Prognostic Value of [18F]-FDG PET/CT Radiomics Combined with Sarcopenia Status among Patients with Advanced Gastroesophageal Cancer

Abstract

We investigated, whether 18[18F]-FDG PET/CT-derived radiomics combined with sarcopenia measurements improves survival prognostication among patients with advanced, metastatic gastroesophageal cancer. In our study, 128 consecutive patients with advanced, metastatic esophageal and gastroesophageal cancer (n = 128; 26 females; 102 males; mean age 63.5 ± 11.7 years; age range: 29–91 years) undergoing 18[18F]-FDG PET/CT for staging between November 2008 and December 2019 were included. Segmentation of the primary tumor and radiomics analysis derived from PET and CT images was performed semi-automatically with a commonly used open-source software platform (LIFEX, Version 6.30, lifexsoft.org). Patients’ nutritional status was determined by measuring the skeletal muscle index (SMI) at the level of L3 on the CT component. Univariable and multivariable analyses were performed to establish a survival prediction model including radiomics, clinical data, and SMI score. Univariable Cox proportional hazards model revealed ECOG (<0.001) and bone metastasis (p = 0.028) to be significant clinical parameters for overall survival (OS) and progression free survival (PFS). Age (p = 0.017) was an additional prognostic factor for OS. Multivariable analysis showed improved prognostication for overall and progression free survival when adding sarcopenic status, PET and CT radiomics to the model with clinical parameters only. PET and CT radiomics derived from hybrid 18[18F]-FDG PET/CT combined with sarcopenia measurements and clinical parameters may improve survival prediction among patients with advanced, metastatic gastroesophageal cancer.

The [18F]F-FDG PET/CT Radiomics Classifier of Histologic Subtypes and Anatomical Disease Origins across Various Malignancies: A Proof-of-Principle Study

“…Thus, our study also adds to the literature that non-contrast CT radiomics derived from the CT component of the PET/CT may provide incremental information about pathophysiology and biology, further enhancing the diagnostic and predictive value of PET/CT, beyond staging and restaging purposes. Furthermore, the majority of prediction models pursue a multi-omics approach in combination with clinical parameters [13,30], whereas in our proof-of-principle study, the use of radiomics only already achieved a high degree of statistical performance, indicating further potential improvement of the predictive ability when adding clinical parameters. This emphasizes that PET may remain an important diagnostic tool, providing better disease visualization and revealing glucose metabolism, which is particularly beneficial in N-and M-staging.…”

“…Thus, our study also adds to the literature that non-contrast CT radiomics derived from the CT component of the PET/CT may provide incremental information about pathophysiology and biology, further enhancing the diagnostic and predictive value of PET/CT, beyond staging and restaging purposes. Furthermore, the majority of prediction models pursue a multi-omics approach in combination with clinical parameters [13,30], whereas in our proof-of-principle study, the use of radiomics only already achieved a high degree of statistical performance, indicating further potential The main strength of radiomics data in oncology is the fact that digital radiological images are obtained for almost every cancer patient [26]. Thus, radiomics analyses may contribute to the improvement of understanding tumour biology and the pursuit of precision medicine, in which such markers are used to determine optimal treatment and predict outcome and therapy response.…”

“…Image segmentation and radiomics features extraction were performed with a commonly used open-source and IBSI-compliant software platform (LIFEx, Version 6.30; [12]) by one independent reader with 5 years of experience in oncologic radiology and hybrid imaging. Imaging segmentation and contouring have been described in detail before in other evaluations by our group [13]. The contours of the primary pulmonary, gastroesophageal and head and neck tumours were semi-automatically delineated and segmented using a threshold method, applying three different thresholds on the PET volumes of interest (VOI) (PET overall, PET SUVpeak, and PET 40% and 70% SUVmax thresholds) [13,14].…”

“…Imaging segmentation and contouring have been described in detail before in other evaluations by our group [13]. The contours of the primary pulmonary, gastroesophageal and head and neck tumours were semi-automatically delineated and segmented using a threshold method, applying three different thresholds on the PET volumes of interest (VOI) (PET overall, PET SUVpeak, and PET 40% and 70% SUVmax thresholds) [13,14]. Notably, among them, the overall thresholding (contrast to the background) was the best method of thresholding, having the most significant variables in the further analyses.…”

Prognostic Value of18F-FDG PET/CT Radiomics in Extranodal Nasal-Type NK/T Cell Lymphoma

“…However, ENKTCL can induce chronic inflammation in the nasal cavity and nasopharynx, which may impact the accuracy of measurements. Furthermore, the above parameters are obtained from setting corresponding thresholds for delineated regions of interest, which may not fully capture the spatial distribution characteristics of tracer activity strongly associated with tumor heterogeneity [ 10 11 ]. Radiomics offers potential pathophysiological information through high-throughput extraction of features from medical images, quantitatively analyzes tumor heterogeneity, and selects features for constructing prognostic prediction models through specific algorithms and statistical analysis to promote the development of precise and individualized tumor treatment [ 12 13 ].…”