Dr. Fons van der Sommen Profile

Dr. Fons van der Sommen

SPIE Involvement:

Author

Publications (37)

Proceedings Article | 2 April 2024 Presentation + Paper

Unsupervised cell segmentation by invariant information clustering

Wessel van Nierop, Jan-N. Schneider, Peter H. de With, Fons van der Sommen

Proceedings Volume 12926, 129260V (2024) https://doi.org/10.1117/12.3001442

KEYWORDS: Live cell imaging, Machine learning, Deep learning, Information theory, Image segmentation, Data modeling, Performance modeling, Tunable filters, Ablation, Microscopy, Semantics, Transform theory, Image filtering

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Evaluating task-specific augmentations in self-supervised pre-training for 3D medical image analysis

C. H. Claessens, J. J. M. Hamm, C. G. Viviers, J. Nederend, D. Grünhagen, P. Tanis, P. H. de With, F. van der Sommen

Proceedings Volume 12926, 129261L (2024) https://doi.org/10.1117/12.3000850

KEYWORDS: Medical imaging, 3D image processing, 3D modeling, Lung, Education and training, Image segmentation, Voxels, Tumors, Image classification

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Robustness evaluation of CAD systems for lung nodule segmentation using clinically relevant image perturbations

Fidan Mammadli, Terese A. Hellström, Christiaan G. Viviers, Igor Jacobs, Lotte J. Ewals, Nick Tasios, Dimitrios Mavroeidis, Hendrika P. Verhees, Peter H. de With, Joost Nederend, Fons van der Sommen

Proceedings Volume 12926, 1292628 (2024) https://doi.org/10.1117/12.3006211

KEYWORDS: Motion models, Lung, Computed tomography, Data modeling, Image segmentation, CT reconstruction, Artificial intelligence, Simulations, Performance modeling, Cancer detection

Read Abstract +

Proceedings Article | 29 March 2024 Poster + Paper

Toward requirement-based performance in data-driven image analysis algorithms for robotic applications

Yuri Hudak, Timo J. Oude Vrielink, Fons van der Sommen

Proceedings Volume 12928, 129281Q (2024) https://doi.org/10.1117/12.3005631

KEYWORDS: Image segmentation, Computer simulations, Deformation, Distortion, Image processing algorithms and systems, Education and training, Lung, Performance modeling, Image analysis, Biopsy

Read Abstract +

SPIE Journal Paper | 28 April 2023 Open Access

Training procedure for scanning electron microscope 3D surface reconstruction using unsupervised domain adaptation with simulated data

Tim Houben, Thomas Huisman, Maxim Pisarenco, Fons van der Sommen, Peter de With

JM3, Vol. 22, Issue 03, 031208, (April 2023) https://doi.org/10.1117/12.10.1117/1.JMM.22.3.031208

KEYWORDS: Scanning electron microscopy, Education and training, Semiconducting wafers, Electron microscopes, 3D scanning, Data modeling, Critical dimension metrology, Scatterometry, 3D metrology, 3D modeling

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 27 April 2023 Poster + Presentation + Paper

Depth estimation from SEM images using deep learning and angular data diversity

Tim Houben, Maxim Pisarenco, Thomas Huisman, Hans Onvlee, Fons van der Sommen, Peter de With

Proceedings Volume 12496, 124961E (2023) https://doi.org/10.1117/12.2658094

KEYWORDS: Scanning electron microscopy, Line scan image sensors, Education and training, Simulations, Analytic models, Monte Carlo methods, Electron beams, Neural networks, Image analysis, Silicon

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

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

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

Proceedings Volume 12465, 124651P (2023) https://doi.org/10.1117/12.2647557

KEYWORDS: Computer aided detection, Endoscopy

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Probabilistic 3D segmentation for aleatoric uncertainty quantification in full 3D medical data

Christiaan G. Viviers, M. M. Amaan Valiuddin, Peter H. de With, Fons van der Sommen

Proceedings Volume 12465, 124651I (2023) https://doi.org/10.1117/12.2654255

KEYWORDS: Measurement uncertainty, Deep convolutional neural networks, Spatial data uncertainty, 3D modeling, Education and training, Image segmentation, Computed tomography, Lung, 3D image processing, Voxels, Computer aided detection

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

How does image quality affect computer-aided diagnosis of colorectal polyps?

Thom Scheeve, Nikoo Dehghani, Quirine E. van der Zander, Ayla Thijssen, Ramon-Michel Schreuder, Ad A. Masclee, Erik Schoon, Fons van der Sommen, Peter H. de With

Proceedings Volume 12465, 124650S (2023) https://doi.org/10.1117/12.2654167

KEYWORDS: Image quality, Endoscopy, Polyps, Cancer, Colorectal cancer, Clinical practice, Deep learning, Distortion

Read Abstract +

Colorectal cancer (CRC) is one of the leading causes of cancer-related deaths with rising incidence. Since the survival rate of CRC is correlated with the cancer stage at diagnosis, timely detection and adequate treatment strategies are of utmost importance. Technical innovations such as machine learning (ML) and its application in endoscopy show promising results, but the trust of medical doctors in ML is lacking and the ‘black box’ nature complicates the understanding of such systems in clinical practice. In contrast to CT and MRI, image quality is a limiting factor in especially endoscopic imaging, as it is very operator dependent. However, the influence of image quality on convolutional (deep) neural networks (CNNs) is insufficiently studied in relation to clinical practice and the usage of medical image data for computer-aided detection and diagnosis (CADx) systems. This paper explores the influence of degraded image quality on the performance of CNNs applied to colorectal polyp (CRP) characterization. Five commonly used CNN architectures, from simple to more complex, are employed with a custom classification head for common CRP characterization. To degrade the quality of images, distortions such as noise, blur, and contrast changes are imposed on the data and their influence on the performance degradation is studied for the mentioned CNN architectures. A large prospectively collected in vivo data set, gathered from four Dutch, both academic and community, hospitals is employed. Results for CRP characterization show that promising CNN-based methods are rather susceptible to noise and blur distortions but reasonably resilient to changes in contrast. This implies that image quality needs monitoring and control prior to directly using image data in CNN models, in order to gain trustworthy use of deep learning (DL) models in a clinical setting. We propose that incorporating an image quality indicator in CADx systems will lead to better acceptance of such systems, and is necessary for the safe implementation of DL applications in clinical practice.

Proceedings Article | 7 April 2023 Poster + Paper

Clinical segmentation for improved pancreatic ductal adenocarcinoma detection and segmentation

Terese A. Hellström, Christiaan G. Viviers, Mark Ramaekers, Nick Tasios, Joost Nederend, Misha D. Luyer, Peter H. de With, Fons van der Sommen

Proceedings Volume 12465, 124652M (2023) https://doi.org/10.1117/12.2654164

KEYWORDS: Tumors, Cancer detection, Image segmentation, Pancreas, 3D modeling, Computed tomography, Performance modeling, Pancreatic cancer, Artificial intelligence, Education and training

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Barrett's lesion detection using a minimal integer-based neural network for embedded systems integration

Tim G. Boers, Carolus H. Kusters, Kiki Fockens, Jelmer Jukema, Martijn Jong, Jeroen de Groof, Jacques Bergman, Fons van der Sommen, Peter H. de With

Proceedings Volume 12465, 1246527 (2023) https://doi.org/10.1117/12.2653890

KEYWORDS: Quantization, Image segmentation, Neural networks, Embedded systems

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Effect of domain-specific self-supervised pretraining on predictive uncertainty for colorectal polyp characterization

N. Dehghani, T. Scheeve, T. G. Boers, Q. E. van der Zander, A. Thijssen, R. Schreuder, A. A. Masclee, E. Schoon, F. van der Sommen, P. H. de With

Proceedings Volume 12465, 124651G (2023) https://doi.org/10.1117/12.2653848

KEYWORDS: Calibration, Polyps, Performance modeling, Computer aided detection, Reliability, Medical imaging, Endoscopy, Network architectures, Image classification

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Paper

Colorectal polyp classification using confidence-calibrated convolutional neural networks

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

Proceedings Volume 12033, 120331P (2022) https://doi.org/10.1117/12.2606801

KEYWORDS: Calibration, Reliability, Error control coding, Computer aided diagnosis and therapy, Convolutional neural networks, Systems modeling, Electrochemical etching, In vivo imaging, Endoscopy, Cancer

Read Abstract +

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 colonoscopy procedures. Current deep learning-based state-of-the-art solutions achieve a high classification performance, but lack measures to increase the reliability of such systems. In this paper, the reliability of a Convolutional Neural Network (CNN) for characterization of CRPs is specifically addressed by confidence calibration. Well-calibrated models produce classification-confidence scores that reflect the actual correctness likelihood of the model, thereby supporting reliable predictions by trustworthy and informative confidence scores. Two recently proposed trainable calibration methods are explored for CRP classification to calibrate the confidence of the proposed CNN. We show that the confidence-calibration error can be decreased by 33.86% (−0.01648 ± 0.01085), 48.33% (−0.04415 ± 0.01731), 50.57% (−0.11423 ± 0.00680), 61.68% (−0.01553 ± 0.00204) and 48.27% (−0.22074 ± 0.08652) for the Expected Calibration Error (ECE), Average Calibration Error (ACE), Maximum Calibration Error (MCE), Over-Confidence Error (OE) and Cumulative Calibration Error (CUMU), respectively. Moreover, the absolute difference between the average entropy and the expected entropy was considerably reduced by 32.00% (−0.04374 ± 0.01238) on average. Furthermore, even a slightly improved classification performance is observed, compared to the uncalibrated equivalent. The obtained results show that the proposed model for CRP classification with confidence calibration produces better calibrated predictions without sacrificing classification performance. This work shows promising points of engagement towards obtaining reliable and well-calibrated CADx systems for in-vivo polyp characterization, to assist clinicians during colonoscopy procedures.

Proceedings Article | 4 April 2022 Presentation + Paper

Efficient endoscopic frame informativeness assessment by reusing the encoder of the primary CAD task

Fidan Mammadli, Fons van der Sommen, Tim Boers, Joost van der Putten, Kiki Fockens, Jelmer Jukema, Martijn de Jong, Jacques J.G.H.M. Bergman, Peter H. de With

Proceedings Volume 12033, 120331C (2022) https://doi.org/10.1117/12.2611133

KEYWORDS: Convolutional neural networks, Computer aided diagnosis and therapy, Computer vision technology, Artificial intelligence, Artificial neural networks, Endoscopy, CAD systems, Image quality, Algorithm development, Network architectures, Video, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Presentation + Paper

Towards real-time 6D pose estimation of objects in single-view cone-beam x-ray

Christiaan G. A. Viviers, Joël de Bruijn, Lena Filatova, Peter H. de With, Fons van der Sommen

Proceedings Volume 12034, 120341V (2022) https://doi.org/10.1117/12.2611143

KEYWORDS: X-rays, X-ray imaging, 3D modeling, Systems modeling, Medical imaging, Computer simulations, Image classification, Machine learning, Machine vision, Image guided radiation therapy, 3D applications

Read Abstract +

Proceedings Article | 5 March 2022 Paper

Depth estimation from a single CD-SEM image using domain adaptation with multimodal data

Tim Houben, Thomas Huisman, Maxim Pisarenco, Fons van der Sommen, Peter de With

Proceedings Volume 12084, 120841I (2022) https://doi.org/10.1117/12.2622635

KEYWORDS: Data modeling, 3D modeling, Semiconducting wafers, Monte Carlo methods, Neural networks, Metrology, Semiconductors, Scanning electron microscopy, 3D metrology, Sensors

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Iterative reconstruction anti-correlated ROF model for noise reduction in dual-energy CBCT imaging

Luis A. Zavala-Mondragon, Klaus Juergen Engel, Bernd Menser, Danny Ruijters, Peter H. de With, Fons van der Sommen

Proceedings Volume 11596, 115962G (2021) https://doi.org/10.1117/12.2579500

KEYWORDS: Denoising, Radio over Fiber, Dual energy imaging, Reconstruction algorithms, Neuroimaging, Brain, X-rays, Visible radiation, Signal attenuation, Photon counting

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Tissue-border detection in volumetric laser endomicroscopy using bi-directional gated recurrent neural networks

Sanne Okel, Fons van der Sommen, Endi Selmanaj, Joost van der Putten, Maarten Struyvenberg, Jacques J.G.H.M. Bergman, Peter H. de With

Proceedings Volume 11597, 115972H (2021) https://doi.org/10.1117/12.2579751

KEYWORDS: Image segmentation, Tissues, Neural networks, Endomicroscopy, Laser tissue interaction, Solid modeling, Computer aided diagnosis and therapy, Esophagus, Convolutional neural networks, Computer aided design

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Hyperspectral imaging for tissue classification in glioblastoma tumor patients: a deep spectral-spatial approach

Francesca Manni, Chuchen Cai, Fons van der Sommen, Svitlana Zinger, Caifeng Shan, Erik Edström, Adrian Elmi-Terander, Himar Fabelo, Samuel Ortega, Gustavo Callicó, Peter H. de With

Proceedings Volume 11598, 1159810 (2021) https://doi.org/10.1117/12.2580158

KEYWORDS: Tumors, Hyperspectral imaging, Tissue optics, Tissues, Surgery, Statistical analysis, Optical imaging, In vivo imaging, Image classification, Brain

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Fast tissue detection in volumetric laser endomicroscopy using convolutional neural networks: an object-detection approach

Endi Selmanaj, Fons van der Sommen, Sanne Okel, Joost van der Putten, Maarten Struyvenberg, Jacques J. G. H. M. Bergman, Peter H. de With

Proceedings Volume 11596, 1159635 (2021) https://doi.org/10.1117/12.2579573

KEYWORDS: Tissues, Laser tissue interaction, Endomicroscopy, Convolutional neural networks, Esophagus, Cancer, New and emerging technologies, Network architectures, Laser applications, Computer-aided diagnosis

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Augmented-reality visualization for improved patient positioning workflow during MR-HIFU therapy

Francesca Manni, Cyril Ferrer, Celine E. Vincent, Marco Lai, Lambertus W. Bartels, Clemens Bos, Fons van der Sommen, Peter H. N. de With

Proceedings Volume 11598, 115982C (2021) https://doi.org/10.1117/12.2580838

KEYWORDS: Visualization, Magnetic resonance imaging, Augmented reality, Image fusion, Cameras, Ultrasonography, Tissues, Scanners, Medical imaging, Bone

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Triplet network for classification of benign and pre-malignant polyps

Roger Fonollà, Maciej Smyl, Fons van der Sommen, Ramon Schreuder, Erik Schoon, Peter H. de With

Proceedings Volume 11597, 1159731 (2021) https://doi.org/10.1117/12.2577546

KEYWORDS: Error control coding, Endoscopy, Visualization, Visual process modeling, Tumor growth modeling, Tissues, Safety, Network architectures, Laser imaging, Colorectal cancer

Read Abstract +

Proceedings Article | 16 March 2020 Paper

The field effect in Barrett's Esophagus: a macroscopic view using white light endoscopy and deep learning

Levi Verhage, Joost van der Putten, Fons van der Sommen, Jeroen de Groof, Maarten Struyvenberg, Peter H. de With

Proceedings Volume 11314, 1131437 (2020) https://doi.org/10.1117/12.2549391

KEYWORDS: Data modeling, Esophagus, Algorithm development, Tissues, Performance modeling, Endoscopy, Evolutionary algorithms, Computer aided diagnosis and therapy, Image segmentation, Image classification

Read Abstract +

Proceedings Article | 16 March 2020 Paper

First steps into endoscopic video analysis for Barrett’s cancer detection: challenges and opportunities

Joost van der Putten, Jeroen de Groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter H. de With

Proceedings Volume 11314, 1131431 (2020) https://doi.org/10.1117/12.2544229

KEYWORDS: Video, Video surveillance, Endoscopy, Cancer, Esophagus, Computer aided design, Image classification

Read Abstract +

Proceedings Article | 10 March 2020 Presentation + Paper

Influence of decoder size for binary segmentation tasks in medical imaging

Joost van der Putten, Fons van der Sommen, Peter H. de With

Proceedings Volume 11313, 1131318 (2020) https://doi.org/10.1117/12.2542199

KEYWORDS: Image segmentation, Binary data, Medical imaging, Skin, Computer programming, Data modeling, RGB color model, Network architectures, Statistical modeling, Convolution

Read Abstract +

Proceedings Article | 10 March 2020 Presentation + Paper

Detection of frame informativeness in endoscopic videos using image quality and recurrent neural networks

T. G. W. Boers, J. van der Putten, J. de Groof, M. Struyvenberg, K. Fockens, W. Curvers, E. Schoon, F. van der Sommen, J. Bergman, P.H. de With

Proceedings Volume 11313, 1131315 (2020) https://doi.org/10.1117/12.2545734

KEYWORDS: Endoscopy, Image quality, Video, Neural networks, Artificial intelligence, Esophagus, Visualization, Image classification, Evolutionary algorithms, Binary data

Read Abstract +

Proceedings Article | 18 March 2019 Presentation + Paper

Cancer detection in mass spectrometry imaging data by dilated convolutional neural networks

J. van Kersbergen, F. Ghazvinian Zanjani, S. Zinger, F. van der Sommen, B. Balluff, D. R. Vos, S. Ellis, R. M. Heeran, M. Lucas, H. Marquering, I. Jansen, C. Savci-Heijink, D. de Bruin, P. H. de With

Proceedings Volume 10956, 109560I (2019) https://doi.org/10.1117/12.2512360

KEYWORDS: Bladder, Cancer, Tissues, Lung, Mass spectrometry, Convolution, Convolutional neural networks, Tumors, Image classification, Principal component analysis

Read Abstract +

Proceedings Article | 15 March 2019 Paper

Tissue segmentation in volumetric laser endomicroscopy data using FusionNet and a domain-specific loss function

Joost van der Putten, Fons van der Sommen, Maarten Struyvenberg, Jeroen de Groof, Wouter Curvers, Erik Schoon, Jacques J.G.H.M. Bergman, Peter H. de With

Proceedings Volume 10949, 109492J (2019) https://doi.org/10.1117/12.2512192

KEYWORDS: Image segmentation, Optical coherence tomography, Computer aided diagnosis and therapy, Esophagus, Endomicroscopy, Endoscopy

Read Abstract +

Proceedings Article | 13 March 2019 Paper

A novel clinical gland feature for detection of early Barrett’s neoplasia using volumetric laser endomicroscopy

Thom Scheeve, Maarten Struyvenberg, Wouter Curvers, Albert de Groof, Erik Schoon, Jacques J. G. H. Bergman, Fons van der Sommen, Peter H. de With

Proceedings Volume 10950, 109501Y (2019) https://doi.org/10.1117/12.2508244

KEYWORDS: Image segmentation, Tissues, Image analysis, In vivo imaging, Endomicroscopy, Esophagus, Endoscopy, Machine learning

Read Abstract +

Proceedings Article | 13 March 2019 Paper

Computer-aided classification of colorectal polyps using blue-light and linked-color imaging

Thom Scheeve, Ramon-Michel Schreuder, Fons van der Sommen, Joep E. IJspeert, Evelien Dekker, Erik Schoon, Peter H. De With

Proceedings Volume 10950, 1095012 (2019) https://doi.org/10.1117/12.2508223

KEYWORDS: Colorectal cancer, Endoscopy, Imaging systems, Diagnostics, Computer aided diagnosis and therapy, Image classification, Machine learning

Read Abstract +

Proceedings Article | 8 March 2019 Paper

Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging

Francesca Manni, Fons van der Sommen, Sveta Zinger, Esther Kho, Susan Brouwer de Koning, Theo Ruers, Caifeng Shan, Jean Schleipen, Peter H. de With

Proceedings Volume 10951, 109512K (2019) https://doi.org/10.1117/12.2512238

KEYWORDS: Tumors, Cancer, Tissues, Hyperspectral imaging, Image segmentation, Image classification, Tongue, Visualization, Reflectivity, Pathology

Read Abstract +

Proceedings Article | 27 February 2018 Paper

Quantitative CT based radiomics as predictor of resectability of pancreatic adenocarcinoma

Joost van der Putten, Svitlana Zinger, Fons van der Sommen, Peter H. de With, Mathias Prokop, John Hermans

Proceedings Volume 10575, 105753O (2018) https://doi.org/10.1117/12.2291746

KEYWORDS: Tumors, Computed tomography, Binary data, Feature selection, Surgery, Feature extraction, Tissues, Pancreas

Read Abstract +

Proceedings Article | 3 March 2017 Presentation + Paper

Evaluation of image features and classification methods for Barrett's cancer detection using VLE imaging

Sander Klomp, Fons van der Sommen, Anne-Fré Swager, Svitlana Zinger, Erik Schoon, Wouter Curvers, Jacques Bergman, Peter H. de With

Proceedings Volume 10134, 101340D (2017) https://doi.org/10.1117/12.2253860

KEYWORDS: Esophagus, Cancer, Performance modeling, Visual process modeling, Feature extraction, Image classification, Feature selection, Principal component analysis, Machine learning, Tissues

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Sweet-spot training for early esophageal cancer detection

Fons van der Sommen, Svitlana Zinger, Erik Schoon, Peter H. N. de With

Proceedings Volume 9785, 97851B (2016) https://doi.org/10.1117/12.2208114

KEYWORDS: Cancer, Optical inspection, Visualization, Tissues, Algorithm development, Computer aided diagnosis and therapy, Endoscopy, Inspection, Image analysis, Image segmentation, CAD systems, Esophagus, Computing systems

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Early esophageal cancer detection using RF classifiers

Markus H. Janse, Fons van der Sommen, Svitlana Zinger, Erik Schoon, Peter H. de With

Proceedings Volume 9785, 97851D (2016) https://doi.org/10.1117/12.2208583

KEYWORDS: Cancer, Endoscopy, Computer aided diagnosis and therapy, Image segmentation, Computing systems, Tissues, Data modeling, Binary data, Imaging systems

Read Abstract +

Proceedings Article | 18 March 2016 Paper

Accurate biopsy-needle depth estimation in limited-angle tomography using multi-view geometry

Fons van der Sommen, Sveta Zinger, Peter H. de With

Proceedings Volume 9786, 97860D (2016) https://doi.org/10.1117/12.2214450

KEYWORDS: Image-guided intervention, Reconstruction algorithms, Tomography, X-rays, 3D image processing, CT reconstruction, Computed tomography, Error analysis, Sensors, Image segmentation, Switches

Read Abstract +