Tim Boers

Mr. Tim Boers

Eindhoven University of Technology

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2024 in Medical Image Analysis
Verified
Journal Article
Open access
Tim BoersTim Boers
Tim Boers
KFKiki N. Fockens
Kiki N. Fockens
JPJoost van der Putten
Joost van der Putten
TJTim J.M. Jaspers
Tim J.M. Jaspers
CKCarolus H.J. Kusters
Carolus H.J. Kusters
Fons van der SommenFons van der Sommen
Fons van der Sommen
Pre-training deep learning models with large data sets of natural images, such as ImageNet, has become the standard for endoscopic image analysis. This approach is generally superior to training from scratch, due to the scarcity of high-quality medical imagery and labels. However, it is still unknown whether the learned features on natural imagery provide an optimal starting point for the downstream medical endoscopic imaging tasks. Intuitively, pre-training with imagery closer to the target domain could lead to better-suited feature representations. This study evaluates whether leveraging in-domain pre-training in gastrointestinal endoscopic image analysis has potential benefits compared to pre-training on natural images. To this end, we present a dataset comprising of 5,014,174 gastrointestinal endoscopic images from eight different medical centers (GastroNet-5M), and exploit self-supervised learning with SimCLRv2, MoCov2 and DINO to learn relevant features for in-domain downstream tasks. The learned features are compared to features learned on natural images derived with multiple methods, and variable amounts of data and/or labels (e.g. Billion-scale semi-weakly supervised learning and supervised learning on ImageNet-21k). The effects of the evaluation is performed on five downstream data sets, particularly designed for a variety of gastrointestinal tasks, for example, GIANA for angiodyplsia detection and Kvasir-SEG for polyp segmentation. The findings indicate that self-supervised domain-specific pre-training, specifically using the DINO framework, results into better performing models compared to any supervised pre-training on natural images. On the ResNet50 and Vision-Transformer-small architectures, utilizing self-supervised in-domain pre-training with DINO leads to an average performance boost of 1.63% and 4.62%, respectively, on the downstream datasets. This improvement is measured against the best performance achieved through pre-training on natural images within any of the evaluated frameworks. Moreover, the in-domain pre-trained models also exhibit increased robustness against distortion perturbations (noise, contrast, blur, etc.), where the in-domain pre-trained ResNet50 and Vision-Transformer-small with DINO achieved on average 1.28% and 3.55% higher on the performance metrics, compared to the best performance found for pre-trained models on natural images. Overall, this study highlights the importance of in-domain pre-training for improving the generic nature, scalability and performance of deep learning for medical image analysis. The GastroNet-5M pre-trained weights are made publicly available in our repository: huggingface.co/tgwboers/GastroNet-5M_Pretrained_Weights.

21 September 2018 in Scientific Reports
Verified
Journal Article
Open access
PDF file
ACAvilash Cramer
Avilash Cramer
JHJake Hecla
Jake Hecla
DWDufan Wu
Dufan Wu
XLXiaochun Lai
Xiaochun Lai
Tim BoersTim Boers
Tim Boers
RGRajiv Gupta
Rajiv Gupta
Computed tomography (CT) is used to diagnose many emergent medical conditions, including stroke and traumatic brain injuries. Unfortunately, the size, weight, and expense of CT systems make them largely inaccessible for patients outside of major hospitals. We have designed a module containing multiple miniature x-ray sources that could allow for CT systems to be significantly lighter, smaller, and cheaper, and to operate without any moving parts. We have developed a novel photocathode-based x-ray source, created by depositing a thin film of magnesium on an electron multiplier. When illuminated by a UV LED, this photocathode emits a beam of electrons, with a beam current of up to 1 mA. The produced electrons are accelerated through a high voltage to a tungsten target. These sources are individually addressable and can be pulsed rapidly, through electronic control of the LEDs. Seven of these sources are housed together in a 17.5 degree arc within a custom vacuum manifold. A full ring of these modules could be used for CT imaging. By pulsing the sources in series, we are able to demonstrate x-ray tomosynthesis without any moving parts. With a clinical flat-panel detector, we demonstrate 3D acquisition and reconstructions of a cadaver swine lung.

29 March 2024 in Medical Image Analysis
Verified
Journal Article
Open access
TJTim J.M. Jaspers
Tim J.M. Jaspers
Tim BoersTim Boers
Tim Boers
CKCarolus H.J. Kusters
Carolus H.J. Kusters
MJMartijn R. Jong
Martijn R. Jong
Jelmer JukemaJelmer Jukema
Jelmer Jukema
Fons van der SommenFons van der Sommen
Fons van der Sommen
Computer-aided detection and diagnosis systems (CADe/CADx) in endoscopy are commonly trained using high-quality imagery, which is not representative for the heterogeneous input typically encountered in clinical practice. In endoscopy, the image quality heavily relies on both the skills and experience of the endoscopist and the specifications of the system used for screening. Factors such as poor illumination, motion blur, and specific post-processing settings can significantly alter the quality and general appearance of these images. This so-called domain gap between the data used for developing the system and the data it encounters after deployment, and the impact it has on the performance of deep neural networks (DNNs) supportive endoscopic CAD systems remains largely unexplored. As many of such systems, for e.g. polyp detection, are already being rolled out in clinical practice, this poses severe patient risks in particularly community hospitals, where both the imaging equipment and experience are subject to considerable variation. Therefore, this study aims to evaluate the impact of this domain gap on the clinical performance of CADe/CADx for various endoscopic applications. For this, we leverage two publicly available data sets (KVASIR-SEG and GIANA) and two in-house data sets. We investigate the performance of commonly-used DNN architectures under synthetic, clinically calibrated image degradations and on a prospectively collected dataset including 342 endoscopic images of lower subjective quality. Additionally, we assess the influence of DNN architecture and complexity, data augmentation, and pretraining techniques for improved robustness. The results reveal a considerable decline in performance of 11.6% (±1.5) as compared to the reference, within the clinically calibrated boundaries of image degradations. Nevertheless, employing more advanced DNN architectures and self-supervised in-domain pre-training effectively mitigate this drop to 7.7% (±2.03). Additionally, these enhancements yield the highest performance on the manually collected test set including images with lower subjective quality. By comprehensively assessing the robustness of popular DNN architectures and training strategies across multiple datasets, this study provides valuable insights into their performance and limitations for endoscopic applications. The findings highlight the importance of including robustness evaluation when developing DNNs for endoscopy applications and propose strategies to mitigate performance loss.

1 July 2020 in Artificial Intelligence in Medicine
Verified
Journal Article
Open access
JPJoost van der Putten
Joost van der Putten
JGJeroen de Groof
Jeroen de Groof
MSMaarten Struyvenberg
Maarten Struyvenberg
Tim BoersTim Boers
Tim Boers
KFKiki Fockens
Kiki Fockens
PWPeter H.N. de With
Peter H.N. de With
Patients suffering from Barrett's Esophagus (BE) are at an increased risk of developing esophageal adenocarcinoma and early detection is crucial for a good prognosis. To aid the endoscopists with the early detection for this preliminary stage of esophageal cancer, this work concentrates on the development and extensive evaluation of a state-of-the-art computer-aided classification and localization algorithm for dysplastic lesions in BE. To this end, we have employed a large-scale endoscopic data set, consisting of 494,355 images, in combination with a novel semi-supervised learning algorithm to pretrain several instances of the proposed neural network architecture. Next, several Barrett-specific data sets that are increasingly closer to the target domain with significantly more data compared to other related work, were used in a multi-stage transfer learning strategy. Additionally, the algorithm was evaluated on two prospectively gathered external test sets and compared against 53 medical professionals. Finally, the model was also evaluated in a live setting without interfering with the current biopsy protocol. Results from the performed experiments show that the proposed model improves on the state-of-the-art on all measured metrics. More specifically, compared to the best performing state-of-the-art model, the specificity is improved by more than 20% points while simultaneously preserving high sensitivity and reducing the false positive rate substantially. Our algorithm yields similar scores on the localization metrics, where the intersection of all experts is correctly indicated in approximately 92% of the cases. Furthermore, the live pilot study shows great performance in a clinical setting with a patient level accuracy, sensitivity, and specificity of 90%. Finally, the proposed algorithm outperforms each individual medical expert by at least 5% and the average assessor by more than 10% over all assessor groups with respect to accuracy.

16 September 2024 in Medical Image Analysis
Verified
Journal Article
Open access
CKCarolus H.J. Kusters
Carolus H.J. Kusters
TJTim J.M. Jaspers
Tim J.M. Jaspers
Tim BoersTim Boers
Tim Boers
MJMartijn R. Jong
Martijn R. Jong
Jelmer JukemaJelmer Jukema
Jelmer Jukema
PWPeter H.N. De With
Peter H.N. De With
Gastrointestinal endoscopic image analysis presents significant challenges, such as considerable variations in quality due to the challenging in-body imaging environment, the often-subtle nature of abnormalities with low interobserver agreement, and the need for real-time processing. These challenges pose strong requirements on the performance, generalization, robustness and complexity of deep learning-based techniques in such safety-critical applications. While Convolutional Neural Networks (CNNs) have been the go-to architecture for endoscopic image analysis, recent successes of the Transformer architecture in computer vision raise the possibility to update this conclusion. To this end, we evaluate and compare clinically relevant performance, generalization and robustness of state-of-the-art CNNs and Transformers for neoplasia detection in Barrett's esophagus. We have trained and validated several top-performing CNNs and Transformers on a total of 10,208 images (2,079 patients), and tested on a total of 7,118 images (998 patients) across multiple test sets, including a high-quality test set, two internal and two external generalization test sets, and a robustness test set. Furthermore, to expand the scope of the study, we have conducted the performance and robustness comparisons for colonic polyp segmentation (Kvasir-SEG) and angiodysplasia detection (Giana). The results obtained for featured models across a wide range of training set sizes demonstrate that Transformers achieve comparable performance as CNNs on various applications, show comparable or slightly improved generalization capabilities and offer equally strong resilience and robustness against common image corruptions and perturbations. These findings confirm the viability of the Transformer architecture, particularly suited to the dynamic nature of endoscopic video analysis, characterized by fluctuating image quality, appearance and equipment configurations in transition from hospital to hospital. The code is made publicly available at: https://github.com/BONS-AI-VCA-AMC/Endoscopy-CNNs-vs-Transformers.

1 June 2020 in Gastrointestinal Endoscopy
Verified
Journal Article
Closed access
MSMaarten R. Struyvenberg
Maarten R. Struyvenberg
JGJeroen de Groof
Jeroen de Groof
KFKiki Fockens
Kiki Fockens
JPJoost van der Putten
Joost van der Putten
FSFons van der Sommen
Fons van der Sommen
JBJacques Bergman
Jacques Bergman