Carolus H.J. (Koen) Kusters

PhD Candidate Medical Computer Vision & AI - Eindhoven University of Technology

Biography

Carolus H.J. (Koen) Kusters received the B.Sc and M.Sc (cum laude) degrees in Electrical Engineering from Eindhoven University of Technology, in 2019 and 2021, respectively. He currently is with the Video Coding & Architectures Research Group, Department of Electrical Engineering, Eindhoven University of Technology, as a PhD Candidate. He is passionate about machine learning, deep learning and computer vision for medical applications, which connects with the research focus of the PhD project: "Robust and Efficient AI in Endoscopy".

Contact: c.h.j.kusters@tue.nl.

Publications

Designing a Computer-Aided Detection system for Barrett's neoplasia: Insights in architectural choices, training strategies and inference approaches

Carolus H.J. Kusters, Tim G.W. Boers, Tim J.M. Jaspers, Martijn R. Jong, Rixta A.H. van Eijck van Heslinga, Jelmer B. Jukema, Kiki N. Fockens, Albert J. de Groof, Jacques J. Bergman, Fons van der Sommen and Peter H.N. de With

Submission under review at Computer Methods and Programs in Biomedicine

Code

Standard enhancement settings used on endoscopy systems significantly impair performance of artificial intelligence systems in endoscopy

Carolus H.J. Kusters*, Martijn R. Jong*, Querijn N.E. van Bokhorst, Jelmer B. Jukema, Rixta A.H. van Eijck van Heslinga, Kiki N. Fockens, Britt B.S.L. Houwen, Tim J.M. Jaspers, Tim G.W. Boers, Manon van der Vlugt, Evelien Dekker, Fons van der Sommen, Peter H.N. de With, Albert J. de Groof and Jacques J. Bergman

Endoscopy - Volume XX, Month-Year

Will Transformers change gastrointestinal endoscopic image analysis? A comparative analysis between CNNs and Transformers, in terms of performance, robustness and generalization

Carolus H.J. Kusters, Tim G.W. Boers, Tim J.M. Jaspers, Martijn R. Jong, Jelmer B. Jukema, Kiki N. Fockens, Albert J. de Groof, Jacques J. Bergman, Fons van der Sommen and Peter H.N. de With

Medical Image Analysis - Volume 99, January 2025

Elsevier ScienceDirect

Code

Optimizing Multi-Expert Consensus for Classification and Precise Localization of Barrett's Neoplasia

Carolus H.J. Kusters, Tim G.W. Boers, Tim J.M. Jaspers, Martijn R. Jong, Rixta A.H. van Eijck van Heslinga, Albert J. de Groof, Jacques J. Bergman, Fons van der Sommen and Peter H.N. de With

CaPTion Workshop (3rd Edition) - Satellite Event MICCAI 2024

Springer Proceedings

Code

CNNs vs. Transformers: Performance and Robustness in Endoscopic Image Analysis

Carolus H.J. Kusters, Tim G.W. Boers, Tim J.M. Jaspers, Jelmer B. Jukema, Martijn R. Jong, Kiki N. Fockens, Albert J. de Groof, Jacques J. Bergman, Fons van der Sommen and Peter H.N. de With

AMAI Workshop (2nd Edition) - Satellite Event MICCAI 2023

Springer Proceedings

Code

Real-time Barrett's neoplasia characterization in NBI videos using an int8-based quantized neural network

Carolus H.J. Kusters, Tim G.W. Boers, Jelmer B. Jukema, Martijn R. Jong, Kiki N. Fockens, Albert J. de Groof, Jacques J. Bergman, Fons van der Sommen and Peter H.N. de With

SPIE Medical Imaging 2023

SPIE Digital Library

Computer-Aided Diagnosis Best Paper Award

A CAD System for Real-Time Characterization of Neoplasia in Barrett's Esophagus NBI Videos

Carolus H.J. Kusters, Tim G.W. Boers, Jelmer B. Jukema, Martijn R. Jong, Kiki N. Fockens, Albert J. de Groof, Jacques J. Bergman, Fons van der Sommen and Peter H.N. de With

CaPTion Workshop (1st Edition) - Satellite Event MICCAI 2022

Springer Proceedings

Colorectal Polyp classification using Confidence-Calibrated Convolutional Neural Networks

Koen C. Kusters, Thom Scheeve, Nikoo Dehghani, Quirine E.W. van der Zander, Ramon-Michel Schreuder, Ad A.M. Masclee, Erik J. Schoon, Fons van der Sommen and Peter H.N. de With

SPIE Medical Imaging 2022

SPIE Digital Library

Conditional Generative Adversarial Networks for low-dose CT image denoising aiming at preservation of critical image content

Koen C. Kusters, Luis A. Zavala-Mondragón, Javier Oliván Bescós, Peter Rongen, Peter H.N. de With and Fons van der Sommen

IEEE EMBC 2021

IEEE Xplore

Experiences

PhD Candidate - Video Coding & Architectures
Eindhoven University of Technology

  • Project title: Robust and Efficient Artificial Intelligence (AI) in Endoscopy
    • Description: Focus on robust and efficient Artificial Intelligence (AI) in endoscopy, where machine learning and computer vision techniques are combined with medical knowledge to improve algorithms and make the next steps towards clinical application of AI-based supportive systems in endoscopy. Research in close collaboration with colleagues from Amsterdam University Medical Centers and mainly includes the detection and diagnosis of early neoplasia in Barrett's Esophagus.
    • Supervision: prof.dr.ir. Peter de With (Full professor at TU/e, IEEE Life Fellow) and dr.ir. Fons van der Sommen (Associate professor at TU/e)
  • Teaching Assistant: Neural Networks for Computer Vision (M.Sc Course)

M.Sc Electrical Engineering - Signal Processing Systems
Eindhoven University of Technology

  • Specialization: Signal processing, machine learning, deep learning and computer vision
  • Thesis title: Colorectal Polyp (CRP) Classification using Convolutional Neural Networks (CNNs)
    • Description: Investigated the improvement of performance, robustness and reliability of CNNs for CRP classification
    • Grade: 9.0/10
  • Conference Proceeding: SPIE Medical Imaging 2022
  • Honors: Cum Laude

M.Sc Internship
Philips Medical Systems B.V.

  • Project title: Conditional Generative Adversarial Networks (cGAN) for low-dose Computed Tomography (CT) image denoising
    • Description: Investigated the impact of generator and discriminator architectures within the cGAN framework
    • Grade: 9.0/10
  • Conference Proceeding: IEEE EMBC 2021

B.Sc Electrical Engineering
Eindhoven University of Technology

  • Thesis title: Automatic Tissue Detection in Volumetric Laser Endomicroscopy (VLE) using Deep Learning
    • Description: Design a deep learning algorithm to automatically detect the tissue boundary in endoscopic VLE images of the esophagus
    • Grade: 8.5/10