Michel Salomon
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
Michel Salomon has a total of 128 co-authors. Here are the top co-authors by number of shared publications:
- Christophe Guyeux
University of Franche-Comte
14 shared publications - Raphaël Couturier
CNRS, Institut FEMTO-ST, Universite Marie et Louis Pasteur, Belfort, France
12 shared publications - Bassam AlKindy
University of Mustansiriyah
11 shared publications - Jean-François Couchot
FEMTO-ST Institute, UMR 6174 CNRS, DISC Computer Science Department, Univ. Bourgogne Franche-Comté (UBFC), 16 Route de Gray, Besançon, 25000, France
8 shared publications J. Henriet
6 shared publicationsL. Makovicka
Chrono-Environnement Laboratory, UMR 6249 CNRS, University of Franche-Comté, BP 71427, Pôle Universitaire des Portes du Jura, 25211 Montbéliard Cedex, France
6 shared publications
Latest Publications
- 3 November 2025
- Published by Elsevier in Aerospace Science and Technology
- Vol. 168
Machine learning techniques for detecting anomalies in ADS-B data in the context of low altitude aviation
- 3 November 2025
- Published by Elsevier in Aerospace Science and Technology
- Vol. 168
Machine learning techniques for detecting anomalies in ADS-B data in the context of low altitude aviation
- Open Access
- 29 April 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 154
A novel adaptive noise model selection framework for blind denoising of Scanning Electron Microscopy images
- 29 April 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 154
Open AccessA novel adaptive noise model selection framework for blind denoising of Scanning Electron Microscopy images
- 1 July 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (4) , 1-20
Towards scanning electron microscopy image denoising: a state-of-the-art overview, benchmark, taxonomies, and future direction
- 1 July 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (4) , 1-20
Towards scanning electron microscopy image denoising: a state-of-the-art overview, benchmark, taxonomies, and future direction
- 19 January 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 218
Deep learning and gradient boosting for urban environmental noise monitoring in smart cities
- 19 January 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 218
Deep learning and gradient boosting for urban environmental noise monitoring in smart cities
- 24 March 2022
- Published by Elsevier in Medical Image Analysis
- Vol. 79, 102428
Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
- 24 March 2022
- Published by Elsevier in Medical Image Analysis
- Vol. 79, 102428
Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
- 26 November 2021
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 95, 102014
Automatic deep learning-based myocardial infarction segmentation from delayed enhancement MRI
- 26 November 2021
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 95, 102014
Automatic deep learning-based myocardial infarction segmentation from delayed enhancement MRI
- Open Access
Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed several minutes after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between normal and pathological cases. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.
Open AccessDeep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed several minutes after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between normal and pathological cases. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.
- Open Access
- 8 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 231-235
Using Deep Learning for Object Distance Prediction in Digital Holography
Deep Learning (DL) has marked the beginning of a new era in computer science, particularly in Machine Learning (ML). Nowadays, there are many fields where DL is applied such as speech recognition, automatic navigation systems, image processing, etc [1]. In this paper, a Convolutional Neural Network (CNN), more precisely a CNN built on top of DenseNet169, is proven to be helpful in predicting object distance in computer-generated holographic images. The problem is addressed as a classification problem where 101 classes of images were generated, each class corresponding to a different distance value from the object at a micrometer scale. Experiments show that the proposed network is efficient in this context, being able to classify with a 100% accuracy level if trained properly.
- 8 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 231-235
Open AccessUsing Deep Learning for Object Distance Prediction in Digital Holography
Deep Learning (DL) has marked the beginning of a new era in computer science, particularly in Machine Learning (ML). Nowadays, there are many fields where DL is applied such as speech recognition, automatic navigation systems, image processing, etc [1]. In this paper, a Convolutional Neural Network (CNN), more precisely a CNN built on top of DenseNet169, is proven to be helpful in predicting object distance in computer-generated holographic images. The problem is addressed as a classification problem where 101 classes of images were generated, each class corresponding to a different distance value from the object at a micrometer scale. Experiments show that the proposed network is efficient in this context, being able to classify with a 100% accuracy level if trained properly.
- Open Access
Emidec: A Database Usable for the Automatic Evaluation of Myocardial Infarction from Delayed-Enhancement Cardiac MRI
One crucial parameter to evaluate the state of the heart after myocardial infarction (MI) is the viability of the myocardial segment, i.e., if the segment recovers its functionality upon revascularization. MRI performed several minutes after the injection of a contrast agent (delayed enhancement-MRI or DE-MRI) is a method of choice to evaluate the extent of MI, and by extension, to assess viable tissues after an injury. The Emidec dataset is composed of a series of exams with DE-MR images in short axis orientation covering the left ventricle from normal cases or patients with myocardial infarction, with the contouring of the myocardium and diseased areas (if present) from experts in the domains. Moreover, classical available clinical parameters when the patient is managed by an emergency department are provided for each case. To the best of our knowledge, the Emidec dataset is the first one where annotated DE-MRI are combined with clinical characteristics of the patient, allowing the development of methodologies for exam classification as for exam quantification.
Open AccessEmidec: A Database Usable for the Automatic Evaluation of Myocardial Infarction from Delayed-Enhancement Cardiac MRI
One crucial parameter to evaluate the state of the heart after myocardial infarction (MI) is the viability of the myocardial segment, i.e., if the segment recovers its functionality upon revascularization. MRI performed several minutes after the injection of a contrast agent (delayed enhancement-MRI or DE-MRI) is a method of choice to evaluate the extent of MI, and by extension, to assess viable tissues after an injury. The Emidec dataset is composed of a series of exams with DE-MR images in short axis orientation covering the left ventricle from normal cases or patients with myocardial infarction, with the contouring of the myocardium and diseased areas (if present) from experts in the domains. Moreover, classical available clinical parameters when the patient is managed by an emergency department are provided for each case. To the best of our knowledge, the Emidec dataset is the first one where annotated DE-MRI are combined with clinical characteristics of the patient, allowing the development of methodologies for exam classification as for exam quantification.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Myocardial Infarction Segmentation From Late Gadolinium Enhancement MRI By Neural Networks and Prior Information
In this paper, we propose an automatic myocardial infarction segmentation framework from Delayed Enhancement cardiac MRI (DE-MRI) using a convolutional neural network (CNN) and prior information-based post-treatments. The work was conducted on our DE-MRI dataset, which is collected from daily clinical practice. 195 cases of DE-MRI examinations constitute this dataset, including on average 7 images per case with manually drawn contours by an expert. The objective is to automatically segment myocardial infarctions on both healthy and pathological images in the dataset. In the proposed framework, a downsampling-upsampling segmentation CNN firstly generates high recall segmentations of myocardial infarction from left ventricle DE-MR images, then the proposed prior information-based post-processing method identifies and removes false-positive segmentations from the CNN’s prediction. To obtain a high recall prediction, two U-NET like semantic segmentation networks are investigated: CE-NET and its backbone with Dice loss and Stochastic Gradient Descent (SGD) using a batch size of value 1. The prior information-based post-processing evaluates every single contour in the CNN’s segmentations: region features in each contour are compared to criteria which are firstly estimated based on the training set images and eventually fine-tuned based on the validation set images. All non-conforming contours are removed from the predictions to improve the accuracy of the segmentation. Combining the high recall networks and prior postprocessing information, we achieve segmentation results comparable to those produced by human experts.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Myocardial Infarction Segmentation From Late Gadolinium Enhancement MRI By Neural Networks and Prior Information
In this paper, we propose an automatic myocardial infarction segmentation framework from Delayed Enhancement cardiac MRI (DE-MRI) using a convolutional neural network (CNN) and prior information-based post-treatments. The work was conducted on our DE-MRI dataset, which is collected from daily clinical practice. 195 cases of DE-MRI examinations constitute this dataset, including on average 7 images per case with manually drawn contours by an expert. The objective is to automatically segment myocardial infarctions on both healthy and pathological images in the dataset. In the proposed framework, a downsampling-upsampling segmentation CNN firstly generates high recall segmentations of myocardial infarction from left ventricle DE-MR images, then the proposed prior information-based post-processing method identifies and removes false-positive segmentations from the CNN’s prediction. To obtain a high recall prediction, two U-NET like semantic segmentation networks are investigated: CE-NET and its backbone with Dice loss and Stochastic Gradient Descent (SGD) using a batch size of value 1. The prior information-based post-processing evaluates every single contour in the CNN’s segmentations: region features in each contour are compared to criteria which are firstly estimated based on the training set images and eventually fine-tuned based on the validation set images. All non-conforming contours are removed from the predictions to improve the accuracy of the segmentation. Combining the high recall networks and prior postprocessing information, we achieve segmentation results comparable to those produced by human experts.