Tumor fragmentation estimated by volume surface ratio of tumors measured on 18F-FDG PET/CT is an independent prognostic factor of diffuse large B-cell lymphoma

Enhancing Lymphoma Diagnosis, Treatment, and Follow-Up Using 18F-FDG PET/CT Imaging: Contribution of Artificial Intelligence and Radiomics Analysis

Lymphoma, encompassing a wide spectrum of immune system malignancies, presents significant complexities in its early detection, management, and prognosis assessment since it can mimic post-infectious/inflammatory diseases. The heterogeneous nature of lymphoma makes it challenging to definitively pinpoint valuable biomarkers for predicting tumor biology and selecting the most effective treatment strategies. Although molecular imaging modalities, such as positron emission tomography/computed tomography (PET/CT), specifically 18F-FDG PET/CT, hold significant importance in the diagnosis of lymphoma, prognostication, and assessment of treatment response, they still face significant challenges. Over the past few years, radiomics and artificial intelligence (AI) have surfaced as valuable tools for detecting subtle features within medical images that may not be easily discerned by visual assessment. The rapid expansion of AI and its application in medicine/radiomics is opening up new opportunities in the nuclear medicine field. Radiomics and AI capabilities seem to hold promise across various clinical scenarios related to lymphoma. Nevertheless, the need for more extensive prospective trials is evident to substantiate their reliability and standardize their applications. This review aims to provide a comprehensive perspective on the current literature regarding the application of AI and radiomics applied/extracted on/from 18F-FDG PET/CT in the management of lymphoma patients.

Lymphoma: The Added Value of Radiomics, Volumes and Global Disease Assessment

Lymphoma represents a condition that holds promise for cure with existing treatment modalities; nonetheless, the primary clinical obstacle lies in advancing therapeutic outcomes by pinpointing high-risk individuals who are unlikely to respond favorably to standard therapy. In this article, the authors will delineate the significant strides achieved in the lymphoma field, with a particular emphasis on the 3 prevalent subtypes: Hodgkin lymphoma, diffuse large B-cell lymphomas, and follicular lymphoma.

Prognosis Prediction of Diffuse Large B-Cell Lymphoma in 18F-FDG PET Images Based on Multi-Deep-Learning Models

Diffuse large B-cell lymphoma (DLBCL), a cancer of B cells, has been one of the most challenging and complicated diseases because of its considerable variation in clinical behavior, response to therapy, and prognosis. Radiomic features from medical images, such as PET images, have become one of the most valuable features for disease classification or prognosis prediction using learning-based methods. In this paper, a new flexible ensemble deep learning model is proposed for the prognosis prediction of the DLBCL in 18F-FDG PET images. This study proposes the multi-R-signature construction through selected pre-trained deep learning models for predicting progression-free survival (PFS) and overall survival (OS). The proposed method is trained and validated on two datasets from different imaging centers. Through analyzing and comparing the results, the prediction models, including Age, Ann abor stage, Bulky disease, SUVmax, TMTV, and multi-R-signature, achieve the almost best PFS prediction performance (C-index: 0.770, 95% CI: 0.705-0.834, with feature adding fusion method and C-index: 0.764, 95% CI: 0.695-0.832, with feature concatenate fusion method) and OS prediction (C-index: 0.770 (0.692-0.848) and 0.771 (0.694-0.849)) on the validation dataset. The developed multiparametric model could achieve accurate survival risk stratification of DLBCL patients. The outcomes of this study will be helpful for the early identification of high-risk DLBCL patients with refractory relapses and for guiding individualized treatment strategies.

Prognostic value of the combination of volume, massiveness and fragmentation parameters measured on baseline FDG pet in high-burden follicular lymphoma

The prognostic value of radiomic quantitative features measured on pre-treatment 18F-FDG PET/CT was investigated in patients with follicular lymphoma (FL). We conducted a retrospective study of 126 FL patients (grade 1-3a) diagnosed between 2006 and 2020. A dozen of PET/CT-derived features were extracted via a software (Oncometer3D) from baseline 18F-FDG PET/CT images. The receiver operating characteristic (ROC) curve, Kaplan-Meier method and Cox analysis were used to assess the prognostic factors for progression of disease within 24 months (POD24) and progression-free survival at 24 months. Four different clusters were identified among the twelve PET parameters analyzed: activity, tumor burden, fragmentation-massiveness and dispersion. On ROC analyses, TMTV, the total metabolic tumor volume, had the highest AUC (0.734) followed by medPCD, the median distance between the centroid of the tumors and their periphery (AUC: 0.733). Patients with high TMTV (HR = 4.341; p < 0.001), high Tumor Volume Surface Ratio (TVSR) (HR = 3.204; p < 0.003) and high medPCD (HR = 4.507; p < 0.001) had significantly worse prognosis in both Kaplan-Meier and Cox univariate analyses. Furthermore, a synergistic effect was observed in Kaplan-Meier and Cox analyses combining these three PET/CT-derived parameters (HR = 12.562; p < 0.001). Having two or three high parameters among TMTV, TVSR and medPCD was able to predict POD24 status with a specificity of 68% and a sensitivity of 75%. TMTV, TVSR and baseline medPCD are strong prognostic factors in FL and their combination better predicts disease prognosis.

Indicators describing the tumor lesion aggregation and dissemination and their impact on the prognosis of patients with diffuse large B cell lymphoma receiving chimeric antigen receptor T cell therapy

INTRODUCTION

Chimeric antigen receptor (CAR) T cell therapy has markedly improved the prognosis of patients with diffuse large B-cell lymphoma (DLBCL). The relative positioning of tumor lesions in lymphoma varies among patients, manifesting as either aggregation (clumped together) or dissemination (spread throughout the body). Prognostic significance of factors indicating the relative positioning of tumor lesions in CAR T cell therapy remains underexplored. For aggregation, prior research proposed the tumor volume surface ratio (TVSR), linking it to prognosis in chemotherapy. Regarding dissemination, indicators such as disease stage or extranodal involvement, commonly used in clinical practice, have not demonstrated prognostic significance in CAR T cell therapy. This study aims to analyze current indicators of tumor aggregation or dissemination and introduce a novel indicator to assess the prognostic value of tumor lesions' relative positioning in DLBCL patients undergoing CAR T cell therapy.

METHODS

This retrospective study included 42 patients receiving CAR T cell therapy. Lesion image information was obtained from the last PET/CT scan prior to CAR T cell infusion, including total metabolic tumor volume, total tumor surface, diameter of lymphoma masses, and the sites of tumor lesions. We evaluated TVSR and bulky disease as descriptors of tumor aggregation. We refined existing indicators, stage III&IV and >1 site extranodal involvement, to distill a new indicator, termed 'extra stage', to better represent tumor dissemination. The study examined the prognostic significance of tumor aggregation and dissemination.

RESULTS

Our findings indicate that TVSR, while prognostically valuable in chemotherapy, lacks practical prognostic value in CAR T cell therapy. Conversely, bulky disease emerged as an optimal prognostic indicator of tumor aggregation. Both bulky disease and extra stage were associated with poor prognosis and exhibiting synergistic prognostic impact in CAR T cell therapy.

CONCLUSIONS

Overall, the relative positioning of tumor lesions significantly influences the prognosis of patients with DLBCL receiving CAR T cell therapy. The ideal scenario involves tumors with minimal dissemination and no aggregation.

Development of a radiomic-clinical nomogram for prediction of survival in patients with diffuse large B-cell lymphoma treated with chimeric antigen receptor T cells

BACKGROUND

In our current work, an 18F-FDG PET/CT radiomics-based model was developed to assess the progression-free survival (PFS) and overall survival (OS) of patients with relapsed or refractory (R/R) diffuse large B-cell lymphoma (DLBCL) who received chimeric antigen receptor (CAR)-T cell therapy.

METHODS

A total of 61 DLBCL cases receiving 18F-FDG PET/CT before CAR-T cell infusion were included in the current analysis, and these patients were randomly assigned to a training cohort (n = 42) and a validation cohort (n = 19). Radiomic features from PET and CT images were obtained using LIFEx software, and radiomics signatures (R-signatures) were then constructed by choosing the optimal parameters according to their PFS and OS. Subsequently, the radiomics model and clinical model were constructed and validated.

RESULTS

The radiomics model that integrated R-signatures and clinical risk factors showed superior prognostic performance compared with the clinical models in terms of both PFS (C-index: 0.710 vs. 0.716; AUC: 0.776 vs. 0.712) and OS (C-index: 0.780 vs. 0.762; AUC: 0.828 vs. 0.728). For validation, the C-index of the two approaches was 0.640 vs. 0.619 and 0.676 vs. 0.699 for predicting PFS and OS, respectively. Moreover, the AUC was 0.886 vs. 0.635 and 0.778 vs. 0.705, respectively. The calibration curves indicated good agreement, and the decision curve analysis suggested that the net benefit of radiomics models was higher than that of clinical models.

CONCLUSIONS

PET/CT-derived R-signature could be a potential prognostic biomarker for R/R DLBCL patients undergoing CAR-T cell therapy. Moreover, the risk stratification could be further enhanced when the PET/CT-derived R-signature was combined with clinical factors.

Prognostic value of whole-body dynamic 18F-FDG PET/CT Patlak in diffuse large B-cell lymphoma

Objective

This study aims to investigate the significance of interim whole-body dynamic 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) Patlak parameters for predicting the prognosis of patients with diffuse large B-cell lymphoma. To estimate the predictive value of the whole-body dynamic 18F-FDG PET/CT Patlak parameter for 2-year progression-free survival (PFS) and 2-year overall survival (OS).

Methods

This study reports the findings of 67 patients with diffuse large B-cell lymphoma (DLBCL). These patients underwent interim whole-body dynamic 18F-FDG PET/CT scans from June 2021 to January 2023 at the Department of Nuclear Medicine, First Affiliated Hospital of Anhui Medical University. The predictive values of maximum standard uptake value (SUVmax), maximum of net glucose uptake rate (Kimax) and the predictive model combining Kimax and interim treatment response on the prognosis of patients was analyzed using receiver operating characteristic (ROC) curves. Kaplan-Meier survival curves and log-rank tests were used for survival analysis. Univariate and multivariate analyses were performed to screen for independent prognostic risk factors.

Results

After a median follow-up of 18 months, 21 patients (31.3%) experienced disease recurrence or death. The cut-off values for the SUVmax and the Kimax were 6.1 and 0.13 μmol min-1·ml-1, respectively. Ann Arbor stage, IPI, SUVmax, Kimax and interim treatment response were associated with PFS and OS in the univariate analysis. However, only Kimax and interim treatment response were independent influences on PFS and OS in multivariate analysis.

Conclusion

Interim whole-body dynamic 18F-FDG PET/CT Patlak imaging has significant prognostic value in patients with DLBCL. Among them, the interim dynamic parameter Kimax showed the best predictive value for prognosis compared with the interim SUVmax and interim treatment response. The predictive model established by Kimax and the interim treatment response allowed for the accurate stratification of the prognostic risk of DLBCL.

Multi-scale feature similarity-based weakly supervised lymphoma segmentation in PET/CT images

Accurate lymphoma segmentation in PET/CT images is important for evaluating Diffuse Large B-Cell Lymphoma (DLBCL) prognosis. As systemic multiple lymphomas, DLBCL lesions vary in number and size for different patients, which makes DLBCL labeling labor-intensive and time-consuming. To reduce the reliance on accurately labeled datasets, a weakly supervised deep learning method based on multi-scale feature similarity is proposed for automatic lymphoma segmentation. Weak labeling was performed by randomly dawning a small and salient lymphoma volume for the patient without accurate labels. A 3D V-Net is used as the backbone of the segmentation network and image features extracted in different convolutional layers are fused with the Atrous Spatial Pyramid Pooling (ASPP) module to generate multi-scale feature representations of input images. By imposing multi-scale feature consistency constraints on the predicted tumor regions as well as the labeled tumor regions, weakly labeled data can also be effectively used for network training. The cosine similarity, which has strong generalization, is exploited here to measure feature distances. The proposed method is evaluated with a PET/CT dataset of 147 lymphoma patients. Experimental results show that when using data, half of which have accurate labels and the other half have weak labels, the proposed method performed similarly to a fully supervised segmentation network and achieved an average Dice Similarity Coefficient (DSC) of 71.47%. The proposed method is able to reduce the requirement for expert annotations in deep learning-based lymphoma segmentation.

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.

A prognostic model integrating PET-derived metrics and image texture analyses with clinical risk factors from GOYA

Image texture analysis (radiomics) uses radiographic images to quantify characteristics that may identify tumour heterogeneity and associated patient outcomes. Using fluoro-deoxy-glucose positron emission tomography/computed tomography (FDG-PET/CT)-derived data, including quantitative metrics, image texture analysis and other clinical risk factors, we aimed to develop a prognostic model that predicts survival in patients with previously untreated diffuse large B-cell lymphoma (DLBCL) from GOYA (NCT01287741). Image texture features and clinical risk factors were combined into a random forest model and compared with the international prognostic index (IPI) for DLBCL based on progression-free survival (PFS) and overall survival (OS) predictions. Baseline FDG-PET scans were available for 1263 patients, 832 patients of these were cell-of-origin (COO)-evaluable. Patients were stratified by IPI or radiomics features plus clinical risk factors into low-, intermediate- and high-risk groups. The random forest model with COO subgroups identified a clearer high-risk population (45% 2-year PFS [95% confidence interval (CI) 40%-52%]; 65% 2-year OS [95% CI 59%-71%]) than the IPI (58% 2-year PFS [95% CI 50%-67%]; 69% 2-year OS [95% CI 62%-77%]). This study confirms that standard clinical risk factors can be combined with PET-derived image texture features to provide an improved prognostic model predicting survival in untreated DLBCL.

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

Simple Summary

Diffuse large B-cell lymphoma (DLBCL) is the most common type of lymphoma. Even with the improvements in the treatment of DLBCL, around a quarter of patients will experience recurrence. The aim of this single centre retrospective study was to predict which patients would have recurrence within 2 years of their treatment using machine learning techniques based on radiomics extracted from the staging PET/CT images. Our study demonstrated that in our dataset of 229 patients (training data = 183, test data = 46) that a combined radiomic and clinical based model performed better than a simple model based on metabolic tumour volume, and that it had a good predictive ability which was maintained when tested on an unseen test set.

Abstract

Background: 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). Methods: 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. Results: 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. Conclusions: Radiomics based models demonstrate promise in predicting outcomes in DLBCL patients.

Gross Tumor Volume Definition and Comparative Assessment for Esophageal Squamous Cell Carcinoma From 3D 18F-FDG PET/CT by Deep Learning-Based Method

Background

The accurate definition of gross tumor volume (GTV) of esophageal squamous cell carcinoma (ESCC) can promote precise irradiation field determination, and further achieve the radiotherapy curative effect. This retrospective study is intended to assess the applicability of leveraging deep learning-based method to automatically define the GTV from 3D 18F-FDG PET/CT images of patients diagnosed with ESCC.

Methods

We perform experiments on a clinical cohort with 164 18F-FDG PET/CT scans. The state-of-the-art esophageal GTV segmentation deep neural net is first employed to delineate the lesion area on PET/CT images. Afterwards, we propose a novel equivalent truncated elliptical cone integral method (ETECIM) to estimate the GTV value. Indexes of Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD) are used to evaluate the segmentation performance. Conformity index (CI), degree of inclusion (DI), and motion vector (MV) are used to assess the differences between predicted and ground truth tumors. Statistical differences in the GTV, DI, and position are also determined.

Results

We perform 4-fold cross-validation for evaluation, reporting the values of DSC, HD, and MSD as 0.72 ± 0.02, 11.87 ± 4.20 mm, and 2.43 ± 0.60 mm (mean ± standard deviation), respectively. Pearson correlations (R2) achieve 0.8434, 0.8004, 0.9239, and 0.7119 for each fold cross-validation, and there is no significant difference (t = 1.193, p = 0.235) between the predicted and ground truth GTVs. For DI, a significant difference is found (t = −2.263, p = 0.009). For position assessment, there is no significant difference (left-right in x direction: t = 0.102, p = 0.919, anterior–posterior in y direction: t = 0.221, p = 0.826, and cranial–caudal in z direction: t = 0.569, p = 0.570) between the predicted and ground truth GTVs. The median of CI is 0.63, and the gotten MV is small.

Conclusions

The predicted tumors correspond well with the manual ground truth. The proposed GTV estimation approach ETECIM is more precise than the most commonly used voxel volume summation method. The ground truth GTVs can be solved out due to the good linear correlation with the predicted results. Deep learning-based method shows its promising in GTV definition and clinical radiotherapy application.

FDG-PET/CT in Lymphoma: Where Do We Go Now?

18F-fluorodeoxyglucose positron emission tomography combined with computed tomography (FDG-PET/CT) is an essential part of the management of patients with lymphoma at staging and response evaluation. Efforts to standardize PET acquisition and reporting, including the 5-point Deauville scale, have enabled PET to become a surrogate for treatment success or failure in common lymphoma subtypes. This review summarizes the key clinical-trial evidence that supports PET-directed personalized approaches in lymphoma but also points out the potential place of innovative PET/CT metrics or new radiopharmaceuticals in the future.

A novel analytic approach for outcome prediction in diffuse large B-cell lymphoma by [18F]FDG PET/CT

PURPOSE

This 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).

METHODS

We 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.

RESULTS

The 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.

CONCLUSION

The 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 REGISTRATION

NCT04317313. Registered March 16, 2020. Public site: https://clinicaltrials.gov/ct2/show/NCT04317313.

Computed Tomography Imaging Characteristics: Potential Indicators of Epidermal Growth Factor Receptor Mutation in Lung Adenocarcinoma

PURPOSE

The purpose of this study was to investigate the correlation between computed tomography imaging characteristics in lung adenocarcinoma and epidermal growth factor receptor (EGFR) mutations.

METHODS

A total of 124 patients with lung adenocarcinoma and known EGFR mutation status were collected in this retrospective study. Computed tomography quantitative parameters of each tumor, including total volume, total surface, surface-to-volume ratio (SVR), average diameter, maximum diameter, and average density, were determined using computer-aided detection software. The correlation between the EGFR mutation status and imaging characteristics was assessed. The predictive value of these imaging characteristics for EGFR mutation was calculated using the area under the receiver operating characteristic curve.

RESULT

Fifty-eight of 124 patients showed EGFR mutations. Patients who are female (P < 0.001) and nonsmokers (P < 0.001) and those with serum carcinoembryonic antigen (CEA) level of ≥5 (P = 0.035) were likely to have EGFR mutation. Computed tomography features including air bronchogram (P = 0.035), absence of cavitation (P = 0.010), and absence of pulmonary emphysema (P = 0.002) and quantitative parameters, such as smaller total surface (P = 0.002), smaller total volume (P = 0.001), higher SVR (P = 0.003), and smaller average diameter (P = 0.001), were associated with EGFR mutation. Logistic regression analysis revealed that the most significant independent prognostic factors of EGFR mutation for the model were nonsmoking (P = 0.035), CEA level of ≥5 (P = 0.004), presence of air bronchogram (P = 0.040), absence of cavitation (P = 0.021), and high SVR (P = 0.014). The area under the receiver operating characteristic curve, sensitivity, and specificity of the model for predicting EGFR mutation were 0.827, 75.8%, and 82.8%, respectively.

CONCLUSIONS

EGFR-mutated adenocarcinoma showed significantly increased CEA level, presence of air bronchogram, absence of cavitation, and higher quantitative parameter SVR than those with wild-type EGFR.

Development and validation of preoperative magnetic resonance imaging-based survival predictive nomograms for patients with perihilar cholangiocarcinoma after radical resection: A pilot study

PURPOSE

We aim to develop survival predictive tools to inform clinical decision-making in perihilar cholangiocarcinoma (pCCA).

MATERIALS AND METHODS

A total of 184 patients who had curative resection and magnetic resonance imaging (MRI) examination for pCCA between January 2010 and December 2018 were enrolled. 110 patients were randomly selected for model development, while the other 74 patients for model testing. Preoperative clinical, laboratory, and imaging data were analyzed. Preoperative clinical predictors were used independently or integrated with radiomics signatures to construct different preoperative models through the multivariable Cox proportional hazards method. The nomograms were constructed to predict overall survival (OS), and the performance of which was evaluated by the discrimination ability, time-dependent receiver operating characteristic curve (ROC), calibration curve, and decision curve.

RESULTS

The clinical model (Modelclinic) was constructed based on three independent variables including preoperative CEA, cN stage, and invasion of hepatic artery in images. The model yield the best performance (Modelclinic&AP&PVP) was build using three independent variables, SignatureAP and SignaturePVP. In training and testing cohorts, the concordance indexes (C-indexes) of Modelclinic were 0.846 (95 % CI, 0.735-0.957) and 0.755 (95 % CI, 0.540-969), and Modelclinic&AP&PVP achieved C-indexes of 0.962 (95 % CI, 0.905-1) and 0.814 (95 % CI, 0.569-1). Both Modelclinic and Modelclinic&AP&PVP outperformed the TNM staging system. Good agreement was observed in the calibration curves, and favorable clinical utility was validated using the decision curve analysis for Modelclinic and Modelclinic&AP&PVP.

CONCLUSION

Two preoperative nomograms were constructed to predict 1-, 3-, and 5-years survival for individual pCCA patients, demonstrating the potential for clinical application to assist decision-making.

Baseline PET/CT imaging parameters for prediction of treatment outcome in Hodgkin and diffuse large B cell lymphoma: a systematic review

Purpose

To systematically review the literature evaluating clinical utility of imaging metrics derived from baseline fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) for prediction of progression-free (PFS) and overall survival (OS) in patients with classical Hodgkin lymphoma (HL) and diffuse large B cell lymphoma (DLBCL).

Methods

A search of MEDLINE/PubMed, Web of Science, Cochrane, Scopus and clinicaltrials.gov databases was undertaken for articles evaluating PET/CT imaging metrics as outcome predictors in HL and DLBCL. PRISMA guidelines were followed. Risk of bias was assessed using the Quality in Prognosis Studies (QUIPS) tool.

Results

Forty-one articles were included (31 DLBCL, 10 HL). Significant predictive ability was reported in 5/20 DLBCL studies assessing SUVmax (PFS: HR 0.13–7.35, OS: HR 0.83–11.23), 17/19 assessing metabolic tumour volume (MTV) (PFS: HR 2.09–11.20, OS: HR 2.40–10.32) and 10/13 assessing total lesion glycolysis (TLG) (PFS: HR 1.078–11.21, OS: HR 2.40–4.82). Significant predictive ability was reported in 1/4 HL studies assessing SUVmax (HR not reported), 6/8 assessing MTV (PFS: HR 1.2–10.71, OS: HR 1.00–13.20) and 2/3 assessing TLG (HR not reported). There are 7/41 studies assessing the use of radiomics (4 DLBCL, 2 HL); 5/41 studies had internal validation and 2/41 included external validation. All studies had overall moderate or high risk of bias.

Conclusion

Most studies are retrospective, underpowered, heterogenous in their methodology and lack external validation of described models. Further work in protocol harmonisation, automated segmentation techniques and optimum performance cut-off is required to develop robust methodologies amenable for clinical utility.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05233-2.

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

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.

Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network

PURPOSE

Lymphoma lesion detection and segmentation on whole-body FDG-PET/CT are a challenging task because of the diversity of involved nodes, organs or physiological uptakes. We sought to investigate the performances of a three-dimensional (3D) convolutional neural network (CNN) to automatically segment total metabolic tumour volume (TMTV) in large datasets of patients with diffuse large B cell lymphoma (DLBCL).

METHODS

The dataset contained pre-therapy FDG-PET/CT from 733 DLBCL patients of 2 prospective LYmphoma Study Association (LYSA) trials. The first cohort (n = 639) was used for training using a 5-fold cross validation scheme. The second cohort (n = 94) was used for external validation of TMTV predictions. Ground truth masks were manually obtained after a 41% SUVmax adaptive thresholding of lymphoma lesions. A 3D U-net architecture with 2 input channels for PET and CT was trained on patches randomly sampled within PET/CTs with a summed cross entropy and Dice similarity coefficient (DSC) loss. Segmentation performance was assessed by the DSC and Jaccard coefficients. Finally, TMTV predictions were validated on the second independent cohort.

RESULTS

Mean DSC and Jaccard coefficients (± standard deviation) in the validations set were 0.73 ± 0.20 and 0.68 ± 0.21, respectively. An underestimation of mean TMTV by - 12 mL (2.8%) ± 263 was found in the validation sets of the first cohort (P = 0.27). In the second cohort, an underestimation of mean TMTV by - 116 mL (20.8%) ± 425 was statistically significant (P = 0.01).

CONCLUSION

Our CNN is a promising tool for automatic detection and segmentation of lymphoma lesions, despite slight underestimation of TMTV. The fully automatic and open-source features of this CNN will allow to increase both dissemination in routine practice and reproducibility of TMTV assessment in lymphoma patients.

Correlations between baseline 18F-FDG PET tumour parameters and circulating DNA in diffuse large B cell lymphoma and Hodgkin lymphoma

Background

¹⁸F-FDG PET/CT is a standard for many B cell malignancies, while blood DNA measurements are emerging tools. Our objective was to evaluate the correlations between baseline PET parameters and circulating DNA in diffuse large B cell lymphoma (DLBCL) and classical Hodgkin lymphoma (cHL).

Methods

Twenty-seven DLBCL and forty-eight cHL were prospectively included. Twelve PET parameters were analysed. Spearman’s correlations were used to compare PET parameters each other and to circulating cell-free DNA ([cfDNA]) and circulating tumour DNA ([ctDNA]). p values were controlled by Benjamini–Hochberg correction.

Results

Among the PET parameters, three different clusters for tumour burden, fragmentation/massiveness and dispersion parameters were observed. Some PET parameters were significantly correlated with blood DNA parameters, including the total metabolic tumour surface (TMTS) describing the tumour–host interface (e.g. ρ = 0.81 p < 0.001 for [ctDNA] of DLBLC), the tumour median distance between the periphery and the centroid (medPCD) describing the tumour’s massiveness (e.g. ρ = 0.81 p < 0.001 for [ctDNA] of DLBLC) and the volume of the bounding box including tumours (TumBB) describing the disease’s dispersion (e.g. ρ = 0.83 p < 0.001 for [ctDNA] of DLBLC).

Conclusions

Some PET parameters describing tumour burden, fragmentation/massiveness and dispersion are significantly correlated with circulating DNA parameters of DLBCL and cHL patients. These results could help to understand the pathophysiology of B cell malignancies.

Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma

PURPOSE

To automatically detect lymph nodes involved in lymphoma on fluorine 18 (¹⁸F) fluorodeoxyglucose (FDG) PET/CT images using convolutional neural networks (CNNs).

MATERIALS AND METHODS

In this retrospective study, baseline disease of 90 patients with lymphoma was segmented on ¹⁸F-FDG PET/CT images (acquired between 2005 and 2011) by a nuclear medicine physician. An ensemble of three-dimensional patch-based, multiresolution pathway CNNs was trained using fivefold cross-validation. Performance was assessed using the true-positive rate (TPR) and number of false-positive (FP) findings. CNN performance was compared with agreement between physicians by comparing the annotations of a second nuclear medicine physician to the first reader in 20 of the patients. Patient TPR was compared using Wilcoxon signed rank tests.

RESULTS

Across all 90 patients, a range of 0-61 nodes per patient was detected. At an average of four FP findings per patient, the method achieved a TPR of 85% (923 of 1087 nodes). Performance varied widely across patients (TPR range, 33%-100%; FP range, 0-21 findings). In the 20 patients labeled by both physicians, a range of 1-49 nodes per patient was detected and labeled. The second reader identified 96% (210 of 219) of nodes with an additional 3.7 per patient compared with the first reader. In the same 20 patients, the CNN achieved a 90% (197 of 219) TPR at 3.7 FP findings per patient.

CONCLUSION

An ensemble of three-dimensional CNNs detected lymph nodes at a performance nearly comparable to differences between two physicians' annotations. This preliminary study is a first step toward automated PET/CT assessment for lymphoma.© RSNA, 2020.