Radiomic assessment of oesophageal adenocarcinoma: a critical review of 18F-FDG PET/CT, PET/MRI and CT

Abstract

Objectives Radiomic models present an avenue to improve oesophageal adenocarcinoma assessment through quantitative medical image analysis. However, model selection is complicated by the abundance of available predictors and the uncertainty of their relevance and reproducibility. This analysis reviews recent research to facilitate precedent-based model selection for prospective validation studies. Methods This analysis reviews research on 18F-FDG PET/CT, PET/MRI and CT radiomics in oesophageal adenocarcinoma between 2016 and 2021. Model design, testing and reporting are evaluated according to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score and Radiomics Quality Score (RQS). Key results and limitations are analysed to identify opportunities for future research in the area. Results Radiomic models of stage and therapeutic response demonstrated discriminative capacity, though clinical applications require greater sensitivity. Although radiomic models predict survival within institutions, generalisability is limited. Few radiomic features have been recommended independently by multiple studies. Conclusions Future research must prioritise prospective validation of previously proposed models to further clinical translation.

Performance of radiomics-based artificial intelligence systems in the diagnosis and prediction of treatment response and survival in esophageal cancer: a systematic review and meta-analysis of diagnostic accuracy

“…Although there are reviews that discuss radiomics in esophageal cancer, they are specific to cancer type or an imaging modality. 5–8 This systematic review and meta-analysis consolidates the evidence for the role of radiomics throughout the esophageal cancer therapeutic pathway.…”

Nuclear medicine radiomics in digestive system tumors: Concept, applications, challenges, and future perspectives

“…[ 84 ] It is necessary to use external validation and confirm observations in multicenter settings to further clinical translation. [ 95 ] It is possible to evaluate accurate models based on the area under the curve (AUC). [ 96 ] AUC scores closer to 1.0 indicate a stronger discriminatory power.…”

“…We think that increased emphasis ought to be placed on assessing the broader applicability of models and robustness of the RFs through larger, high-quality prospective studies and independent external validation set for multi-institutional collaboration. [ 71 , 95 , 67 , 164 ]…”

Amide Proton Transfer‐Weighted Imaging and Multiple Models Intravoxel Incoherent Motion‐Based 18F‐FDG PET/MRI for Predicting Progression‐Free Survival in Non‐Small Cell Lung Cancer

“…13 18 F-Fluorodeoxyglucose positron emission tomography ( 18 F-FDG PET) is a molecular imaging method that focuses on the semiquantitative analysis of changes in glucose metabolism in lesions based on the uptake level of 18 F-FDG. 14 At present, although a few studies have explored the value of these imaging methods in the identification of benign and malignant lung lesions, subtype assessment, and epidermal growth factor receptor expression. [15][16][17][18] The aim of this study was to use an integrated 3.0 T PET/MRI scanner to perform chest APWI, multiple models IVIM, and 18 F-FDG PET scans in NSCLC patients and to analyze the relationship between each semiquantitative/ quantitative parameter and clinical factor and patients' progression-free survival (PFS), with a view to providing a reference for the personalized assessment of NSCLC patients' prognosis.…”

“…Intravoxel incoherent motion (IVIM) is another quantitative MRI imaging sequence that is capable of fitting three models, namely, mono‐, bi‐, and stretch‐exponential, according to different algorithms, which in turn reflect information regarding the diffusion, perfusion, and heterogeneity of the diseased tissue 13 . 18 F‐Fluorodeoxyglucose positron emission tomography ( 18 F‐FDG PET) is a molecular imaging method that focuses on the semiquantitative analysis of changes in glucose metabolism in lesions based on the uptake level of 18 F‐FDG 14 . At present, although a few studies have explored the value of these imaging methods in the identification of benign and malignant lung lesions, subtype assessment, and epidermal growth factor receptor expression 15–18 …”