• Home
  • Bas van der Velden
Bas van der Velden

Bas van der Velden
Wageningen Food Safety Research

PhD

About

56
Publications
6,435
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,557
Citations
Introduction
Head of Data Science at Wageningen Food Safety Research. Deep learning expert with a focus on eXplainable Artificial Intelligence (XAI) and 10+ years of hands-on experience.
Additional affiliations
January 2017 - present
University Medical Center Utrecht
Position
  • PhD Student
February 2016 - May 2016
Memorial Sloan Kettering Cancer Center
Position
  • Researcher
January 2013 - December 2017
University Medical Center Utrecht
Position
  • PhD Student
Education
January 2013 - December 2017
University Medical Center Utrecht
Field of study
  • Medical Imaging
September 2005 - November 2012
Eindhoven University of Technology
Field of study
  • Medical Engineering

Publications

Publications (56)
Article
Full-text available
Accurate prediction of response to neoadjuvant chemotherapy (NAC) can help tailor treatment to individual patients’ needs. Little is known about the combination of liquid biopsies and computer extracted features from multiparametric magnetic resonance imaging (MRI) for the prediction of NAC response in breast cancer. Here, we report on a prospectiv...
Article
Background Automated identification of quantitative breast parenchymal enhancement features on dynamic contrast-enhanced (DCE) MRI scans could provide added value in assessment of breast cancer risk in women with extremely dense breasts. Purpose To automatically identify quantitative properties of the breast parenchyma on baseline DCE MRI scans and...
Article
Background Several single-center studies found that high contralateral parenchymal enhancement (CPE) at breast MRI was associated with improved long-term survival in patients with estrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative breast cancer. Due to varying sample sizes, population characteristics, and f...
Article
Full-text available
Background: While several methods have been proposed for automated assessment of breast-cancer response to neoadjuvant chemotherapy on breast MRI, limited information is available about their performance across multiple institutions. Purpose: To assess the value and robustness of deep learning-derived volumes of locally advanced breast cancer (L...
Article
Full-text available
Objectives: Computer-aided triaging (CAT) and computer-aided diagnosis (CAD) of screening breast magnetic resonance imaging have shown potential to reduce the workload of radiologists in the context of dismissing normal breast scans and dismissing benign disease in women with extremely dense breasts. The aim of this study was to validate the poten...
Chapter
Explainable artificial intelligence (XAI) is increasingly used to analyze the behavior of neural networks. Concept activation uses human-interpretable concepts to explain neural network behavior. This study aimed at assessing the feasibility of regression concept activation to explain detection and classification of multi-modal volumetric data.Proo...
Preprint
Full-text available
Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. He...
Preprint
Full-text available
Explainable artificial intelligence (XAI) is increasingly used to analyze the behavior of neural networks. Concept activation uses human-interpretable concepts to explain neural network behavior. This study aimed at assessing the feasibility of regression concept activation to explain detection and classification of multi-modal volumetric data. Pro...
Article
Full-text available
Purpose Although adjuvant systemic therapy (AST) helps increase breast cancer-specific survival (BCSS), there is a growing concern for overtreatment. By estimating the expected BCSS of AST using PREDICT, this study aims to quantify the number of patients treated with AST without benefit to provide estimates of overtreatment. Methods Data of all no...
Article
With an increase in deep learning-based methods, the call for explainability of such methods grows, especially in high-stakes decision making areas such as medical image analysis. This survey presents an overview of eXplainable Artificial Intelligence (XAI) used in deep learning-based medical image analysis. A framework of XAI criteria is introduce...
Chapter
This paper assesses whether using clinical characteristics in addition to imaging can improve automated segmentation of kidney cancer on contrast-enhanced computed tomography (CT). A total of 300 kidney cancer patients with contrast-enhanced CT scans and clinical characteristics were included. A baseline segmentation of the kidney cancer was perfor...
Preprint
Full-text available
Purpose: Although adjuvant systemic therapy (AST) helps increase breast cancer-specific survival (BCSS), there is a growing concern for overtreatment. By estimating the expected BCSS of AST using PREDICT, this study aims to quantify the number of patients treated with AST without benefit to provide estimates of overtreatment. Methods: Data of all n...
Article
Full-text available
Purpose To assess whether contralateral parenchymal enhancement (CPE) on MRI is associated with gene expression pathways in ER+/HER2-breast cancer, and if so, whether such pathways are related to survival. Methods Preoperative breast MRIs were analyzed of early ER+/HER2-breast cancer patients eligible for breast-conserving surgery included in a pr...
Article
Full-text available
Purpose: We aimed to evaluate changes in dynamic contrast-enhanced (DCE) and diffusion-weighted (DW)-MRI acquired before and after single-dose ablative neoadjuvant partial breast irradiation (NA-PBI) and to explore the relation between semi-quantitative MRI parameters and radiologic and pathologic responses. Methods: We analyzed 3.0T DCE and DW-MRI...
Article
Background Supplemental screening with MRI has proved beneficial in women with extremely dense breasts. Most MRI examinations show normal anatomic and physiologic variation that may not require radiologic review. Thus, ways to triage these normal MRI examinations to reduce radiologist workload are needed. Purpose To determine the feasibility of an...
Preprint
Full-text available
This paper assesses whether using clinical characteristics in addition to imaging can improve automated segmentation of kidney cancer on contrast-enhanced computed tomography (CT). A total of 300 kidney cancer patients with contrast-enhanced CT scans and clinical characteristics were included. A baseline segmentation of the kidney cancer was perfor...
Preprint
Full-text available
Cerebral microbleeds are small, dark, round lesions that can be visualised on T2*-weighted MRI or other sequences sensitive to susceptibility effects. In this work, we propose a multi-stage approach to both microbleed detection and segmentation. First, possible microbleed locations are detected with a Mask R-CNN technique. Second, at each possible...
Preprint
Full-text available
Lacunes of presumed vascular origin are fluid-filled cavities of between 3 - 15 mm in diameter, visible on T1 and FLAIR brain MRI. Quantification of lacunes relies on manual annotation or semi-automatic / interactive approaches; and almost no automatic methods exist for this task. In this work, we present a two-stage approach to segment lacunes of...
Preprint
Full-text available
With an increase in deep learning-based methods, the call for explainability of such methods grows, especially in high-stakes decision making areas such as medical image analysis. This survey presents an overview of eXplainable Artificial Intelligence (XAI) used in deep learning-based medical image analysis. A framework of XAI criteria is introduce...
Article
Full-text available
Objective To investigate whether BIRADS MRI characteristics before or during neoadjuvant endocrine therapy (NET) are associated with the preoperative endocrine prognostic index (PEPI) in ER+/HER2- breast cancer patients. Methods This retrospective observational cohort study included 35 ER+/HER2- patients with 38 tumors (3 bilateral cases) treated...
Article
Objectives: Incidental MR-detected breast lesions (ie, additional lesions to the index cancer) pose challenges in the preoperative workup of patients with early breast cancer. We pursue computer-assisted triaging of magnetic resonance imaging (MRI)-guided breast biopsy of additional lesions at high specificity. Materials and methods: We investig...
Preprint
Full-text available
Breast density, which is the ratio between fibroglandular tissue (FGT) and total breast volume, can be assessed qualitatively by radiologists and quantitatively by computer algorithms. These algorithms often rely on segmentation of breast and FGT volume. In this study, we propose a method to directly assess breast density on MRI, and provide interp...
Article
Full-text available
To purpose of this paper was to assess the feasibility of volumetric breast density estimations on MRI without segmentations accompanied with an explainability step. A total of 615 patients with breast cancer were included for volumetric breast density estimation. A 3-dimensional regression convolutional neural network (CNN) was used to estimate th...
Article
Full-text available
Objectives To investigate whether contralateral parenchymal enhancement (CPE) on MRI during neoadjuvant endocrine therapy (NET) is associated with the preoperative endocrine prognostic index (PEPI) of ER+/HER2− breast cancer.Methods This retrospective observational cohort study included 40 unilateral ER+/HER2− breast cancer patients treated with NE...
Article
Full-text available
Background Differences in imaging parameters influence computer‐extracted parenchymal enhancement measures from breast MRI. Purpose To investigate the effect of differences in dynamic contrast‐enhanced MRI acquisition parameter settings on quantitative parenchymal enhancement of the breast, and to evaluate harmonization of contrast‐enhancement val...
Article
Background Better understanding of the molecular biology associated with MRI phenotypes may aid in the diagnosis and treatment of breast cancer. Purpose To discover the associations between MRI phenotypes of breast cancer and their underlying molecular biology derived from gene expression data. Materials and Methods This is a secondary analysis of...
Article
Full-text available
Background: Previous studies have shown discrepancies between index and synchronous breast cancer in histology and molecular phenotype. It is yet unknown whether this observation also applies to the MRI phenotype. Purpose: To investigate whether the appearance of breast cancer on MRI (i.e. phenotype) is different from that of additional breast c...
Article
Full-text available
Purpose: To retrospectively explore the relation between parenchymal enhancement of the healthy contralateral breast on dynamic contrast-enhanced magnetic resonance imaging (MRI) and genomic tests for estrogen receptor (ER)-pathway activity in patients with ER-positive/HER2-negative cancer. Methods: A subset of 227 consecutively included patient...
Conference Paper
Response of breast cancer to neoadjuvant chemotherapy (NAC) can be monitored using the change in visible tumor on magnetic resonance imaging (MRI). In our current workflow, seed points are manually placed in areas of enhancement likely to contain cancer. A constrained volume growing method uses these manually placed seed points as input and generat...
Preprint
Full-text available
Response of breast cancer to neoadjuvant chemotherapy (NAC) can be monitored using the change in visible tumor on magnetic resonance imaging (MRI). In our current workflow, seed points are manually placed in areas of enhancement likely to contain cancer. A constrained volume growing method uses these manually placed seed points as input and generat...
Preprint
Full-text available
Functional behavior of breast cancer - representing underlying biology - can be analyzed using MRI. The most widely used breast MR imaging protocol is dynamic contrast-enhanced T1-weighted imaging. The cancer enhances on dynamic contrast-enhanced MR imaging because the contrast agent leaks from the leaky vessels into the interstitial space. The con...
Article
Full-text available
Objectives: To assess whether contralateral parenchymal enhancement reproduces as an independent biomarker for patient survival in an independent patient cohort from a different cancer institution. Methods: This is a HIPAA-compliant IRB approved retrospective study. Patients with ER-positive/HER2-negative operable invasive ductal carcinoma and p...
Article
There is growing interest in minimally invasive breast cancer therapy. Eligibility of patients is, however, dependent on several factors related to the tumor and treatment technology. The aim of this study is to assess the proportion of patients eligible for minimally invasive breast cancer therapy for different safety and treatment margins based o...
Article
p> Purpose: To determine whether markers of healthy breast stroma are able to select a subgroup of patients at low risk of death or metastasis from patients considered at high risk according to routine markers of the tumor. Experimental Design: Patients with ER-positive/HER2-negative breast cancer were consecutively included for retrospective anal...
Article
Full-text available
We present a radiomics model to discriminate between patients at low risk and those at high risk of treatment failure at long-term follow-up based on eigentumors: principal components computed from volumes encompassing tumors in washin and washout images of pre-treatment dynamic contrast-enhanced (DCE-) MR images. Eigentumors were computed from the...
Preprint
Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is...
Conference Paper
Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks. A single CNN is...
Article
Objectives: Ductal carcinoma in situ (DCIS) is a risk factor for incomplete resection of breast cancer. Especially, extensive DCIS (E-DCIS) or extensive intraductal component often results in positive resection margins. Detecting DCIS around breast cancer before treatment may therefore alter surgery. The purpose of this study was to develop a pred...
Conference Paper
Introduction Molecular assays such as the 70-gene signature are increasingly used as prognostic indicators to select chemotherapy in individual patients. These assays are typically derived from postoperative excision specimens and require several weeks to complete. Earlier assessment of the results of such assays could open up new therapeutic optio...
Article
Full-text available
Finger tracking has the potential to expand haptic research and applications, as eye tracking has done in vision research. In research applications, it is desirable to know the bias and variance associated with a finger-tracking method. However, assessing the bias and variance of a deterministic method is not straightforward. Multiple measurements...
Article
Purpose To retrospectively investigate whether parenchymal enhancement in dynamic contrast material–enhanced magnetic resonance (MR) imaging of the contralateral breast in patients with unilateral invasive breast cancer is associated with therapy outcome. Materials and Methods After obtaining approval of the institutional review board and patients...
Conference Paper
Eye tracking is widely used in psychological research. There are many cases in which hand and finger tracking would be very useful. Fiducial markers on the fingers can be robustly tracked with a camera or electrical receiver, but this method requires special equipment, and may limit the subject’s freedom of movement. Single-camera machine vision ap...

Network

Cited By