Person | TU Delft Repository

Floris H.P. van Velden

View Pure Profile

Authored

6 records found

Design and evaluation of a modular multimodality imaging phantom to simulate heterogeneous uptake and enhancement patterns for radiomic quantification in hybrid imaging

A feasibility study

Journal article - Gijsbert M. Kalisvaart, Floris H.P. van Velden, D.R. Schaart, D.R. Schaart, Willem Grootjans, Irene Hernández-Girón, Karin M. Meijer, Laura M.H. Ghesquiere-Dierickx, Laura M.H. Ghesquiere-Dierickx, Laura M.H. Ghesquiere-Dierickx, Wyger M. Brink, A. Webb, Lioe Fee de Geus-Oei, Lioe Fee de Geus-Oei, Cornelis H. Slump, D.V. Kuznetsov

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 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 99mTc-pertechnetate, 18F-fluorodeoxyglucose ([18F]FDG), iodine- and gadolinium-based contrast agents for SPECT, PET, CT, and T1-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 [18F]FDG-PET, 99mTc-SPECT, CT, and T1-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.@en

Baseline and early digital [ 18 F]FDG PET/CT and multiparametric MRI contain promising features to predict response to neoadjuvant therapy in locally advanced rectal cancer patients

A pilot study

Journal article - Floris A. Vuijk, Shirin Feshtali Shahbazi, W.A. Noortman, W.A. Noortman, Floris H.P. van Velden, Petra Dibbets-Schneider, A. Marinelli, H. Putter, Alexander L. Vahrmeijer, L.F. de Geus-Oei, L.F. de Geus-Oei, L.F. de Geus-Oei

OBJECTIVE: In this pilot study, we investigated the feasibility of response prediction using digital [ 18 F]FDG PET/computed tomography (CT) and multiparametric MRI before, during, and after neoadjuvant chemoradiation therapy in locally advanced rectal cancer (LARC) patients and aimed to select the most promising imaging modalities and timepoints for further investigation in a larger trial. METHODS: Rectal cancer patients scheduled to undergo neoadjuvant chemoradiation therapy were prospectively included in this trial, and underwent multiparametric MRI and [ 18 F]FDG PET/CT before, 2 weeks into, and 6-8 weeks after chemoradiation therapy. Two groups were created based on pathological tumor regression grade, that is, good responders (TRG1-2) and poor responders (TRG3-5). Using binary logistic regression analysis with a cutoff value of P ≤ 0.2, promising predictive features for response were selected. RESULTS: Nineteen patients were included. Of these, 5 were good responders, and 14 were poor responders. Patient characteristics of these groups were similar at baseline. Fifty-seven features were extracted, of which 13 were found to be promising predictors of response. Baseline [T2: volume, diffusion-weighted imaging (DWI): apparent diffusion coefficient (ADC) mean, DWI: difference entropy], early response (T2: volume change, DWI: ADC mean change) and end-of-treatment presurgical evaluation MRI (T2: gray level nonuniformity, DWI: inverse difference normalized, DWI: gray level nonuniformity normalized), as well as baseline (metabolic tumor volume, total lesion glycolysis) and early response PET/CT (Δ maximum standardized uptake value, Δ peak standardized uptake value corrected for lean body mass), were promising features. CONCLUSION: Both multiparametric MRI and [ 18 F]FDG PET/CT contain promising imaging features to predict response to neoadjuvant chemoradiotherapy in LARC patients. A future larger trial should investigate baseline, early response, and end-of-treatment presurgical evaluation MRI and baseline and early response PET/CT.@en

Investigating the potential added value of [ 18 F]FDG-PET/CT in long COVID patients with persistent symptoms

A proof of concept study

Journal article - Linda L. Chen, Linda L. Chen, Linda L. Chen, Linda L. Chen, Alina van de Burgt, Alina van de Burgt, Frits Smit, Frits Smit, Rowena S. Audhoe, Sandra M. de Boer, Floris H.P. van Velden, L.F. de Geus-Oei, L.F. de Geus-Oei, L.F. de Geus-Oei

Objective Since the end of 2019, the coronavirus disease 2019 (COVID-19) virus has infected millions of people, of whom a significant group suffers from sequelae from COVID-19, termed long COVID. As more and more patients emerge with long COVID who have symptoms of fatigue, myalg ...

The influence of the exclusion of central necrosis on [<sup>18</sup>F]FDG PET radiomic analysis

Journal article - Wyanne A. Noortman, Wyanne A. Noortman, Dennis Vriens, Floris H.P. van Velden, C.D.Y. Mooij, C.D.Y. Mooij, Cornelis H. Slump, Erik H. Aarntzen, Anouk van Berkel, Henri J.L.M. Timmers, Johan Bussink, Tineke W.H. Meijer, Lioe Fee de Geus-Oei, Lioe Fee de Geus-Oei

Background: Central necrosis can be detected on [18F]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 ...

Dynamic rubidium-82 PET/CT as a novel tool for quantifying hemodynamic differences in renal blood flow using a one-tissue compartment model

Journal article - Alina van de Burgt, Alina van de Burgt, Floris H.P. van Velden, Koen Kwakkenbos, Koen Kwakkenbos, Frits Smit, Frits Smit, L.F. de Geus-Oei, L.F. de Geus-Oei, L.F. de Geus-Oei, Ilona A. Dekkers

Purpose: Assessing renal perfusion in-vivo is challenging and quantitative information regarding renal hemodynamics is hardly incorporated in medical decision-making while abnormal renal hemodynamics might play a crucial role in the onset and progression of renal disease. Combining physiological stimuli with rubidium-82 positron emission tomography/computed tomography (82Rb PET/CT) offers opportunities to test the kidney perfusion under various conditions. The aim of this study is: (1) to investigate the application of a one-tissue compartment model for measuring renal hemodynamics with dynamic 82Rb PET/CT imaging, and (2) to evaluate whether dynamic PET/CT is sensitive to detect differences in renal hemodynamics in stress conditions compared to resting state. Methods: A one-tissue compartment model for the kidney was applied to cardiac 82Rb PET/CT scans that were obtained for ischemia detection as part of clinical care. Retrospective data, collected from 17 patients undergoing dynamic myocardial 82Rb PET/CT imaging in rest, were used to evaluate various CT-based volumes of interest (VOIs) of the kidney. Subsequently, retrospective data, collected from 10 patients (five impaired kidney functions and five controls) undergoing dynamic myocardial 82Rb PET/CT imaging, were used to evaluate image-derived input functions (IDIFs), PET-based VOIs of the kidney, extraction fractions, and whether dynamic 82Rb PET/CT can measure renal hemodynamics differences using the renal blood flow (RBF) values in rest and after exposure to adenosine pharmacological stress. Results: The delivery rate (K1) values showed no significant (p = 0.14) difference between the mean standard deviation (SD) K1 values using one CT-based VOI and the use of two, three, and four CT-based VOIs, respectively 2.01(0.32), 1.90(0.40), 1.93(0.39), and 1.94(0.40) mL/min/mL. The ratio between RBF in rest and RBF in pharmacological stress for the controls were overall significantly lower compared to the impaired kidney function group for both PET-based delineation methods (region growing and iso-contouring), with the smallest median interquartile range (IQR) of 0.40(0.28–0.66) and 0.96(0.62–1.15), respectively (p < 0.05). The K1 of the impaired kidney function group were close to 1.0 mL/min/mL. Conclusions: This study demonstrated that obtaining renal K1 and RBF values using 82Rb PET/CT was feasible using a one-tissue compartment model. Applying iso-contouring as the PET-based VOI of the kidney and using AA as an IDIF is suggested for consideration in further studies. Dynamic 82Rb PET/CT imaging showed significant differences in renal hemodynamics in rest compared to when exposed to adenosine. This indicates that dynamic 82Rb PET/CT has potential to detect differences in renal hemodynamics in stress conditions compared to the resting state, and might be useful as a novel diagnostic tool for assessing renal perfusion.@en

Dynamic rubidium-82 PET/CT as a novel tool for quantifying hemodynamic differences in renal blood flow using a one-tissue compartment model

Contributed

3 records found

Artificial intelligence in breast-specific gamma imaging

Exploring the possibilities of automation of breast cancer detection and classification

Master thesis - J.R.J. Willemse, Lenka Pereira Arias-Bouda, W. Grootjans, Floris H.P. van Velden

Introduction Breast cancer is the most frequently diagnosed type of cancer in women in 2020. Treatment and prognosis of breast cancer is highly dependent on early and accurate diagnosis. In recent years, many studies have evaluated the use of artificial intelligence for the detection of breast cancer in mammographic images. Another imaging modality, breast-specific gamma imaging (BSGI), or molecular breast imaging, has not yet been subject to AI algorithms to detect breast cancer. In this paper, we aim to develop and evaluate convolutional neural networks (CNNs) that can detect malignancies in breast-specific gamma imaging, and evaluate the efficacy of different machine learning classifiers to classify breast tumors based on estrogen receptor (ER) status, progesterone receptor (PR) status and human epidermal growth factor receptor 2 (HER2-neu) status. Methods Three CNNs were created and trained and tested on a total of 3,503 BSGI images. The models varied in complexity in terms of convolutional layers and filter sizes. A semi quantitative lesion segmentation was created based on adaptive thresholding and shape and location analysis. Radiomics features were extracted, and univariate feature selection was applied to disregard redundant features. Different machine learning classifiers, which are widely used in literature for binary classification problems, were evaluated. Results In detecting malignancies in a dataset containing clean breasts and breast with malignant lesions, the best performing network reached an area under the receiving operating characteristic (AUROC) of 0.93, while an AUROC of 0.88 was achieved when using the same networks in the classification of malignant versus benign lesions. The best performing machine learning classifiers were the linear discriminating analysis (LDA) classifier for ER and PR status, reaching accuracies of 75% in both receptors. In Her2-neu prediction using machine learning, the best accuracy of 69% was achieved by the RF classifier. Discussion & conclusions Based on the results presented in this paper, CNNs can accurately detect malignancies in BSGI images, and discriminate malignancies from benign lesions to a certain extent. The combination of radiomics and machine learning, however, is in its current implementation not accurate enough to predict the ER, PR and Her2-neu status in BSGI images. Future research, however, could focus on using a combination of imaging modalities, such as BSGI, MRI and mammography to improve the predictive accuracy of machine learning.

Explainable artificial intelligence in nuclear medicine

Development and evaluation of a medical-based explainable artificial intelligence approach to predict progression free survival in patients with metastatic colorectal cancer using pre-treatment 18F-FDG PET

Master thesis - B.M. de Vries, J.J. van den Dobbelsteen, Ronald Boellaard, Willemien Menke, Floris H.P. van Velden

Purpose: 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) is used in the diagnostic process and management of patients with metastatic colorectal cancer (mCRC). Also, 18F-FDG PET radiomic features have been found to hold prognostic value for clinical outcome in mCRC. However, no prognostic model has yet been developed to predict clinical outcome in mCRC using 18F-FDG PET images. Computer-aided pattern recognition can be helpful in this process but needs to be validated. The aim of this work was to develop and evaluate a medical-based explainable artificial intelligence (XAI) framework for discriminating between dichotomous progression free survival (PFS) in patients with mCRC undergoing anti-epidermal growth factor receptor (anti-EGFR) monoclonal antibody (mAb) treatment using pre-treatment 18F-FDG PET images. Methods: We conducted an analysis of 18F-FDG PET images, expressed in standardized uptake values (SUV), obtained from 80 patients with mCRC who were eligible for third-line treatment with an anti-EGFR mAb as part of the IMPACT study. A coronal 2.5D Convolutional Neural Network (CNN) was built to capture features of the 18F-FDG PET images specific for the two patient groups and a medical-based XAI framework was developed to extract the 18F-FDG PET features used by the CNN. The images were randomly divided into a training and a validation set (10-fold cross-validation). Performance of the CNN was evaluated based on the average area under the curve (AUC), accuracy, sensitivity and specificity from the cross-validation. A statistical analysis was performed to assess the predictive value of the 18F-FDG PET features extracted by the XAI framework. Results: The coronal 2.5D-CNN was able to discriminate between dichotomous PFS (median PFS: 152 days) in patients with mCRC undergoing anti-EGFR mAb treatment using pre-treatment 18F-FDG PET images, with an average AUC of 0.95 ± 0.11 (SD), accuracy of 94% ± 12, sensitivity of 91% ± 21 and specificity of 94% ± 21 %. The XAI framework showed that especially low 18F-FDG PET uptake volume features hold significant differences between the two patient groups. Conclusion: The coronal 2.5D-CNN showed good performance to predict dichotomous PFS from pre-treatment 18F-FDG PET images in patients with mCRC undergoing anti-EGFR mAb treatment. Low 18F-FDG PET uptake volume features seem to have potential as IB in this patient cohort, but further validation is required.

Automatic segmentation of the spinal joints and intervertebral disks on low-dose computed tomography: an atlas-based approach

Master thesis - W.R.P. van der Heijden, Ronald Boellaard, C.J. van der Laken, Floris H.P. van Velden, J.P.H.J. Rutges

Introduction: Spondyloarthritis (SpA) belongs to the chronic inflammatory rheumatic diseases, and primarily affects the axial skeleton. Quantitative 18F-NaF PET/CT is a new imaging approach that shows promise for accurate diagnosis and treatment assessment. Manual segmentation of low-dose computed tomography (LDCT) for quantitative feature extraction is time-consuming and subjective, and can be replaced by automatic methods. This study aims to develop and validate an automatic algorithm for the segmentation of the spinal joints and intervertebral disks (IVD’s) on LDCT using two different approaches. Methods: Two methods for spinal structure segmentation were developed and compared. Both methods used segmentations of bony structures obtained from the TotalSegmentator algorithm. The first method employed morphological dilation and erosion operations to localise the joints and IVD’s, while the second method used a multi-atlas-based method approach with partial atlases and corresponding manually segmented labelmaps. The performance of the methods was assessed on ten manually segmented LDCT’s using sensitivity, and maximum and average Hausdorff distance (HD) for IVD’s and the sacroiliac joints (SIJ) and mean error distance for the smaller joints. The reproducibility of the methods was evaluated using a set of 20 LDCT test-retest images. Results: The atlas-based method achieved significantly better maximum HD (8.45 (1.80) vs. 9.64 (5.83) (p = 0.002)) and sensitivity (0.79 (0.22) vs. 0.61 (0.30) (p < 0.001)) for all IVD’s combined compared to the morphological method. The atlas-based method also outperformed the morphological method for the facet joints, costovertebral joints and costotransverse joints with a mean error distance of 4.71 mm (2.72) vs 6.90 mm (4.80) (p < 0.001). For the thoracic IVD’s the morphological method showed significantly better average HD (1.48 (1.03) vs. 1.72 (0.53) (p = 0.018)) and maximum HD (6.97 (3.36) vs. 8.22 (1.66) (p < 0.001)) than the atlas-based method. In the reproducibility assessment on the test-retest scans, the atlas-based method outperformed the morphological method for all metrics and structures, with average HD’s well below the voxel resolution (< 2 mm). Conclusion: We present the first methods for automatic segmentation of the spinal structures on LDCT. The atlas-based method seems to be the most suitable algorithm, achieving average HD’s below the voxel size, and maximum errors below one centimetre. However, it is dependent on accurate segmentation by the TotalSegmentator algorithm. Further research is warranted to investigate the influence of the segmentation results on the extraction of quantitative PET information.