Carolus H. J. Kusters
YOU?
Author Swipe
View article: Scaling up self-supervised learning for improved surgical foundation models
Scaling up self-supervised learning for improved surgical foundation models Open
Foundation models have revolutionized computer vision by achieving vastly superior performance across diverse tasks through large-scale pretraining on extensive datasets. However, their application in surgical computer vision has been limi…
View article: Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions
Evaluation of an improved computer-aided detection system for Barrett’s neoplasia in real-world imaging conditions Open
Background Computer-aided detection (CADe) systems may improve detection of Barrett’s neoplasia. Most CADe systems are developed with data from expert centers, unrepresentative of heterogeneous imaging conditions in community hospitals, an…
View article: Designing a Computer-Aided Detection system for Barrett ’s neoplasia: Insights in architectural choices, training strategies and inference approaches
Designing a Computer-Aided Detection system for Barrett ’s neoplasia: Insights in architectural choices, training strategies and inference approaches Open
This study provides critical insights into the structured development of effective CADe systems for Barrett's neoplasia detection. By addressing the specific challenges associated with endoscopic imaging and Barrett's neoplasia, the study …
View article: Challenges in Implementing Endoscopic Artificial Intelligence: The Impact of Real‐World Imaging Conditions on Barrett's Neoplasia Detection
Challenges in Implementing Endoscopic Artificial Intelligence: The Impact of Real‐World Imaging Conditions on Barrett's Neoplasia Detection Open
Background Endoscopic deep learning systems are often developed using high‐quality imagery obtained from expert centers. Therefore, they may underperform in community hospitals where image quality is more heterogeneous. Objective This stud…
View article: Comparison of graphic user interfaces for computer-aided detection in Barrett’s neoplasia
Comparison of graphic user interfaces for computer-aided detection in Barrett’s neoplasia Open
Although endoscopists expressed a preference for the heatmap GUI, this was not associated with a statistical difference in performance outcomes.
View article: Self-supervised learning for automated image quality assessment in endoscopy
Self-supervised learning for automated image quality assessment in endoscopy Open
Computer-aided detection and diagnosis systems (CADe/x) in endoscopy are primarily trained on high-quality imagery from expert centers. However, various factors can significantly impact the image quality of endoscopic images during endosco…
View article: 2.5D mapping of the esophagus as imaging quality and completeness assuring extension for endoscopic computer-aided detection systems
2.5D mapping of the esophagus as imaging quality and completeness assuring extension for endoscopic computer-aided detection systems Open
Quality and completeness of images taken during endoscopy of the esophagus are of high importance for their use in computer-aided detection (CADe) systems. Providing a tissue map to show visited locations with sufficient image quality, and…
View article: The development and ex vivo evaluation of a computer-aided quality control system for Barrett’s esophagus endoscopy
The development and ex vivo evaluation of a computer-aided quality control system for Barrett’s esophagus endoscopy Open
Background Timely detection of neoplasia in Barrett’s esophagus (BE) remains challenging. While computer-aided detection (CADe) systems have been developed to assist endoscopists, their effectiveness depends heavily on the quality of the e…
View article: Impact of standard enhancement settings of endoscopy systems on performance of endoscopic artificial intelligence systems
Impact of standard enhancement settings of endoscopy systems on performance of endoscopic artificial intelligence systems Open
Background Artificial intelligence (AI) systems in endoscopy are predominantly developed and tested using high-quality imagery from expert centers. However, their performance may be different when applied in clinical practice, partly due t…
View article: Exploring the Effect of Dataset Diversity in Self-supervised Learning for Surgical Computer Vision
Exploring the Effect of Dataset Diversity in Self-supervised Learning for Surgical Computer Vision Open
Over the past decade, computer vision applications in minimally invasive surgery have rapidly increased. Despite this growth, the impact of surgical computer vision remains limited compared to other medical fields like pathology and radiol…
View article: Optimizing Multi-expert Consensus for Classification and Precise Localization of Barrett’s Neoplasia
Optimizing Multi-expert Consensus for Classification and Precise Localization of Barrett’s Neoplasia Open
Recognition of early neoplasia in Barrett’s Esophagus (BE) is challenging, despite advances in endoscopic technology. Even with correct identification, the subtle nature of lesions leads to significant inter-observer variability in placing…
View article: Will Transformers change gastrointestinal endoscopic image analysis? A comparative analysis between CNNs and Transformers, in terms of performance, robustness and generalization
Will Transformers change gastrointestinal endoscopic image analysis? A comparative analysis between CNNs and Transformers, in terms of performance, robustness and generalization Open
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 agre…
View article: Foundation models in gastrointestinal endoscopic AI: Impact of architecture, pre-training approach and data efficiency
Foundation models in gastrointestinal endoscopic AI: Impact of architecture, pre-training approach and data efficiency Open
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-qu…
View article: Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision
Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision Open
Over the past decade, computer vision applications in minimally invasive surgery have rapidly increased. Despite this growth, the impact of surgical computer vision remains limited compared to other medical fields like pathology and radiol…
View article: Appropriate trust in artificial intelligence for the optical diagnosis of colorectal polyps: the role of human/artificial intelligence interaction
Appropriate trust in artificial intelligence for the optical diagnosis of colorectal polyps: the role of human/artificial intelligence interaction Open
Appropriate trust was common, and CADx prediction utilization was highest for the optional CADx without confidence scores. These results express the importance of a better understanding of human-artificial intelligence interaction.
View article: The use of a real-time computer-aided detection system for visible lesions in the Barrett’s esophagus during live endoscopic procedures: a pilot study (with video)
The use of a real-time computer-aided detection system for visible lesions in the Barrett’s esophagus during live endoscopic procedures: a pilot study (with video) Open
In this pilot study, detection by the CADe system of all potentially neoplastic lesions in Barrett's esophagus was comparable to that of an expert endoscopist. Continued refinement of the system may improve specificity. External validation…
View article: Comparison of graphical user interfaces for computer-aided detection of Barrett’s neoplasia
Comparison of graphical user interfaces for computer-aided detection of Barrett’s neoplasia Open
Aims Despite the surge of artificial intelligence applications in endoscopy, the interaction between the endoscopist and AI system remains an underexplored aspect. This endoscopist-AI interaction ultimately may have significant impact on t…
View article: Image quality pitfalls in AI: Safeguarding Barrett's neoplasia detection with robust deep learning training strategies
Image quality pitfalls in AI: Safeguarding Barrett's neoplasia detection with robust deep learning training strategies Open
Aims Endoscopic artificial intelligence systems, developed in expert centers with high-quality imaging, may underperform in community hospitals due to image quality heterogeneity. This study aimed to quantify the performance degradation of…
View article: Domain-specific data augmentation improves robustness of endoscopic AI systems
Domain-specific data augmentation improves robustness of endoscopic AI systems Open
Aims The emergence of deep learning has significantly increased the amount of artificial intelligence (AI) systems in endoscopy. However, these systems are generally developed in expert centers with the use of uniform, high-quality imagery…
View article: Artificial intelligence for characterization of diminutive colorectal polyps: A feasibility study comparing two computer-aided diagnosis systems
Artificial intelligence for characterization of diminutive colorectal polyps: A feasibility study comparing two computer-aided diagnosis systems Open
BACKGROUND Artificial intelligence (AI) has potential in the optical diagnosis of colorectal polyps. AIM To evaluate the feasibility of the real-time use of the computer-aided diagnosis system (CADx) AI for ColoRectal Polyps (AI4CRP) for t…
View article: Barrett's lesion detection using a minimal integer-based neural network for embedded systems integration
Barrett's lesion detection using a minimal integer-based neural network for embedded systems integration Open
Embedded processing architectures are often integrated into devices to develop novel functions in a cost-effective medical system. In order to integrate neural networks in medical equipment, these models require specialized optimizations f…
View article: Real-time Barrett's neoplasia characterization in NBI videos using an int8-based quantized neural network
Real-time Barrett's neoplasia characterization in NBI videos using an int8-based quantized neural network Open
Computer-Aided Diagnosis (CADx) systems for characterization of Narrow-Band Imaging (NBI) videos of suspected lesions in Barrett’s Esophagus (BE) can assist endoscopists during endoscopic surveillance. The real clinical value and applicati…
View article: REAL-TIME CLASSIFICATION OF COLORECTAL POLYPS USING ARTIFICIAL INTELLIGENCE – A PROSPECTIVE PILOT STUDY COMPARING TWO COMPUTER-AIDED DIAGNOSIS SYSTEMS AND ONE EXPERT ENDOSCOPIST
REAL-TIME CLASSIFICATION OF COLORECTAL POLYPS USING ARTIFICIAL INTELLIGENCE – A PROSPECTIVE PILOT STUDY COMPARING TWO COMPUTER-AIDED DIAGNOSIS SYSTEMS AND ONE EXPERT ENDOSCOPIST Open
Quirine van der Zander: NO financial relationship with a commercial interest | Ramon-Michel Schreuder: NO financial relationship with a commercial interest | Ayla Thijssen: NO financial relationship with a commercial interest | Koen Kuster…
View article: Colorectal polyp classification using confidence-calibrated convolutional neural networks
Colorectal polyp classification using confidence-calibrated convolutional neural networks Open
Computer-Aided Diagnosis (CADx) systems for in-vivo characterization of Colorectal Polyps (CRPs) which are precursor lesions of Colorectal Cancer (CRC), can assist clinicians with diagnosis and better informed decisionmaking during colonos…
View article: Conditional Generative Adversarial Networks for low-dose CT image denoising aiming at preservation of critical image content
Conditional Generative Adversarial Networks for low-dose CT image denoising aiming at preservation of critical image content Open
X-ray Computed Tomography (CT) is an imaging modality where patients are exposed to potentially harmful ionizing radiation. To limit patient risk, reduced-dose protocols are desirable, which inherently lead to an increased noise level in t…