Aim: To improve identification of peritoneal and distant metastases in locally advanced gastric cancer using [18F]FDG-PET radiomics. Methods: [18F]FDG-PET scans of 206 patients acquired in 16... Show moreAim: To improve identification of peritoneal and distant metastases in locally advanced gastric cancer using [18F]FDG-PET radiomics. Methods: [18F]FDG-PET scans of 206 patients acquired in 16 different Dutch hospitals in the prospective multicentre PLASTIC-study were analysed. Tumours were delineated and 105 radiomic features were extracted. Three classification models were developed to identify peritoneal and distant metastases (incidence: 21%): a model with clinical variables, a model with radiomic features, and a clinicoradiomic model, combining clinical variables and radiomic features. A least absolute shrinkage and selection operator (LASSO) regression classifier was trained and evaluated in a 100-times repeated random split, stratified for the presence of peritoneal and distant metastases. To exclude features with high mutual correlations, redundancy filtering of the Pearson correlation matrix was performed (r = 0.9). Model performances were expressed by the area under the receiver operating characteristic curve (AUC). In addition, subgroup analyses based on Lauren classification were performed. Results: None of the models could identify metastases with low AUCs of 0.59, 0.51, and 0.56, for the clinical, radiomic, and clinicoradiomic model, respectively. Subgroup analysis of intestinal and mixed-type tumours resulted in low AUCs of 0.67 and 0.60 for the clinical and radiomic models, and a moderate AUC of 0.71 in the clinicoradiomic model. Subgroup analysis of diffuse-type tumours did not improve the classification performance. Conclusion: Overall, [18F]FDG-PET-based radiomics did not contribute to the preoperative identification of peritoneal and distant metastases in patients with locally advanced gastric carcinoma. In intestinal and mixed-type tumours, the classification performance of the clinical model slightly improved with the addition of radiomic features, but this slight improvement does not outweigh the laborious radiomic analysis. Show less
Noortman, W.A.; Aide, N.; Vriens, D.; Arkes, L.S.; Slump, C.H.; Boellaard, R.; ... ; Geus-Oei, L.F. de 2023
Aim: To build and externally validate an [F-18]FDG PET radiomic model to predict overall survival in patients with head and neck squamous cell carcinoma (HNSCC).Methods: Two multicentre datasets of... Show moreAim: To build and externally validate an [F-18]FDG PET radiomic model to predict overall survival in patients with head and neck squamous cell carcinoma (HNSCC).Methods: Two multicentre datasets of patients with operable HNSCC treated with preoperative afatinib who underwent a baseline and evaluation [F-18]FDG PET/CT scan were included (EORTC: n = 20, Unicancer: n = 34). Tumours were delineated, and radiomic features were extracted. Each cohort served once as a training and once as an external validation set for the prediction of overall survival. Supervised feature selection was performed using variable hunting with variable importance, selecting the top two features. A Cox proportional hazards regression model using selected radiomic features and clinical characteristics was fitted on the training dataset and validated in the external validation set. Model performances are expressed by the concordance index (C-index).Results: In both models, the radiomic model surpassed the clinical model with validation C-indices of 0.69 and 0.79 vs. 0.60 and 0.67, respectively. The model that combined the radiomic features and clinical variables performed best, with validation C-indices of 0.71 and 0.82.Conclusion: Although assessed in two small but independent cohorts, an [F-18]FDG-PET radiomic signature based on the evaluation scan seems promising for the prediction of overall survival for HNSSC treated with preoperative afatinib. The robustness and clinical applicability of this radiomic signature should be assessed in a larger cohort. Show less
Hulst, H.J. van der; Vos, J.L.; Tissier, R.; Smit, L.A.; Martens, R.M.; Beets-Tan, R.G.H.; ... ; Castelijns, J.A. 2022
Simple Summary Immunotherapy may induce early treatment response in head and neck squamous cell carcinoma (HNSCC) for some patients. Routine imaging parameters fail to diagnose these responses;... Show moreSimple Summary Immunotherapy may induce early treatment response in head and neck squamous cell carcinoma (HNSCC) for some patients. Routine imaging parameters fail to diagnose these responses; however, magnetic resonance (MR) diffusion-weighted imaging (DWI) may be able to do so. This study sought to correlate DWI parameters with treatment response early after immunotherapy treatment in HNSCC. We analyzed 24 patients with advanced HNSCC with imaging before and after the immunotherapy. We found that rounder tumors that were smaller in diameter before treatment were more likely to respond. A decrease in skewness of the tumor after treatment compared to before treatment, as well as an overall low skewness post-treatment, were linked to better treatment response. Though this study was explorative in nature, these results are promising for the predictive use of MR-DWI in HNSCC treated with immunotherapy. Background: Neoadjuvant immune checkpoint blockade (ICB) prior to surgery may induce early pathological responses in head and neck squamous cell carcinoma (HNSCC) patients. Routine imaging parameters fail to diagnose these responses early on. Magnetic resonance (MR) diffusion-weighted imaging (DWI) has proven to be useful for detecting HNSCC tumor mass after (chemo)radiation therapy. METHODS: 32 patients with stage II-IV, resectable HNSCC, treated at a phase Ib/IIa IMCISION trial (NCT03003637), were retrospectively analyzed using MR-imaging before and after two doses of single agent nivolumab (anti-PD-1) (n = 6) or nivolumab with ipilimumab (anti-CTLA-4) ICB (n = 26). The primary tumors were delineated pre- and post-treatment. A total of 32 features were derived from the delineation and correlated with the tumor regression percentage in the surgical specimen. Results: MR-DWI data was available for 24 of 32 patients. Smaller baseline tumor diameter (p = 0.01-0.04) and higher sphericity (p = 0.03) were predictive of having a good pathological response to ICB. Post-treatment skewness and the change in skewness between MRIs were negatively correlated with the tumor's regression (p = 0.04, p = 0.02). Conclusion: Pre-treatment DWI tumor diameter and sphericity may be quantitative biomarkers for the prediction of an early pathological response to ICB. Furthermore, our data indicate that ADC skewness could be a marker for individual response evaluation. Show less
Weeda, Y.A.; Kalisvaart, G.M.; Velden, F.H.P. van; Gelderblom, H.; Molen, A.J. van der; Bovee, J.V.M.G.; ... ; Geus-Oei, L.F. de 2022
Gastrointestinal stromal tumors (GISTs) are rare mesenchymal neoplasms. Tyrosine kinase inhibitor (TKI) therapy is currently part of routine clinical practice for unresectable and metastatic... Show moreGastrointestinal stromal tumors (GISTs) are rare mesenchymal neoplasms. Tyrosine kinase inhibitor (TKI) therapy is currently part of routine clinical practice for unresectable and metastatic disease. It is important to assess the efficacy of TKI treatment at an early stage to optimize therapy strategies and eliminate futile ineffective treatment, side effects and unnecessary costs. This systematic review provides an overview of the imaging features obtained from contrast-enhanced (CE)-CT and 2-deoxy-2-[F-18]fluoro-D-glucose ([F-18]FDG) PET/CT to predict and monitor TKI treatment response in GIST patients. PubMed, Web of Science, the Cochrane Library and Embase were systematically screened. Articles were considered eligible if quantitative outcome measures (area under the curve (AUC), correlations, sensitivity, specificity, accuracy) were used to evaluate the efficacy of imaging features for predicting and monitoring treatment response to various TKI treatments. The methodological quality of all articles was assessed using the Quality Assessment of Diagnostic Accuracy Studies, v2 (QUADAS-2) tool and modified versions of the Radiomics Quality Score (RQS). A total of 90 articles were included, of which 66 articles used baseline [F-18]FDG-PET and CE-CT imaging features for response prediction. Generally, the presence of heterogeneous enhancement on baseline CE-CT imaging was considered predictive for high-risk GISTs, related to underlying neovascularization and necrosis of the tumor. The remaining articles discussed therapy monitoring. Clinically established imaging features, including changes in tumor size and density, were considered unfavorable monitoring criteria, leading to under- and overestimation of response. Furthermore, changes in glucose metabolism, as reflected by [F-18]FDG-PET imaging features, preceded changes in tumor size and were more strongly correlated with tumor response. Although CE-CT and [F-18]FDG-PET can aid in the prediction and monitoring in GIST patients, further research on cost-effectiveness is recommended. Show less
PET radiomics applied to oncology allow the measurement of intratumoral heterogeneity. This quantification can be affected by image protocols; hence, there is an increased interest in understanding... Show morePET radiomics applied to oncology allow the measurement of intratumoral heterogeneity. This quantification can be affected by image protocols; hence, there is an increased interest in understanding how radiomic expression on PET images is affected by different imaging conditions. To address that interest, this study explored how radiomic features are affected by changes in F-18-FDG uptake time, image reconstruction, lesion delineation, and radiomic binning settings. Methods: Ten non-small cell lung cancer patients underwent F-18-FDG PET on 2 consecutive days. On each day, scans were obtained at 60 and 90 min after injection and reconstructed following EARL version 1 and with point-spread-function resolution modeling (PSF-EARL2). Lesions were delineated with an SUV threshold of 4.0, with 40% of SUVmax, and with a contrast-based isocontour. PET image intensity was discretized with both a fixed bin width (FBW) and a fixed bin number before the calculation of the radiomic features. Repeatability of features was measured with the intraclass correlation coefficient, and the change in feature value over time was calculated as a function of its repeatability. Features were then classified into use-case scenarios based on their repeatability and susceptibility to tracer uptake time. Results: With PSF-EARL2 reconstruction, 40% of SUVmax lesion delineation, and FBW intensity discretization, most features (94%) were repeatable at both uptake times (intraclass correlation coefficient. 0.9), 35% being classified for dual-time-point use cases as being sensitive to changes in uptake time, 39% were classified for cross-sectional studies with an unclear dependency on time, 20% were classified for cross-sectional use while being robust to uptake time changes, and 6% were discarded for poor repeatability. EARL version 1 images had 1 fewer repeatable feature (neighborhood gray-level different matrix coarseness) than PSF- EARL2; the contrast-based delineation had the poorest repeatability of the delineation methods, with 45% of features being discarded; and fixed bin number resulted in lower repeatability than FBW ( 45% and 6% of features were discarded, respectively). Conclusion: Repeatability was maximized with PSF-EARL2 reconstruction, lesion delineation at 40% of SUVmax, and FBW intensity discretization. On the basis of their susceptibility to uptake time, radiomic features were classified into specific non-small cell lung cancer PET radiomics use cases. Show less
Ramos, L.A.; Os, H. van; Hilbert, A.; Olabarriaga, S.D.; Lugt, A. van der; Roos, Y.B.W.E.M.; ... ; Marquering, H.A. 2022
Background: Accurate prediction of clinical outcome is of utmost importance for choices regarding the endovascular treatment (EVT) of acute stroke. Recent studies on the prediction modeling for... Show moreBackground: Accurate prediction of clinical outcome is of utmost importance for choices regarding the endovascular treatment (EVT) of acute stroke. Recent studies on the prediction modeling for stroke focused mostly on clinical characteristics and radiological scores available at baseline. Radiological images are composed of millions of voxels, and a lot of information can be lost when representing this information by a single value. Therefore, in this study we aimed at developing prediction models that take into account the whole imaging data combined with clinical data available at baseline. Methods: We included 3,279 patients from the MR CLEAN Registry; a prospective, observational, multicenter registry of patients with ischemic stroke treated with EVT. We developed two approaches to combine the imaging data with the clinical data. The first approach was based on radiomics features, extracted from 70 atlas regions combined with the clinical data to train machine learning models. For the second approach, we trained 3D deep learning models using the whole images and the clinical data. Models trained with the clinical data only were compared with models trained with the combination of clinical and image data. Finally, we explored feature importance plots for the best models and identified many known variables and image features/brain regions that were relevant in the model decision process. Results: From 3,279 patients included, 1,241 (37%) patients had a good functional outcome [modified Rankin Scale (mRS) <= 2] and 1,954 (60%) patients had good reperfusion [modified Thrombolysis in Cerebral Infarction (eTICI) >= 2b]. There was no significant improvement by combining the image data to the clinical data for mRS prediction [mean area under the receiver operating characteristic (ROC) curve (AUC) of 0.81 vs. 0.80] above using the clinical data only, regardless of the approach used. Regarding predicting reperfusion, there was a significant improvement when image and clinical features were combined (mean AUC of 0.54 vs. 0.61), with the highest AUC obtained by the deep learning approach. Conclusions: The combination of radiomics and deep learning image features with clinical data significantly improved the prediction of good reperfusion. The visualization of prediction feature importance showed both known and novel clinical and imaging features with predictive values. Show less
Background: Accuracy and precision assessment in radiomic features is important for the determination of their potential to characterize cancer lesions. In this regard, simulation of different... Show moreBackground: Accuracy and precision assessment in radiomic features is important for the determination of their potential to characterize cancer lesions. In this regard, simulation of different imaging conditions using specialized phantoms is increasingly being investigated. In this study, the design and evaluation of a modular multimodality imaging phantom to simulate heterogeneous uptake and enhancement patterns for radiomics quantification in hybrid imaging is presented. Methods: A modular multimodality imaging phantom was constructed that could simulate different patterns of heterogeneous uptake and enhancement patterns in positron emission tomography (PET), single-photon emission computed tomography (SPECT), computed tomography (CT), and magnetic resonance (MR) imaging. The phantom was designed to be used as an insert in the standard NEMA-NU2 IEC body phantom casing. The entire phantom insert is composed of three segments, each containing three separately fillable compartments. The fillable compartments between segments had different sizes in order to simulate heterogeneous patterns at different spatial scales. The compartments were separately filled with different ratios of Tc-99m-pertechnetate, F-18-fluorodeoxyglucose ([F-18]FDG), iodine- and gadolinium-based contrast agents for SPECT, PET, CT, and T-1-weighted MR imaging respectively. Image acquisition was performed using standard oncological protocols on all modalities and repeated five times for repeatability assessment. A total of 93 radiomic features were calculated. Variability was assessed by determining the coefficient of quartile variation (CQV) of the features. Comparison of feature repeatability at different modalities and spatial scales was performed using Kruskal-Wallis-, Mann-Whitney U-, one-way ANOVA- and independent t-tests. Results: Heterogeneous uptake and enhancement could be simulated on all four imaging modalities. Radiomic features in SPECT were significantly less stable than in all other modalities. Features in PET were significantly less stable than in MR and CT. A total of 20 features, particularly in the gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) class, were found to be relatively stable in all four modalities for all three spatial scales of heterogeneous patterns (with CQV < 10%). Conclusion: The phantom was suitable for simulating heterogeneous uptake and enhancement patterns in [F-18]FDG-PET, Tc-99m-SPECT, CT, and T-1-weighted MR images. The results of this work indicate that the phantom might be useful for the further development and optimization of imaging protocols for radiomic quantification in hybrid imaging modalities. Show less
Noortman, W.A.; Vriens, D.; Mooij, C.D.Y.; Slump, C.H.; Aarntzen, E.H.; Berkel, A. van; ... ; Velden, F.H.P. van 2021
Background: Central necrosis can be detected on [F-18]FDG PET/CT as a region with little to no tracer uptake. Currently, there is no consensus regarding the inclusion of regions of central necrosis... Show moreBackground: Central necrosis can be detected on [F-18]FDG PET/CT as a region with little to no tracer uptake. Currently, there is no consensus regarding the inclusion of regions of central necrosis during volume of interest (VOI) delineation for radiomic analysis. The aim of this study was to assess how central necrosis affects radiomic analysis in PET. Methods: Forty-three patients, either with non-small cell lung carcinomas (NSCLC, n = 12) or with pheochromocytomas or paragangliomas (PPGL, n = 31), were included retrospectively. VOIs were delineated with and without central necrosis. From all VOIs, 105 radiomic features were extracted. Differences in radiomic features between delineation methods were assessed using a paired t-test with Benjamini-Hochberg multiple testing correction. In the PPGL cohort, performances of the radiomic models to predict the noradrenergic biochemical profile were assessed by comparing the areas under the receiver operating characteristic curve (AUC) for both delineation methods. Results: At least 65% of the features showed significant differences between VOIvital-tumour and VOIgross-tumour (65%, 79% and 82% for the NSCLC, PPGL and combined cohort, respectively). The AUCs of the radiomic models were not significantly different between delineation methods. Conclusion: In both tumour types, almost two-third of the features were affected, demonstrating that the impact of whether or not to include central necrosis in the VOI on the radiomic feature values is significant. Nevertheless, predictive performances of both delineation methods were comparable. We recommend that radiomic studies should report whether or not central necrosis was included during delineation. Show less
Biomarkers of aging are urgently needed to identify individuals at high risk of developing age-associated disease or disability. Growing evidence from population-based studies points to whole-body... Show moreBiomarkers of aging are urgently needed to identify individuals at high risk of developing age-associated disease or disability. Growing evidence from population-based studies points to whole-body magnetic resonance imaging's (MRI) enormous potential for quantifying subclinical disease burden and for assessing changes that occur with aging in all organ systems. The Aging Imageomics Study aims to identify biomarkers of human aging by analyzing imaging, biopsychosocial, cardiovascular, metabolomic, lipidomic, and microbiome variables. This study recruited 1030 participants aged >= 50 years (mean 67, range 50-96 years) that underwent structural and functional MRI to evaluate the brain, large blood vessels, heart, abdominal organs, fat, spine, musculoskeletal system and ultrasonography to assess carotid intima-media thickness and plaques. Patients were notified of incidental findings detected by a certified radiologist when necessary. Extensive data were also collected on anthropometrics, demographics, health history, neuropsychology, employment, income, family status, exposure to air pollution and cardiovascular status. In addition, several types of samples were gathered to allow for microbiome, metabolomic and lipidomic profiling. Using big data techniques to analyze all the data points from biological phenotyping together with health records and lifestyle measures, we aim to cultivate a deeper understanding about various biological factors (and combinations thereof) that underlie healthy and unhealthy aging. Show less
Cardiovascular computed tomography (CCT) has undergone rapid maturation over the last decade and is now of proven clinical utility in the diagnosis and management of coronary artery disease, in... Show moreCardiovascular computed tomography (CCT) has undergone rapid maturation over the last decade and is now of proven clinical utility in the diagnosis and management of coronary artery disease, in guiding structural heart disease intervention, and in the diagnosis and treatment of congenital heart disease. The next decade will undoubtedly witness further advances in hardware and advanced analytics that will potentially see an increasingly core role for CCT at the center of clinical cardiovascular practice. In coronary artery disease assessment this may be via improved hemodynamic adjudication, and shear stress analysis using computational flow dynamics, more accurate and robust plaque characterization with spectral or photon- counting CT, or advanced quantification of CT data via artificial intelligence, machine learning, and radiomics. In structural heart disease, CCT is already pivotal to procedural planning with adjudication of gradients before and following intervention, whereas in congenital heart disease CCT is already used to support clinical decision making from neonates to adults, often with minimal radiation dose. In both these areas the role of computational flow dynamics, advanced tissue printing, and image modelling has the potential to revolutionize the way these complex conditions are managed, and CCT is likely to become an increasingly critical enabler across the whole advancing field of cardiovascular medicine. (c) 2019 by the American College of Cardiology Foundation. Show less