Denis Kouame
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Denis Kouame has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Adrian Basarab
Université Claude Bernard Lyon 1, INSA Lyon, CNRS, Inserm, CREATIS UMR 5220, U1294, Lyon, France
13 shared publications - Jonathan Mamou
Weill Cornell Medicine
5 shared publications - Sayantan Dutta
Department of Radiology, Weill Cornell Medicine, New York, NY, USA
4 shared publications - Alin Achim
University of Bristol, Bristol, U.K.
3 shared publications - Bertrand Georgeot
Laboratoire de Physique Théorique, Université de Toulouse, CNRS, UPS, Toulouse, France
3 shared publications - Duong-Hung Pham
IRIT Lab, Université de Toulouse, and CNRS UMR 5505, 118 Route de Narbonne, Toulouse, 31400, Occitanie, France
3 shared publications
Latest Publications
- Open Access
- 1 August 2025
- Published by AIP Publishing in AIP Advances
- Vol. 15 (8)
A novel perspective on denoising using quantum localization with application to medical imaging
Background noise in many fields, such as medical imaging, poses significant challenges for accurate diagnosis, prompting the development of denoising algorithms. Traditional methodologies, however, often struggle to address the complexities of noisy environments in high dimensional imaging systems. This paper introduces a novel quantum-inspired approach for image denoising, drawing upon principles of quantum and condensed matter physics. Our approach views medical images as amorphous structures akin to those found in condensed matter physics, and we propose an algorithm that incorporates the concept of mode resolved localization directly into the denoising process. Notably, unlike previous studies that considered localization as a hindrance, our approach considers quantum localization as a fundamental component of image reconstruction, which is used to differentiate between noisy and non-noisy modes based on diffusivity and localization measurements. This perspective eliminates the need for hyperparameter tuning, making the proposed method a standalone algorithm that can be implemented with minimal manual intervention and can perform automatic filtering of noise regardless of noise level. Through numerical validation, we showcase the effectiveness of our approach in addressing noise-related challenges in imaging, and especially medical imaging, underscoring its relevance for possible quantum computing applications.
- 1 August 2025
- Published by AIP Publishing in AIP Advances
- Vol. 15 (8)
Open AccessA novel perspective on denoising using quantum localization with application to medical imaging
Background noise in many fields, such as medical imaging, poses significant challenges for accurate diagnosis, prompting the development of denoising algorithms. Traditional methodologies, however, often struggle to address the complexities of noisy environments in high dimensional imaging systems. This paper introduces a novel quantum-inspired approach for image denoising, drawing upon principles of quantum and condensed matter physics. Our approach views medical images as amorphous structures akin to those found in condensed matter physics, and we propose an algorithm that incorporates the concept of mode resolved localization directly into the denoising process. Notably, unlike previous studies that considered localization as a hindrance, our approach considers quantum localization as a fundamental component of image reconstruction, which is used to differentiate between noisy and non-noisy modes based on diffusivity and localization measurements. This perspective eliminates the need for hyperparameter tuning, making the proposed method a standalone algorithm that can be implemented with minimal manual intervention and can perform automatic filtering of noise regardless of noise level. Through numerical validation, we showcase the effectiveness of our approach in addressing noise-related challenges in imaging, and especially medical imaging, underscoring its relevance for possible quantum computing applications.
- Open Access
- 17 July 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt B) , 110730
A weighted Hankel approach and Cramér–Rao bound analysis for quantitative acoustic microscopy imaging
- 17 July 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt B) , 110730
Open AccessA weighted Hankel approach and Cramér–Rao bound analysis for quantitative acoustic microscopy imaging
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 72 (5) , 636-645
Computational Super-Resolution for Ultrasound Localization Microscopy Through Solving an Inverse Problem
Ultrasound localization microscopy (ULM) represents a significant advancement over traditional ultrasound (US) imaging, enabling super-resolution (SR) imaging of microvascular structures with unprecedented detail, by using microbubbles (MBs) as highly reflective contrast agents. After injection into the bloodstream, MBs are localized in US images to reconstruct the microvasculature. However, this technique faces a trade-off between MB localization accuracy and acquisition time. Perfusion with low MB concentrations reduces signal overlap and achieves high localization accuracy but requires extended acquisition times. Conversely, higher MB concentrations shorten acquisition times but increase signal overlap, limiting localization precision. Traditionally, ULM consists of five main steps: tissue filtering, MB detection, MB super-localization, tracking, and rendering. In this study, we present a novel approach that combines a robust principal component analysis (RPCA) with a computational SR technique, replacing the first three steps of ULM with a single process based on solving a SR inverse problem. This method isolates MB signals from background noise and enhances the localization of overlapping MBs, thereby improving overall ULM performance. Experimental results from simulated and in vivo data demonstrate that our proposed approach increases the SR factor by up to 30% and enhances the contrast ratio (CR) by 3.5 dB. It also produces comparable results across other image quality metrics. These improvements enable denser, higher-contrast vascular images.
- 21 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 72 (5) , 636-645
Computational Super-Resolution for Ultrasound Localization Microscopy Through Solving an Inverse Problem
Ultrasound localization microscopy (ULM) represents a significant advancement over traditional ultrasound (US) imaging, enabling super-resolution (SR) imaging of microvascular structures with unprecedented detail, by using microbubbles (MBs) as highly reflective contrast agents. After injection into the bloodstream, MBs are localized in US images to reconstruct the microvasculature. However, this technique faces a trade-off between MB localization accuracy and acquisition time. Perfusion with low MB concentrations reduces signal overlap and achieves high localization accuracy but requires extended acquisition times. Conversely, higher MB concentrations shorten acquisition times but increase signal overlap, limiting localization precision. Traditionally, ULM consists of five main steps: tissue filtering, MB detection, MB super-localization, tracking, and rendering. In this study, we present a novel approach that combines a robust principal component analysis (RPCA) with a computational SR technique, replacing the first three steps of ULM with a single process based on solving a SR inverse problem. This method isolates MB signals from background noise and enhances the localization of overlapping MBs, thereby improving overall ULM performance. Experimental results from simulated and in vivo data demonstrate that our proposed approach increases the SR factor by up to 30% and enhances the contrast ratio (CR) by 3.5 dB. It also produces comparable results across other image quality metrics. These improvements enable denser, higher-contrast vascular images.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32, 4059-4063
PlaSo: Unsupervised Residual Pl ug and Pl a y for Image S uper-Res o lution
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32, 4059-4063
PlaSo: Unsupervised Residual Pl ug and Pl a y for Image S uper-Res o lution
- 16 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 381-385
Automatic Tuning of Denoising Algorithms Parameters Without Ground Truth
Denoising is omnipresent in image processing. It is usually addressed with algorithms relying on a set of hyperparameters that control the quality of the recovered image. Manual tuning of those parameters can be a daunting task, which calls for the development of automatic tuning methods. Given a denoising algorithm, the best set of parameters is the one that minimizes the error between denoised and ground-truth images. Clearly, this ideal approach is unrealistic, as the ground-truth images are unknown in practice. In this work, we propose unsupervised cost functions—i.e., that only require the noisy image—that allow us to reach this ideal gold standard performance. Specifically, the proposed approach makes it possible to obtain an average PSNR output within less than 1% of the best achievable PSNR.
- 16 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 381-385
Automatic Tuning of Denoising Algorithms Parameters Without Ground Truth
Denoising is omnipresent in image processing. It is usually addressed with algorithms relying on a set of hyperparameters that control the quality of the recovered image. Manual tuning of those parameters can be a daunting task, which calls for the development of automatic tuning methods. Given a denoising algorithm, the best set of parameters is the one that minimizes the error between denoised and ground-truth images. Clearly, this ideal approach is unrealistic, as the ground-truth images are unknown in practice. In this work, we propose unsupervised cost functions—i.e., that only require the noisy image—that allow us to reach this ideal gold standard performance. Specifically, the proposed approach makes it possible to obtain an average PSNR output within less than 1% of the best achievable PSNR.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 156-160
Quantum Algorithm for Signal Denoising
This letter presents a novel quantum algorithm for signal denoising, which performs a thresholding in the frequency domain through amplitude amplification and using an adaptive threshold determined by local mean values. The proposed algorithm is able to process both classical and quantum signals. It is parametrically faster than previous classical and quantum denoising algorithms. Numerical results show that it is efficient at removing noise of both classical and quantum origin, significantly outperforming existing quantum algorithms in this respect, especially in the presence of quantum noise.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 156-160
Quantum Algorithm for Signal Denoising
This letter presents a novel quantum algorithm for signal denoising, which performs a thresholding in the frequency domain through amplitude amplification and using an adaptive threshold determined by local mean values. The proposed algorithm is able to process both classical and quantum signals. It is parametrically faster than previous classical and quantum denoising algorithms. Numerical results show that it is efficient at removing noise of both classical and quantum origin, significantly outperforming existing quantum algorithms in this respect, especially in the presence of quantum noise.
- 10 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (11) , 3278-3288
CX-DaGAN: Domain Adaptation for Pneumonia Diagnosis on a Small Chest X-Ray Dataset
Recent advances in deep learning led to several algorithms for the accurate diagnosis of pneumonia from chest X-rays. However, these models require large training medical datasets, which are sparse, isolated, and generally private. Furthermore, these models in medical imaging are known to over-fit to a particular data domain source, i.e., these algorithms do not conserve the same accuracy when tested on a dataset from another medical center, mainly due to image distribution discrepancies. In this work, a domain adaptation and classification technique is proposed to overcome the over-fit challenges on a small dataset. This method uses a private-small dataset (target domain), a public-large labeled dataset from another medical center (source domain), and consists of three steps. First, it performs a data selection of the source domain’s most representative images based on similarity constraints through principal component analysis subspaces. Second, the selected samples from the source domain are fit to the target distribution through an image to image translation based on a cycle-generative adversarial network. Finally, the target train dataset and the adapted images from the source dataset are used within a convolutional neural network to explore different settings to adjust the layers and perform the classification of the target test dataset. It is shown that fine-tuning a few specific layers together with the selected-adapted images increases the sorting accuracy while reducing the trainable parameters. The proposed approach achieved a notable increase in the target dataset’s overall classification accuracy, reaching up to 97.78% compared to 90.03% by standard transfer learning.
- 10 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (11) , 3278-3288
CX-DaGAN: Domain Adaptation for Pneumonia Diagnosis on a Small Chest X-Ray Dataset
Recent advances in deep learning led to several algorithms for the accurate diagnosis of pneumonia from chest X-rays. However, these models require large training medical datasets, which are sparse, isolated, and generally private. Furthermore, these models in medical imaging are known to over-fit to a particular data domain source, i.e., these algorithms do not conserve the same accuracy when tested on a dataset from another medical center, mainly due to image distribution discrepancies. In this work, a domain adaptation and classification technique is proposed to overcome the over-fit challenges on a small dataset. This method uses a private-small dataset (target domain), a public-large labeled dataset from another medical center (source domain), and consists of three steps. First, it performs a data selection of the source domain’s most representative images based on similarity constraints through principal component analysis subspaces. Second, the selected samples from the source domain are fit to the target distribution through an image to image translation based on a cycle-generative adversarial network. Finally, the target train dataset and the adapted images from the source dataset are used within a convolutional neural network to explore different settings to adjust the layers and perform the classification of the target test dataset. It is shown that fine-tuning a few specific layers together with the selected-adapted images increases the sorting accuracy while reducing the trainable parameters. The proposed approach achieved a notable increase in the target dataset’s overall classification accuracy, reaching up to 97.78% compared to 90.03% by standard transfer learning.
- Open Access
- 13 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1673-1676
Single Image Super-Resolution Of Noisy 3d Dental Ct Images Using Tucker Decomposition
Tensor decomposition has proven to be a strong tool in various 3D image processing tasks such as denoising and superresolution. In this context, we recently proposed a computationally effective, canonical polyadic decomposition (CPD) based algorithm for single image super-resolution. In this work, we investigated the added value brought by Tucker decomposition. While CPD allows a joint implementation of the denoising and deconvolution steps, with Tucker decomposition the denoising is followed by the deconvolution. This way the ill-posedness of the deconvolution caused by noise is partially mitigated. The results achieved using the two different tensor decomposition techniques were compared, and the robustness against noise was investigated. For validation, dental images were used. The superiority of the proposed method is shown in terms of peak signal-to-ratio, structural similarity index, the root canal segmentation accuracy, and runtime.
- 13 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1673-1676
Open AccessSingle Image Super-Resolution Of Noisy 3d Dental Ct Images Using Tucker Decomposition
Tensor decomposition has proven to be a strong tool in various 3D image processing tasks such as denoising and superresolution. In this context, we recently proposed a computationally effective, canonical polyadic decomposition (CPD) based algorithm for single image super-resolution. In this work, we investigated the added value brought by Tucker decomposition. While CPD allows a joint implementation of the denoising and deconvolution steps, with Tucker decomposition the denoising is followed by the deconvolution. This way the ill-posedness of the deconvolution caused by noise is partially mitigated. The results achieved using the two different tensor decomposition techniques were compared, and the robustness against noise was investigated. For validation, dental images were used. The superiority of the proposed method is shown in terms of peak signal-to-ratio, structural similarity index, the root canal segmentation accuracy, and runtime.
- Open Access
- 19 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 2, 190-206
Quantum Mechanics-Based Signal and Image Representation: Application to Denoising
Decomposition of digital signals and images into other basis or dictionaries than time or space domains is a very common approach in signal and image processing and analysis. Such a decomposition is commonly obtained using fixed transforms (e.g., Fourier or wavelet) or dictionaries learned from example databases or from the signal or image itself. In this work, we investigate in detail a new approach of constructing such a signal or image-dependent bases inspired by quantum mechanics tools, i.e., by considering the signal or image as a potential in the discretized Schroedinger equation. To illustrate the potential of the proposed decomposition, denoising results are reported in the case of Gaussian, Poisson, and speckle noise and compared to the state of the art algorithms based on wavelet shrinkage, total variation regularization or patch-wise sparse coding in learned dictionaries, non-local means image denoising, and graph signal processing.
- 19 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 2, 190-206
Open AccessQuantum Mechanics-Based Signal and Image Representation: Application to Denoising
Decomposition of digital signals and images into other basis or dictionaries than time or space domains is a very common approach in signal and image processing and analysis. Such a decomposition is commonly obtained using fixed transforms (e.g., Fourier or wavelet) or dictionaries learned from example databases or from the signal or image itself. In this work, we investigate in detail a new approach of constructing such a signal or image-dependent bases inspired by quantum mechanics tools, i.e., by considering the signal or image as a potential in the discretized Schroedinger equation. To illustrate the potential of the proposed decomposition, denoising results are reported in the case of Gaussian, Poisson, and speckle noise and compared to the state of the art algorithms based on wavelet shrinkage, total variation regularization or patch-wise sparse coding in learned dictionaries, non-local means image denoising, and graph signal processing.
- Open Access
Preconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images -- Extended Version
Joint deconvolution and segmentation of ultrasound images is a challenging problem in medical imaging. By adopting a hierarchical Bayesian model, we propose an accelerated Markov chain Monte Carlo scheme where the tissue reflectivity function is sampled thanks to a recently introduced proximal unadjusted Langevin algorithm. This new approach is combined with a forward-backward step and a preconditioning strategy to accelerate the convergence, and with a method based on the majorization-minimization principle to solve the inner nonconvex minimization problems. As demonstrated in numerical experiments conducted on both simulated and in vivo ultrasound images, the proposed method provides high-quality restoration and segmentation results and is up to six times faster than an existing Hamiltonian Monte Carlo method.
Open AccessPreconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images -- Extended Version
Joint deconvolution and segmentation of ultrasound images is a challenging problem in medical imaging. By adopting a hierarchical Bayesian model, we propose an accelerated Markov chain Monte Carlo scheme where the tissue reflectivity function is sampled thanks to a recently introduced proximal unadjusted Langevin algorithm. This new approach is combined with a forward-backward step and a preconditioning strategy to accelerate the convergence, and with a method based on the majorization-minimization principle to solve the inner nonconvex minimization problems. As demonstrated in numerical experiments conducted on both simulated and in vivo ultrasound images, the proposed method provides high-quality restoration and segmentation results and is up to six times faster than an existing Hamiltonian Monte Carlo method.