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

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.