The role of 18F-FDG PET/CT radiomics in lymphoma

The Predictive Role of Baseline 18F-FDG PET/CT Radiomics in Follicular Lymphoma on Watchful Waiting: A Preliminary Study

Background: Patients with low tumour burden follicular lymphoma (FL) are managed with an initial watchful waiting (WW) approach. The way to better predict the time-to-treatment (TTT) is still under investigation for its possible clinical impact. This study explored whether radiomic features extracted from baseline 18F-FDG PET/CT could predict TTT in FL patients on WW. Methods: Thirty-eight patients on initial WW (grade 1-3a) were retrospectively included from 2010 to 2019. Eighty-one PET/CT morphological and first-level intensity radiomic features were extracted from the total metabolic tumour burden (TMTV), the lesion having the highest SUVmax and a reference volume-of-interest placed on the healthy liver. Models using linear regression (LR) and support vector machine (SVM) were constructed to assess the feasibility of using radiomic features to predict TTT. A leave-one-out cross-validation approach was used to assess the performance. Results: For LR models, we found a root-mean-squared error of 29.4, 28.6, 26.4 and 26.8 and an R2 of 0.03, 0.08, 0.21 and 0.20, respectively, incrementing the features from one to four. Accordingly, the best model included three features: the liver minimum SUV value, the liver SUV skewness and the sum of squared SUV values in the TMTV. For SVM models, accuracies of 0.79, 0.63, 0.76 and 0.68 and areas under the curve of 0.80, 0.72, 0.77 and 0.63 were found, respectively, incrementing the features from one to four. The best performing model used one feature, namely the median value of the lesion containing the SUVmax value. Conclusions: The baseline PET/CT radiomic approach has the potential to predict TTT in FL patients on WW. Integrating radiomics with clinical parameters could further aid in patient stratification.

Diagnostic Value of 18F-FDG PET/CT Radiomics in Lymphoma: A Systematic Review and Meta-Analysis

IntroductionVarious machine learning models and features have been proposed for lymphoma diagnosis using 18F-fluorodeoxyglucose (18F-FDG) PET/CT radiomics. This research aimed to systematically evaluate the diagnostic value of 18F-FDG PET/CT radiomics in lymphoma by conducting a meta-analysis.MethodsData from published studies regarding the diagnosis of lymphoma using 18F-FDG PET/CT radiomics, from January 2010 to July 2024, were gathered from PubMed, Web of Science, and the Cochrane Library. Following their separate searches and screenings of the literature, two researchers extracted data and assessed the caliber of all the included studies. The quality assessment involved the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2), the Radiomics Quality Score (RQS), and the METhodological RadiomICs Score (METRICS). The meta-analysis was conducted by using RevMan 5.4.1, R 4.4.0, and Stata 17.0 software. Six meta-regressions were conducted on study performance, considering sample size, image modality, region of interest (ROI) selection, ROI segmentation, radiomics mode, and algorithms.ResultsIn total, 20 studies classified as type 2a or above according to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement were included for this systematic review and meta-analysis. The studies achieved an average RQS of 13 (ranging from 10 to 17), accounting for 36.1% of the total points. The average METRICS score was 69.3% (ranging from 54.8% to 80.9%). The quality category of the studies is mainly "good". The results of our meta-analysis showed that the pooled sensitivity (SEN), specificity (SPE), positive likelihood ratio, negative likelihood ratio and diagnostic odds ratio with 95% confidence interval (CI) were 0.82 (0.78, 0.88), 0.83 (0.76, 0.87), 4.7 (3.4, 6.6), 0.20 (0.15, 0.28) and 23 (13, 42), respectively. The area under the curve of the summary receiver operating characteristic curve was 0.90 (0.87, 0.92). The results of Spearman correlation analysis revealed no threshold effect among the studies (P = .423). Significant heterogeneity was observed among the studies (overall I2 = 83.7%; 95% CI: 76.0, 88.9; P < .01). Meta-regressions indicated that sample size and ROI selection contributed to the heterogeneity in SEN, while algorithms affected the heterogeneity in SPE (P < .05). Deeks' test confirmed there was no significant publication bias in all the included studies. The Fagan nomogram showed an absolute increase of 34% in the post-test probability following a positive test result.ConclusionThe results supported that 18F-FDG PET/CT radiomics has high diagnostic value for lymphoma. However, there is high heterogeneity among different studies. In the future, clinical practicality needs to be substantiated by more prospective studies with rigorous adherence to existing guidelines and multicentric validation.

The predictive power of 18F-FDG PET/CT two-lesions radiomics and conventional models in classical Hodgkin's Lymphoma: a comparative retrospectively-validated study

In a previous preliminary study, radiomic features from the largest and the hottest lesion in baseline 18F-FDG PET/CT (bPET/CT) of classical Hodgkin's Lymphoma (cHL) predicted early response-to-treatment and prognosis. Aim of this large retrospectively-validated study is to evaluate the predictive role of two-lesions radiomics in comparison with other clinical and conventional PET/CT models. cHL patients with bPET/CT between 2010 and 2020 were retrospectively included and randomized into training-validation sets. Target lesions were: Lesion_A, with largest axial diameter (Dmax); Lesion_B, with highest SUVmax. Total-metabolic-tumor-volume (TMTV) was calculated and 212 radiomic features were extracted. PET/CT features were harmonized using ComBat across two scanners. Outcomes were progression-free-survival (PFS) and Deauville Score at interim PET/CT (DS). For each outcome, three predictive models and their combinations were trained and validated: - radiomic model "R"; - conventional PET/CT model "P"; - clinical model "C". 197 patients were included (training = 118; validation = 79): 38/197 (19%) patients had adverse events and 42/193 (22%) had DS ≥ 4. In the training phase, only one radiomic feature was selected for PFS prediction in model "R" (Lesion_B F_cm.corr, C-index 66.9%). Best "C" model combined stage and IPS (C-index 74.8%), while optimal "P" model combined TMTV and Dmax (C-index 63.3%). After internal validation, "C", "C + R", "R + P" and "C + R + P" significantly predicted PFS. The best validated model was "C + R" (C-index 66.3%). No model was validated for DS prediction. In this large retrospectively-validated study, a combination of baseline 18F-FDG PET/CT two-lesions radiomics and other conventional models showed an added prognostic power in patients with cHL. As single models, conventional clinical parameters maintain their prognostic power, while radiomics or conventional PET/CT alone seem to be sub-optimal to predict survival.

Multicentric study on the reproducibility and robustness of PET-based radiomics features with a realistic activity painting phantom

Previously, we developed an "activity painting" tool for PET image simulation; however, it could simulate heterogeneous patterns only in the air. We aimed to improve this phantom technique to simulate arbitrary lesions in a radioactive background to perform relevant multi-center radiomic analysis. We conducted measurements moving a 22Na point source in a 20-liter background volume filled with 5 kBq/mL activity with an adequately controlled robotic system to prevent the surge of the water. Three different lesion patterns were "activity-painted" in five PET/CT cameras, resulting in 8 different reconstructions. We calculated 46 radiomic indeces (RI) for each lesion and imaging setting, applying absolute and relative discretization. Reproducibility and reliability were determined by the inter-setting coefficient of variation (CV) and the intraclass correlation coefficient (ICC). Hypothesis tests were used to compare RI between lesions. By simulating precisely the same lesions, we confirmed that the reconstructed voxel size and the spatial resolution of different PET cameras were critical for higher order RI. Considering conventional RIs, the SUVpeak and SUVmean proved the most reliable (CV<10%). CVs above 25% are more common for higher order RIs, but we also found that low CVs do not necessarily imply robust parameters but often rather insensitive RIs. Based on the hypothesis test, most RIs could clearly distinguish between the various lesions using absolute resampling. ICC analysis also revealed that most RIs were more reproducible with absolute discretization. The activity painting method in a real radioactive environment proved suitable for precisely detecting the radiomic differences derived from the different camera settings and texture characteristics. We also found that inter-setting CV is not an appropriate metric for analyzing RI parameters' reliability and robustness. Although multicentric cohorts are increasingly common in radiomics analysis, realistic texture phantoms can provide indispensable information on the sensitivity of an RI and how an individual RI parameter measures the texture.

PET radiomics in lung cancer: advances and translational challenges

Radiomics is an emerging field of medical imaging that aims at improving the accuracy of diagnosis, prognosis, treatment planning and monitoring non-invasively through the automated or semi-automated quantitative analysis of high-dimensional image features. Specifically in the field of nuclear medicine, radiomics utilizes imaging methods such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) to evaluate biomarkers related to metabolism, blood flow, cellular activity and some biological pathways. Lung cancer ranks among the leading causes of cancer-related deaths globally, and radiomics analysis has shown great potential in guiding individualized therapy, assessing treatment response, and predicting clinical outcomes. In this review, we summarize the current state-of-the-art radiomics progress in lung cancer, highlighting the potential benefits and existing limitations of this approach. The radiomics workflow was introduced first including image acquisition, segmentation, feature extraction, and model building. Then the published literatures were described about radiomics-based prediction models for lung cancer diagnosis, differentiation, prognosis and efficacy evaluation. Finally, we discuss current challenges and provide insights into future directions and potential opportunities for integrating radiomics into routine clinical practice.

PET/CT in Hodgkin Lymphoma: An Update

¹⁸F-FDG-PET/CT is now an integral part of the workup and management of patients with Hodgkin's lymphoma (HL). PET/CT is currently routinely performed for staging and for response assessment at the end of treatment. Interim PET/CT is typically performed after 1-4 of 6-8 chemo/chemoimmunotherapy cycles ± radiation for prognostication and potential treatment escalation or de-escalation early in the course of therapy, a concept known as response-or risk-adapted treatment. Quantitative PET is an area of growing interest. Metrics such as the standardized uptake value (SUV), metabolic tumor volume, total lesion glycolysis, and their changes with treatment are being investigated as more reproducible and, potentially, more accurate predictors of response and prognosis. Despite the progress made in standardizing the use of PET/CT in lymphoma, challenges remain, particularly with respect to its limited positive predictive value. This review highlights the most relevant applications of PET/CT in HL, its strengths and limitations, as well as recent efforts to implement PET/CT-based metrics as promising tools for precision medicine. Finally, the value of PET/CT for response assessment to immunotherapy is discussed.

Role of Artificial Intelligence in PET/CT Imaging for Management of Lymphoma

Our review shows that AI-based analysis of lymphoma whole-body FDG-PET/CT can inform all phases of clinical management including staging, prognostication, treatment planning, and treatment response evaluation. We highlight advancements in the role of neural networks for performing automated image segmentation to calculate PET-based imaging biomarkers such as the total metabolic tumor volume (TMTV). AI-based image segmentation methods are at levels where they can be semi-automatically implemented with minimal human inputs and nearing the level of a second-opinion radiologist. Advances in automated segmentation methods are particularly apparent in the discrimination of lymphomatous vs non-lymphomatous FDG-avid regions, which carries through to automated staging. Automated TMTV calculators, in addition to automated calculation of measures such as Dmax are informing robust models of progression-free survival which can then feed into improved treatment planning.

Baseline 18F-FDG PET/CT Radiomics in Classical Hodgkin's Lymphoma: The Predictive Role of the Largest and the Hottest Lesions

This study investigated the predictive role of baseline 18F-FDG PET/CT (bPET/CT) radiomics from two distinct target lesions in patients with classical Hodgkin's lymphoma (cHL). cHL patients examined with bPET/CT and interim PET/CT between 2010 and 2019 were retrospectively included. Two bPET/CT target lesions were selected for radiomic feature extraction: Lesion_A, with the largest axial diameter, and Lesion_B, with the highest SUVmax. Deauville score at interim PET/CT (DS) and 24-month progression-free-survival (PFS) were recorded. Mann-Whitney test identified the most promising image features (p < 0.05) from both lesions with regards to DS and PFS; all possible radiomic bivariate models were then built through a logistic regression analysis and trained/tested with a cross-fold validation test. The best bivariate models were selected based on their mean area under curve (mAUC). A total of 227 cHL patients were included. The best models for DS prediction had 0.78 ± 0.05 maximum mAUC, with a predominant contribution of Lesion_A features to the combinations. The best models for 24-month PFS prediction reached 0.74 ± 0.12 mAUC and mainly depended on Lesion_B features. bFDG-PET/CT radiomic features from the largest and hottest lesions in patients with cHL may provide relevant information in terms of early response-to-treatment and prognosis, thus representing an earlier and stronger decision-making support for therapeutic strategies. External validations of the proposed model are planned.

Semi-automated 18F-FDG PET segmentation methods for tumor volume determination in Non-Hodgkin lymphoma patients: a literature review, implementation and multi-threshold evaluation

In the treatment of Non-Hodgkin lymphoma (NHL), multiple therapeutic options are available. Improving outcome predictions are essential to optimize treatment. The metabolic active tumor volume (MATV) has shown to be a prognostic factor in NHL. It is usually retrieved using semi-automated thresholding methods based on standardized uptake values (SUV), calculated from ¹⁸F-Fluorodeoxyglucose Positron Emission Tomography (¹⁸F-FDG PET) images. However, there is currently no consensus method for NHL. The aim of this study was to review literature on different segmentation methods used, and to evaluate selected methods by using an in house created software tool. A software tool, MUltiple SUV Threshold (MUST)-segmenter was developed where tumor locations are identified by placing seed-points on the PET images, followed by subsequent region growing. Based on a literature review, 9 SUV thresholding methods were selected and MATVs were extracted. The MUST-segmenter was utilized in a cohort of 68 patients with NHL. Differences in MATVs were assessed with paired t-tests, and correlations and distributions figures. High variability and significant differences between the MATVs based on different segmentation methods (p < 0.05) were observed in the NHL patients. Median MATVs ranged from 35 to 211 cc. No consensus for determining MATV is available based on the literature. Using the MUST-segmenter with 9 selected SUV thresholding methods, we demonstrated a large and significant variation in MATVs. Identifying the most optimal segmentation method for patients with NHL is essential to further improve predictions of toxicity, response, and treatment outcomes, which can be facilitated by the MUST-segmenter.

[18F]FDG PET/CT and PET/MR in Patients with Adrenal Lymphoma: A Systematic Review of Literature and a Collection of Cases

AIM

The present study aimed to assess the existing data about Primary Adrenal Lymphoma (PAL) evaluated with FDG PET and to describe a small monocentric series of cases. A systematic analysis (from 2010 to 2022) was made by using PubMed and Web of Science databases reporting data about the role of FDG PET/CT in patients with suspicious or known adrenal lymphoma. The quality of the papers was assessed by using QUADAS-2 criteria. Moreover, from a single institutional collection between 2010 and 2021, data from patients affected by adrenal lymphoma and undergoing contrast-enhanced compute tomography (ceCT)/magnetic resonance (MR) and FDG PET/CT or PET/MR were retrieved and singularly described. Seventy-eight papers were available from PubMed and 25 from Web of Science. Forty-seven (Nr. 47) Patients were studied, most of them in the initial staging of disease (n = 42; 90%). Only in one paper, the scan was made before and after therapy. The selected clinical cases were relative to the initial staging of disease, the restaging, and the evaluation of response to therapy. PET/CT and PET/MR always showed a high FDG uptake in the primary adrenal lesions and in metastatic sites. Moreover, PET metrics, such as maximum standardized uptake value (SUVmax) and metabolic tumor volume (MTV), were elevated in all primary adrenal lesions. In conclusions, FDG PET either coupled with CT or MRI can be useful in staging, restaging, and for the evaluation of treatment response in patients affected by PAL.

Classical Hodgkin Lymphoma: A Joint Clinical and PET Model to Predict Poor Responders at Interim Assessment

(1) This study aimed to investigate whether baseline clinical and Positron Emission Tomography/Computed Tomography (bPET)-derived parameters could help predicting early response to the first two cycles of chemotherapy (Deauville Score at interim PET, DS at iPET) in patients with classical Hodgkin lymphoma (cHL) to identify poor responders (DS ≥ 4) who could benefit from first-line treatment intensification at an earlier time point. (2) cHL patients with a bPET and an iPET imaging study in our Centre’s records (2013−2019), no synchronous/metachronous tumors, no major surgical resection of disease prior to bPET, and treated with two cycles of ABVD chemotherapy before iPET were retrospectively included. Baseline International Prognostic Score for HL (IPS) parameters were collected. Each patient’s bPET total metabolic tumor volume (TMTV) and highest tumoral SUVmax were collected. ROC curves and Youden’s index were used to derive the optimal thresholds of TMTV and SUVmax with regard to the DS (≥4). Chi-square or Fisher’s exact test were used for the univariate analysis. A multivariate analysis was then performed using logistic regression. The type I error rate in the hypothesis testing was set to 5%. (3) A total of 146 patients were included. The optimal threshold to predict a DS ≥ 4 was >177 mL for TMTV and >14.7 for SUVmax (AUC of 0.65 and 0.58, respectively). The univariate analysis showed that only TMTV, SUVmax, advanced disease stage, and age were significantly associated with a DS ≥ 4. A multivariate model was finally derived from TMTV, SUVmax, and age, with an AUC of 0.77. (4) A multivariate model with bPET parameters and age at diagnosis was satisfactorily predictive of poor response at iPET after ABVD induction chemotherapy in cHL patients. More studies are needed to validate these results and further implement DS-predictive factors at baseline in order to prevent poor response and intensify therapeutic strategies a-priori when needed.

Artificial Intelligence in Lymphoma PET Imaging:: A Scoping Review (Current Trends and Future Directions)

Malignant lymphomas are a family of heterogenous disorders caused by clonal proliferation of lymphocytes. 18F-FDG-PET has proven to provide essential information for accurate quantification of disease burden, treatment response evaluation, and prognostication. However, manual delineation of hypermetabolic lesions is often a time-consuming and impractical task. Applications of artificial intelligence (AI) may provide solutions to overcome this challenge. Beyond segmentation and detection of lesions, AI could enhance tumor characterization and heterogeneity quantification, as well as treatment response prediction and recurrence risk stratification. In this scoping review, we have systematically mapped and discussed the current applications of AI (such as detection, classification, segmentation as well as the prediction and prognostication) in lymphoma PET.