CT radiomics to predict Deauville score 4 positive and negative Hodgkin lymphoma manifestations

Abstract

Abstract18F-FDG-PET/CT is standard to assess response in Hodgkin lymphoma by quantifying metabolic activity with the Deauville score. PET/CT, however, is time-consuming, cost-extensive, linked to high radiation and has a low availability. As an alternative, we investigated radiomics from non-contrast-enhanced computed tomography (NECT) scans. 75 PET/CT examinations of 43 patients on two different scanners were included. Target lesions were classified as Deauville score 4 positive (DS4+) or negative (DS4−) based on their SUVpeak and then segmented in NECT images. From these segmentations, 107 features were extracted with PyRadiomics. All further statistical analyses were then performed scanner-wise: differences between DS4+ and DS4− manifestations were assessed with the Mann–Whitney-U-test and single feature performances with the ROC-analysis. To further verify the reliability of the results, the number of features was reduced using different techniques. The feature median showed a high sensitivity for DS4+ manifestations on both scanners (scanner A: 0.91, scanner B: 0.85). It furthermore was the only feature that remained in both datasets after applying different feature reduction techniques. The feature median from NECT concordantly has a high sensitivity for DS4+ Hodgkin manifestations on two different scanners and thus could provide a surrogate for increased metabolic activity in PET/CT.

[18F]FDG PET radiomics score generated by cross-combination approach for treatment response and prognosis prediction in primary gastrointestinal diffuse large B-cell lymphoma patients

“…Jimenez et al [33] retrospectively analyzed baseline [18F]FDG PET/CT images of 169 lymphoma patients and developed a radiomic model (AUC = 0.860, sensitivity = 92.9%, speci city = 81.4%) that could predict the response to ibrutinib therapy, which was validated in a separate testing cohort. Currently, several studies have demonstrated the predictive value of radiomic features extracted from PET/CT images in predicting treatment response in HL [18,19]. Coskun et al [20] included 45 DLBCL patients treated with the R-CHOP regimen and found through multivariate analysis that SUVmax and gray-level co-occurrence matrix dissimilarity were independent predictors of incomplete response.…”

“…In recent years, signi cant progress has been made in using PET and PET/CT imaging for prognostic prediction through radiomics analysis [16,17]. Several studies have explored the prognostic value of PET/CT radiomics in lymphoma, including Hodgkin lymphoma (HL), NHL, and DLBCL, but there is limited research on the predictive value of PET/CT radiomics in PGI-DLBCL [18][19][20]. In contrast, only a small number of studies have evaluated the role of inter-tumor heterogeneity on [18F]FDG PET/CT in the prediction of lymphoma treatment response [21].These studies have employed various machine learning models to select and develop radiomic features, such as multilayer perceptron neural networks combined with logistic regression(LR) analysis [22], least absolute shrinkage and selection operator (LASSO) models [23]and LR models [24].…”

Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT

“…Radiomics, as a modern approach, facilitates quantitative assessments of medical images that extend beyond mere morphological characteristics [10]. The utilization of radiomics has expanded significantly over the years, particularly within the domain of cancer research, such as in the liver [11], prostate [12], breast [13], lung [14], and bone metastasis [15].…”