Bart Diricx

Dermoscopy-Based AI Risk Scoring Enhanced Experienced Dermatologists’ Decision-Making: a Large Retrospective Reader Study

Laudine Janssen, Sofie Van Kelst, Heleen Cokelaere, Julie Terrasson et autres

Introduction: The integration of artificial intelligence (AI) in dermoscopy is promising for diagnostic and management decisions. Objectives: This study aimed to assess the impact of a deep learning-generated AI risk score, based on dermoscopic images and metadata, on dermatologists' diagnostic accuracy, confidence, …

be (code pays fourni par la source)

Perceptual quality assessment in digital pathology: Modeling diagnostic usability from expert opinions

Tien Nguyen, Saeed Mahmoudpour, Guillaume E. Courtoy, Wim Waelput et autres

be (code pays fourni par la source)

When normalization hallucinates: unseen risks in AI‑powered whole slide image processing

Karel Moens, Matthew B. Blaschko, Tinne Tuytelaars, Bart Diricx et autres

Whole slide image (WSI) normalization remains a vital preprocessing step in computational pathology. Increasingly driven by deep learning, these models learn to approximate data distributions from training examples. This often results in outputs that gravitate toward the average, potentially masking diagnostically important …

be, us (code pays fourni par la source)

A Dataset for Artefact Detection of Whole Slide Images in Digital Pathology

Thang Nguyen-Tien, Saeed Mahmoudpour, Guillaume E. Courtoy, Wim Waelput et autres

Whole slide images (WSIs) are fundamental components of modern pathology, aiding pathologists in diagnosing diseases such as cancer. However, artefacts such as blurry regions, folded tissue, or uneven staining, often introduced during biopsy or slide preparation, can affect the accuracy and efficiency …

be (code pays fourni par la source)

Perceived color contrast metrics for clinical images

Jonas De Vylder, Peter Ouillette, Bart Diricx, Johan Rostang et autres

In medical imaging, contrast plays a crucial role in determining visual quality and facilitating accurate interpretation, particularly in fields like digital pathology and dermatology where color variations are diagnostically significant. Traditional contrast metrics often focus on intensity variations, potentially overlooking critical color …

be, us (code pays fourni par la source)

Open-source tool for model performance analysis for subpopulations

Stijn Vandewiele, Jonas De Vylder, Bart Diricx, Edward Sandra et autres

When a CAD-AI network is created and employed, both safety and effectiveness need to be guaranteed for all subgroups of the target population. We present a novel toolbox for automatic slicing and performance assessment in a generic and modular approach, helping to …

Can Multispectral Dermoscopy Help In Distinguishing Blue Color?

Laudine Janssen, Sofie Van Kelst, Bart Diricx, Tom Kimpe et autres

INTRODUCTION: The interpretation of colors is essential in the dermoscopic evaluation of skin lesions. The same blue color on white dermoscopy may indicate blood or pigment deep in the dermis. Contrary to white dermoscopy, multispectral dermoscopy uses different wavelengths of light to …

be (code pays fourni par la source)

Preoperative assessment of cutaneous melanoma thickness by multispectral dermoscopy

Laudine Janssen, Sofie Van Kelst, Julie De Smedt, Julie Terrasson et autres

Preoperative assessment of Breslow thickness by means of sonography and clinical and dermoscopic criteria in white light dermoscopy has been reported, but up until now, the use of multispectral dermoscopy has not been investigated. Aim of this research is to determine whether …

be (code pays fourni par la source)

33218 Advantages of standardization of dermoscopic imaging by leveraging the DICOM standard

Bart Diricx, Jonas De Vylder, Elie De Brauwer, Josep Malvehy et autres

es, au (code pays fourni par la source)

31686 Automatic detection of blue-white veil in melanoma based on multispectral dermoscopy

Bart Diricx, Jonas De Vylder, Sofie Mylle, Laudine Janssen et autres

be (code pays fourni par la source)

Data-Efficient Sensor Upgrade Path Using Knowledge Distillation

Pieter Van Molle, Cedric De Boom, Tim Verbelen, Bert Vankeirsbilck et autres

Deep neural networks have achieved state-of-the-art performance in image classification. Due to this success, deep learning is now also being applied to other data modalities such as multispectral images, lidar and radar data. However, successfully training a deep neural network requires a …

be (code pays fourni par la source)

Leveraging the Bhattacharyya coefficient for uncertainty quantification in deep neural networks

Pieter Van Molle, Tim Verbelen, Bert Vankeirsbilck, Jonas De Vylder et autres

Abstract Modern deep learning models achieve state-of-the-art results for many tasks in computer vision, such as image classification and segmentation. However, its adoption into high-risk applications, e.g. automated medical diagnosis systems, happens at a slow pace. One of the main reasons for …

be (code pays fourni par la source)