommended phase 2 dose was venetoclax 800 mg OD continuously for 6 cycles starting on day 2 of cycle 1, with obinutuzumab 1000 mg on days 1, 8, and 15 of cycle 1 and on day 1 of cycles 2 to 6, followed by obinutuzumab maintenance every 2 months for 2 years. Only 1 patient had a DLT consisting of grade 4 thrombocytopenia after the first obinutuzumab infusion. Neutropenia was the most common adverse event of grade ≥3 at least possibly attributed to study treatment. Twenty-four patients were evaluable for response after cycle 6 by computed tomography (CT) and 19 by positron emission tomography/CT (PET/CT): overall and complete response rates were 87.5% (95% CI, 67.6% to 97.3%) and 25% (95% CI, 9.8% to 46.7%) in the CT-evaluated patients and 84.2% (95% CI, 60.4% to 96.6%) and 68.4% (95% CI, 43.4% to 87.4%), respectively, in the PET/CT-evaluated patients. One-year progression-free survival was 77.8% (95% CI, 54.6% to 90.1%) and 79% (95% CI, 47.9% to 92.7%) for CT and PET/CT-evaluable patients, respectively, whereas progression-free survival at 30 months was 73.2% (95% CI, 49.8%, 87.0%) as assessed by CT and 79.0% (95% CI, 47.9%, 92.7%) by PET/CT. Despite the activity observed, our results do not support further development of the combination in this patient population. This trial was registered at www.clinicaltrials.gov as #NCT02877550.

18F-FDG PET Improves Baseline Clinical Predictors of Response in Diffuse Large B-Cell Lymphoma: The HOVON-84 Study

We aimed to determine the added value of baseline metabolic tumor volume (MTV) and interim PET (I-PET) to the age-adjusted international prognostic index (aaIPI) to predict 2-y progression-free survival (PFS) in diffuse large B-cell lymphoma. Secondary objectives were to investigate optimal I-PET response criteria (using Deauville score [DS] or quantitative change in SUV_max [ΔSUV_max] between baseline and I-PET4 [observational I-PET scans after 4 cycles of rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone administered in 2-wk intervals with intensified rituximab in the first 4 cycles [R(R)-CHOP14]). Methods: I-PET4 scans in the HOVON-84 (Hemato-Oncologie voor Volwassenen Nederland [Haemato Oncology Foundation for Adults in the Netherlands]) randomized clinical trial (EudraCT 2006-005174-42) were centrally reviewed using DS (cutoff, 4-5). Additionally, ΔSUV_max (prespecified cutoff, 70%) and baseline MTV were measured. Multivariable hazard ratio (HR), positive predictive value (PPV), and negative predictive value (NPV) were obtained for 2-y PFS. Results: In total, 513 I-PET4 scans were reviewed according to DS, and ΔSUV_max and baseline MTV were available for 367 and 296 patients. The NPV of I-PET ranged between 82% and 86% for all PET response criteria. Univariate HR and PPV were better for ΔSUV_max (4.8% and 53%, respectively) than for DS (3.1% and 38%, respectively). aaIPI and ΔSUV_max independently predicted 2-y PFS (HR, 3.2 and 5.0, respectively); adding MTV brought about a slight improvement. Low or low-intermediate aaIPI combined with a ΔSUV_max of more than 70% (37% of patients) yielded an NPV of 93%, and the combination of high-intermediate or high aaIPI and a ΔSUV_max of 70% or less yielded a PPV of 65%. Conclusion: In this study on diffuse large B-cell lymphoma, I-PET after 4 cycles of R(R)-CHOP14 added predictive value to aaIPI for 2-y PFS, and both were independent response biomarkers in a multivariable Cox model. We externally validated that ΔSUV_max outperformed DS in 2-y PFS prediction.

Risk stratification for relapsed/refractory classical Hodgkin lymphoma integrating pretransplant Deauville score and residual metabolic tumor volume

Pretransplant Deauville score (DS) is an imaging biomarker used for risk stratification in relapsed/refractory classical Hodgkin lymphoma (cHL). However, the prognostic value of residual metabolic tumor volume (rMTV) in patients with DS 4-5 has been less well characterized. We retrospectively assessed 106 patients with relapsed/refractory cHL who underwent autologous stem cell transplantation. Pretransplant DS was determined as 1-3 (59%) and 4-5 (41%), with a markedly inferior event-free survival (EFS) in patients with DS 4-5 (hazard ratio [HR], 3.14; p = .002). High rMTV_41% (rMTV_high , ≥4.4 cm³ ) predicted significantly poorer EFS in patients with DS 4-5 (HR, 3.70; p = .014). In a multivariable analysis, we identified two independent factors predicting treatment failure: pretransplant DS combined with rMTV_41% and disease status (primary refractory vs. relapsed). These two factors allow to stratify patients into three groups with divergent 2-year EFS: 89% for low-risk (51%; relapsed disease and either pretransplant DS 1-3 or DS 4-5/rMTV_low ; HR 1), 65% for intermediate-risk (28%; refractory disease and either DS 1-3 or DS 4-5/rMTV_low ; HR 3.26), and 45% for high-risk (21%; DS 4-5/rMTV_high irrespective of disease status; HR 7.61) groups. Pretransplant DS/rMTV_41% combination and disease status predict the risk of post-transplant treatment failure and will guide risk-stratified approaches in relapsed/refractory cHL.

Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake

Introduction

The automatic classification of lymphoma lesions in PET is a main topic of ongoing research. An automatic algorithm would enable the swift evaluation of PET parameters, like texture and heterogeneity markers, concerning their prognostic value for patients outcome in large datasets. Moreover, the determination of the metabolic tumor volume would be facilitated. The aim of our study was the development and evaluation of an automatic algorithm for segmentation and classification of lymphoma lesions in PET.

Methods

Pre-treatment PET scans from 60 Hodgkin lymphoma patients from the EuroNet-PHL-C1 trial were evaluated. A watershed algorithm was used for segmentation. For standardization of the scan length, an automatic cropping algorithm was developed. All segmented volumes were manually classified into one of 14 categories. The random forest method and a nested cross-validation was used for automatic classification and evaluation.

Results

Overall, 853 volumes were segmented and classified. 203/246 tumor lesions and 554/607 non-tumor volumes were classified correctly by the automatic algorithm, corresponding to a sensitivity, a specificity, a positive and a negative predictive value of 83%, 91%, 79% and 93%. In 44/60 (73%) patients, all tumor lesions were correctly classified. In ten out of the 16 patients with misclassified tumor lesions, only one false-negative tumor lesion occurred. The automatic classification of focal gastrointestinal uptake, brown fat tissue and composed volumes consisting of more than one tissue was challenging.

Conclusion

Our algorithm, trained on a small number of patients and on PET information only, showed a good performance and is suitable for automatic lymphoma classification.

A comparison of FDG PET/MR and PET/CT for staging, response assessment, and prognostic imaging biomarkers in lymphoma

The aim of the current study was to investigate the diagnostic performance of FDG PET/MR compared to PET/CT in a patient cohort including Hodgkins lymphoma, diffuse large B-cell lymphoma, and high-grade B-cell lymphoma at baseline and response assessment. Sixty-one patients were examined with FDG PET/CT directly followed by PET/MR. Images were read by two pairs of nuclear medicine physicians and radiologists. Concordance for lymphoma involvement between PET/MR and the reference standard PET/CT was assessed at baseline and response assessment. Correlation of prognostic biomarkers Deauville score, criteria of response, SUVmax, SUVpeak, and MTV was performed between PET/MR and PET/CT. Baseline FDG PET/MR showed a sensitivity of 92.5% and a specificity 97.9% compared to the reference standard PET/CT (κ 0.91) for nodal sites. For extranodal sites, a sensitivity of 80.4% and a specificity of 99.5% were found (κ 0.84). Concordance in Ann Arbor was found in 57 of 61 patients (κ 0.92). Discrepancies were due to misclassification of region and not lesion detection. In response assessment, a sensitivity of 100% and a specificity 99.9% for all sites combined were found (κ 0.92). There was a perfect agreement on Deauville scores 4 and 5 and criteria of response between the two modalities. Intraclass correlation coefficient (ICC) for SUVmax, SUVpeak, and MTV values showed excellent reliability (ICC > 0.9). FDG PET/MR is a reliable alternative to PET/CT in this patient population, both in terms of lesion detection at baseline staging and response assessment, and for quantitative prognostic imaging biomarkers.

Deep Learning Approach to Automatize TMTV Calculations Regardless of Segmentation Methodology for Major FDG-Avid Lymphomas

The total metabolic tumor volume (TMTV) is a new prognostic factor in lymphomas that could benefit from automation with deep learning convolutional neural networks (CNN). Manual TMTV segmentations of 1218 baseline 18FDG-PET/CT have been used for training. A 3D V-NET model has been trained to generate segmentations with soft dice loss. Ground truth segmentation has been generated using a combination of different thresholds (TMTVprob), applied to the manual region of interest (Otsu, relative 41% and SUV 2.5 and 4 cutoffs). In total, 407 and 405 PET/CT were used for test and validation datasets, respectively. The training was completed in 93 h. In comparison with the TMTVprob, mean dice reached 0.84 in the training set, 0.84 in the validation set and 0.76 in the test set. The median dice scores for each TMTV methodology were 0.77, 0.70 and 0.90 for 41%, 2.5 and 4 cutoff, respectively. Differences in the median TMTV between manual and predicted TMTV were 32, 147 and 5 mL. Spearman’s correlations between manual and predicted TMTV were 0.92, 0.95 and 0.98. This generic deep learning model to compute TMTV in lymphomas can drastically reduce computation time of TMTV.

Pre-treatment total metabolic tumour volumes in lymphoma: Does quantity matter?

Positron emission tomography/computed tomography (PET/CT) is used for the staging of lymphomas. Clinical information, such as Ann Arbor stage and number of involved sites, is derived from baseline staging and correlates with tumour volume. With modern imaging software, exact measures of total metabolic tumour volumes (tMTV) can be determined, in a semi- or fully-automated manner. Several technical factors, such as tumour segmentation and PET/CT technology influence tMTV and there is no consensus on a standardized uptake value (SUV) thresholding method, or how to include the volumes in the bone marrow and spleen. In diffuse large B-cell lymphoma, follicular lymphoma, peripheral T-cell lymphoma, and Hodgkin lymphoma, tMTV has been shown to predict progression-free survival and/or overall survival, after adjustments for clinical risk scores. However, most studies have used receiver operating curves to determine the optimal cut-off for tMTV and many studies did not include a training-validation approach, which led to the risk of overestimation of the independent prognostic value of tMTV. The identified cut-off values are heterogeneous, even when the same SUV thresholding method is used. Future studies should focus on testing tMTV in homogeneously-treated cohorts and seek to validate identified cut-off values externally so that a prognostic value can be documented, over and above currently used clinical surrogates for tumour volume.

A PET in a time of need: toward early PET-adapted therapy in DLBCL in first relapse

Salvage chemotherapy and autologous stem cell transplant remain a standard of care in the management of diffuse large B cell lymphoma (DLBCL) at first relapse. However, this paradigm is increasingly being challenged by novel immunotherapies, such as chimeric antigen receptor T-cells (CART-cells). Traditional positron emission tomography-based (PET) prognostication takes place after salvage and before autologous stem cell transplant (ASCT), and while useful, for many patients this information comes too late and at the expense of unnecessary toxicity. In this edition of Leukemia & Lymphoma, two groups present their findings on the use of early quantitative PET markers and the correlation with outcomes in patients embarking on second line salvage chemotherapy. These approaches have the potential to better identify patients who are destined for treatment failure and help guide appropriate sequencing of alternative therapies or the development of PET-adapted clinical trials.

Current Role of Functional Imaging in the Management of Lymphoma

PURPOSE OF REVIEW

Functional imaging with 18FDG-PET-CT has transformed the staging and response assessment of patients with Hodgkin (HL) and non-Hodgkin lymphoma (NHL). Herein, we review the current role and future directions for functional imaging in the management of patients with lymphoma.

RECENT FINDINGS

Because of its increased sensitivity, PET-CT is the preferred modality for staging of FDG-avid lymphomas. It appears to have a role for interim assessment in patients with HL with adaptive strategies that reduce toxicity in lower risk patients and increase efficacy in those at high risk. Such a role has yet to be demonstrated in other histologies. FDG-PET-CT is also the gold standard for response assessment posttreatment. Newer uses include assessment of total metabolic tumor volume and radiomics in pretreatment prognosis. Whereas PET-CT is more sensitive than other current modalities for staging and response assessment, the future of PET-CT will be in conjunction with other modalities, notably assessment of minimal residual disease and microenvironmental markers to develop risk adaptive strategies to improve the outcome of patients with lymphoma.

Interobserver Agreement on Automated Metabolic Tumor Volume Measurements of Deauville Score 4 and 5 Lesions at Interim 18F-FDG PET in Diffuse Large B-Cell Lymphoma

Metabolic tumor volume (MTV) on interim PET (I-PET) is a potential prognostic biomarker for diffuse large B-cell lymphoma (DLBCL). Implementation of MTV on I-PET requires a consensus on which semiautomated segmentation method delineates lesions most successfully with least user interaction. Methods used for baseline PET are not necessarily optimal for I-PET because of lower lesional SUVs at I-PET. Therefore, we aimed to evaluate which method provides the best delineation quality for Deauville score (DS) 4-5 DLBCL lesions on I-PET at the best interobserver agreement on delineation quality and, second, to assess the effect of lesional SUVmax on delineation quality and performance agreement. Methods: DS 4-5 lesions from 45 I-PET scans were delineated using 6 semiautomated methods: a fixed SUV threshold of 2.5 g/cm3, a fixed SUV threshold of 4.0 g/cm3, an adaptive threshold corrected for source-to-local background activity contrast at 50% of the SUVpeak, 41% of SUVmax per lesion, a majority vote including voxels detected by at least 2 methods, and a majority vote including voxels detected by at least 3 methods (MV3). Delineation quality per MTV was rated by 3 independent observers as acceptable or nonacceptable. For each method, observer scores on delineation quality, specific agreement, and MTV were assessed for all lesions and per category of lesional SUVmax (<5, 5-10, >10). Results: In 60 DS 4-5 lesions on I-PET, MV3 performed best, with acceptable delineation in 90% of lesions and a positive agreement of 93%. Delineation quality scores and agreement per method strongly depended on lesional SUV: the best delineation quality scores were obtained using MV3 in lesions with an SUVmax of less than 10 and using SUV4.0 in more 18F-FDG-avid lesions. Consequently, overall delineation quality and positive agreement improved by applying the most preferred method per SUV category instead of using MV3 as the single best method. The MV3- and SUV4.0-derived MTVs of lesions with an SUVmax of more than 10 were comparable after exclusion of visually failed MV3 contouring. For lesions with an SUVmax of less than 10, MTVs using different methods correlated poorly. Conclusion: On I-PET, MV3 performed best and provided the highest interobserver agreement regarding acceptable delineations of DS 4-5 DLBCL lesions. However, delineation-method preference strongly depended on lesional SUV. Therefore, we suggest exploration of an approach that identifies the optimal delineation method per lesion as a function of tumor 18F-FDG uptake characteristics, that is, SUVmax.

Aberrant patterns of PET response during treatment for DLBCL patients with MYC gene rearrangements

Purpose

MYC gene rearrangements in diffuse large B-cell lymphoma (DLBCL) patients are associated with poor prognosis. Our aim was to compare patterns of 2[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography computed tomography (PET/CT) response in MYC + and MYC- DLBCL patients.

Methods

Interim PET/CT (I-PET) and end of treatment PET/CT (EoT-PET) scans of 81 MYC + and 129 MYC- DLBCL patients from 2 HOVON trials were reviewed using the Deauville 5-point scale (DS). DS1-3 was regarded as negative and DS4-5 as positive. Standardized uptake values (SUV) and metabolic tumor volume (MTV) were quantified at baseline, I-PET, and EoT-PET. Negative (NPV) and positive predictive values (PPV) were calculated using 2-year overall survival.

Results

MYC + DLBCL patients had significantly more positive EoT-PET scans than MYC- patients (32.5 vs 15.7%, p = 0.004). I-PET positivity rates were comparable (28.8 vs 23.8%). In MYC + patients 23.2% of the I-PET negative patients converted to positive at EoT-PET, vs only 2% for the MYC- patients (p = 0.002). Nine (34.6%) MYC + DLBCL showed initially uninvolved localizations at EoT-PET, compared to one (5.3%) MYC- patient. A total of 80.8% of EoT-PET positive MYC + patients showed both increased lesional SUV and MTV compared to I-PET. In MYC- patients, 31.6% showed increased SUV and 42.1% showed increased MTV. NPV of I-PET and EoT-PET was high for both MYC subgroups (81.8–94.1%). PPV was highest at EoT-PET for MYC + patients (61.5%).

Conclusion

MYC + DLBCL patients demonstrate aberrant PET response patterns compared to MYC- patients with more frequent progression during treatment after I-PET negative assessment and new lesions at sites that were not initially involved.

Trial registration number and date of registration

HOVON-84: EudraCT: 2006–005,174-42, retrospectively registered 01–08-2008. HOVON-130: EudraCT: 2014–002,654-39, registered 26–01-2015

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05498-7.

18F-FDG PET baseline radiomics features improve the prediction of treatment outcome in diffuse large B-cell lymphoma

Purpose

Accurate prognostic markers are urgently needed to identify diffuse large B-Cell lymphoma (DLBCL) patients at high risk of progression or relapse. Our purpose was to investigate the potential added value of baseline radiomics features to the international prognostic index (IPI) in predicting outcome after first-line treatment.

Methods

Three hundred seventeen newly diagnosed DLBCL patients were included. Lesions were delineated using a semi-automated segmentation method (standardized uptake value ≥ 4.0), and 490 radiomics features were extracted. We used logistic regression with backward feature selection to predict 2-year time to progression (TTP). The area under the curve (AUC) of the receiver operator characteristic curve was calculated to assess model performance. High-risk groups were defined based on prevalence of events; diagnostic performance was assessed using positive and negative predictive values.

Results

The IPI model yielded an AUC of 0.68. The optimal radiomics model comprised the natural logarithms of metabolic tumor volume (MTV) and of SUV_peak and the maximal distance between the largest lesion and any other lesion (Dmax_bulk, AUC 0.76). Combining radiomics and clinical features showed that a combination of tumor- (MTV, SUV_peak and Dmax_bulk) and patient-related parameters (WHO performance status and age > 60 years) performed best (AUC 0.79). Adding radiomics features to clinical predictors increased PPV with 15%, with more accurate selection of high-risk patients compared to the IPI model (progression at 2-year TTP, 44% vs 28%, respectively).

Conclusion

Prediction models using baseline radiomics combined with currently used clinical predictors identify patients at risk of relapse at baseline and significantly improved model performance.

Trial registration number and date

EudraCT: 2006–005,174-42, 01–08-2008.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05480-3.

Quantitative radiomics features in diffuse large B-cell lymphoma: does segmentation method matter?

INTRODUCTION

Radiomics features may predict outcome in diffuse large B-cell lymphoma (DLBCL). Currently, multiple segmentation methods are used to calculate metabolic tumor volume (MTV). We assessed the influence of segmentation method on the discriminative power of radiomics features in DLBCL for patient level and for the largest lesion. Methods: 50 baseline ¹⁸F-fluorodeoxyglucose positron emission tomography computed tomography (PET/CT) scans of DLBCL patients who progressed or relapsed within 2 years after diagnosis were matched on uptake time and reconstruction method with 50 baseline PET/CT scans of DLBCL patients without progression. Scans were analysed using 6 semi-automatic segmentation methods (standardized uptake value (SUV)4.0, SUV2.5, 41% of the maximum SUV, 50% of the SUVpeak, majority vote (MV)2 and MV3, respectively). Based on these segmentations, 490 radiomics features were extracted at patient level and 486 features for the largest lesion. To quantify the agreement between features extracted from different segmentation methods, the intra-class correlation (ICC) agreement was calculated for each method compared to SUV4.0. The feature space was reduced by deleting features that had high Pearson correlations (≥0.7) with the previously established predictors MTV and/or SUVpeak. Model performance was assessed using stratified repeated cross-validation with 5 folds and 2000 repeats yielding the mean receiver-operating characteristics curve integral (CV-AUC) for all segmentation methods using logistic regression with backward feature selection. Results: The percentage of features yielding an ICC ≥0.75 compared to the SUV4.0 segmentation was lowest for A50P both at patient level and for the largest lesion, with 77.3% and 66.7% of the features yielding an ICC ≥0.75, respectively. Features were not highly correlated with MTV, with at least 435 features at patient level and 409 features for the largest lesion for all segmentation methods with a correlation coefficient <0.7. Features were highly correlated with SUVpeak (at least 190 and 134 were uncorrelated, respectively). CV-AUCs ranged between 0.69±0.11 and 0.84±0.09 for patient level, and between 0.69±0.11 and 0.73±0.10 for lesion level. Conclusion: Even though there are differences in the actual radiomics feature values derived and selected features between segmentation methods, there is no substantial difference in the discriminative power of radiomics features between segmentation methods.