Radiomics or textural feature extraction obtained from positron emission tomography (PET) images through complex mathematical models of the spatial relationship between multiple image voxels is currently emerging as a new tool for assessing intra-tumoral heterogeneity in medical imaging. In this paper, available literature on texture analysis using FDG PET imaging in patients suffering from tumors of the gastro-intestinal tract is reviewed. While texture analysis of FDG PET images appears clinically promising, due to the lack of technical specifications, a large variability in the implemented methodology used for texture analysis and lack of statistical robustness, at present, no firm conclusions can be drawn regarding the predictive or prognostic value of FDG PET texture analysis derived indices in patients suffering from gastro-enterologic tumors. In order to move forward in this field, a harmonized image acquisition and processing protocol as well as a harmonized protocol for texture analysis of tumor volumes, allowing multi-center studies excluding statistical biases should be considered. Furthermore, the complementary and additional value of CT-imaging, as part of the PET/CT imaging technique, warrants exploration.
Background Although most guidelines suggest performing a positron emission tomography/computed tomography (PET/CT) with somatostatin receptor (SSTR) ligands for staging of pulmonary carcinoid tumours (PC), only a limited number of studies have evaluated the role of this imaging tool in this specific patient population. The preoperative differentiation between typical carcinoid (TC) and atypical carcinoid (AC) and the extent of dissemination (N/M status) are crucial factors for treatment allocation and prognosis of these patients. Therefore, we performed a pathology-based retrospective analysis of the value of SSTR PET/CT in tumour grading and detection of nodal and metastatic involvement of PC and compared this with the previous literature and with [18F]FDG PET/CT in a subgroup of patients. Methods SSTR PET/CT scans performed between January 2007 and May 2020 in the context of PC were included. If available, [18F]FDG PET/CT images were also evaluated. The maximum standardized uptake (SUVmax) values of the primary tumour, of the pathologically examined hilar and mediastinal lymph node stations, as well as of the distant metastases, were recorded. Tumoural SUVmax values were related to the tumour type (TC versus AC) for both SSTR and [18F]FDG PET/CT in diagnosing and differentiating both tumour types. Nodal SUVmax values were compared to the pathological status (N+ versus N−) to evaluate the diagnostic accuracy of SSTR PET/CT in detecting lymph node involvement. Finally, a mixed model analysis of all pathologically proven distant metastatic lesions was performed. Results A total of 86 SSTR PET/CT scans performed in 86 patients with PC were retrospectively analysed. [18F]FDG PET/CT was available in 46 patients. Analysis of the SUVmax values in the primary tumour showed significantly higher SSTR uptake in TC compared with AC (median SUVmax 18.4 vs 3.8; p = 0.003) and significantly higher [18F]FDG uptake in AC compared to TC (median SUVmax 5.4 vs 3.5; p = 0.038). Receiver operating characteristic (ROC) curve analysis resulted in an area under the curve (AUC) of 0.78 for the detection of TC on SSTR PET/CT and of 0.73 for the detection of AC on [18F]FDG PET/CT. A total of 267 pathologically evaluated hilar and mediastinal lymph node stations were analysed. ROC analysis of paired SSTR/[18F]FDG SUVmax values for the detection of metastasis of TC in 83 lymph node stations revealed an AUC of 0.91 for SSTR PET/CT and of 0.74 for [18F]FDG PET/CT (difference 0.17; 95% confidence interval − 0.03 to 0.38; p = 0.10). In a sub-cohort of 10 patients with 12 distant lesions that were pathologically examined due to a suspicious aspect on SSTR PET/CT, a positive predictive value (PPV) of 100% was observed. Conclusion Our findings confirm the higher SSTR ligand uptake in TC compared to AC and vice versa for [18F]FDG uptake. More importantly, we found a good diagnostic performance of SSTR PET/CT for the detection of hilar and mediastinal lymph node metastases of TC. Finally, a PPV of 100% for SSTR PET/CT was found in a small sub-cohort of patients with pathologically investigated distant metastatic lesions. Taken together, SSTR PET/CT has a very high diagnostic value in the TNM assessment of pulmonary carcinoids, particularly in TC, which underscores its position in European guidelines.
Background Although most guidelines suggest performing a positron emission tomography/computed tomography (PET/CT) with somatostatin receptor (SSTR) ligands for staging of pulmonary carcinoid tumours (PC), only a limited number of studies have evaluated the role of this imaging tool in this specific patient population. The preoperative differentiation between typical carcinoid (TC) and atypical carcinoid (AC) and the extent of dissemination (N/M status) are crucial factors for treatment allocation and prognosis of these patients. Therefore we performed a retrospective analysis to assess the value of SSTR PET/CT in the tumour grading and the detection of lymph node involvement and distant metastases of PC with histopathology as gold standard, and compared this to [18F]FDG PET/CT in a subgroup of patients and to previous literature with group sizes of mostly 20-30 patients. Methods SSTR PET/CT scans performed between January 2007 and May 2020 in the context of PC were included. If available, [18F]FDG PET/CT images were also evaluated. The maximum standardized uptake (SUVmax) values of the primary tumour, of the pathologically examined hilar and mediastinal lymph nodes, as well as of the distant metastases, were recorded. Tumoural SUVmax values were related to the tumour type (TC versus AC) for both SSTR and [18F]FDG PET/CT in diagnosing and differentiating both tumour types. Nodal SUVmax values were compared to the pathological status (N+ versus N−) to evaluate the diagnostic accuracy of SSTR PET/CT in detecting lymph node involvement. Finally, a mixed model analysis of all pathologically proven distant metastatic lesions was performed. Results A total of 86 SSTR PET/CT scans performed in 86 patients with PC were retrospectively analyzed. [18F]FDG PET/CT was available in 46 patients. Analysis of the SUVmax values in the primary tumour showed significantly higher SSTR uptake in TC compared with AC (median SUVmax 18.4 vs 3.8; p=0.003) and significantly higher [18F]FDG uptake in AC compared to TC (median SUVmax 5.4 vs 3.5; p=0.038). Receiver operating characteristic (ROC) curve analysis resulted in an area under the curve (AUC) of 0.78 for the detection of TC on SSTR PET/CT and of 0.73 for the detection of AC on [18F]FDG PET/CT. A total of 267 pathologically evaluated hilar and mediastinal lymph nodes were analyzed. ROC analysis of paired SSTR/[18F]FDG SUVmax values for the detection of metastasis of TC in 83 lymph nodes revealed an AUC of 0.91 for SSTR PET/CT and of 0.74 for [18F]FDG PET/CT (difference 0.17; 95% confidence interval: -0.03 to 0.38; p = 0.10). In a sub-cohort of 10 patients with 12 lesions suspicious for distant metastases on SSTR PET/CT that were investigated with biopsies, a positive predictive value (PPV) of 100% was observed. Conclusion Our findings confirm the higher SSTR ligand uptake in TC compared to AC and vice versa for the [18F]FDG uptake. More importantly, we found a good diagnostic performance of SSTR PET/CT for the detection of hilar and mediastinal lymph node metastases of TC. Finally, a PPV of 100% for SSTR PET/CT was found in a small sub-cohort of patients with pathologically investigated distant metastatic lesions. Taken together, SSTR PET/CT has a very high diagnostic value in the TNM assessment of pulmonary carcinoids, particularly in TC, which underscores its position in European guidelines.
Background: The clinical utility of radiomics is hampered by a high correlation between the large number of features analysed which may result in the "bouncing beta" phenomenon which could in part explain why in a similar patient population texture features identified and/or cut-off values of prognostic significance differ from one study to another. Principal component analysis (PCA) is a technique for reducing the dimensionality of large datasets containing highly correlated variables, such as texture feature datasets derived from FDG PET images, increasing data interpretability whilst at the same time minimizing information loss by creating new uncorrelated variables that successively maximize variance. Here, we report on PCA of a texture feature dataset derived from 123 malignant melanoma lesions with a significant range in lesion size using the freely available LIFEx software. Results: Thirty-eight features were derived from all lesions. All features were standardized. The statistical assumptions for carrying out PCA analysis were met. Seven principal components with an eigenvalue > 1 were identified. Based on the "elbow sign" of the Scree plot, only the first five were retained. The contribution to the total variance of these components derived using Varimax rotation was, respectively, 30.6%, 23.6%, 16.1%, 7.4% and 4.1%. The components provided summarized information on the locoregional FDG distribution with an emphasis on high FDG uptake regions, contrast in FDG uptake values (steepness), tumour volume, locoregional FDG distribution with an emphasis on low FDG uptake regions and on the rapidity of changes in SUV intensity between different regions. Conclusions:PCA allowed to reduce the dataset of 38 features to a set of 5 uncorrelated new variables explaining approximately 82% of the total variance contained within the dataset. These principal components may prove more useful for multiple regression analysis considering the relatively low numbers of patients usually included in clinical trials on FDG PET texture analysis. Studies assessing the superior differential diagnostic, predictive or prognostic value of principal components derived using PCA as opposed to the initial texture features in clinical relevant settings are warranted.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.