0000000000326931
AUTHOR
Anis Sakly
showing 13 related works from this author
Robustly correlated key‐medical image for DNA‐chaos based encryption
2021
Abstract Medical images include confidential and sensitive information about patients. Hence, ensuring the security of these images is a crucial requirement. This paper proposes an efficient and secure medical image encryption‐decryption scheme based on deoxyribonucleic acid (DNA), one‐dimensional chaotic maps (tent and logistic maps), and hash functions (SHA‐256 and MD5). The first part of the proposed scheme is the key generation based on the hash functions of the image and its metadata. The key then is highly related and intensely sensitive to the original image. The second part is the rotation and permutation of the first two MSB bit‐plans of the medical image to reduce its black backgr…
An intelligent Proportional controller of a Seeded Batch Crystallizer
2020
Crystallization process is used in a very wide range of industrial applications. However, highly nonlinear comportment of such process and the difficulties of characterizing several phenomenological effects makes difficult to find suitable operational procedures for producing required products. In this article, we use a model-free control (MFC) for controlling the mean size of crystals produced by seeded batch cooling crystallization. The MFC method is distinguished notably in terms of the modeling strategy. Rather than developing a crystallization model within the classic population balance equation (PBE) together with the mass balance and the energy balance, as is usually done, we use a l…
Enhancement and assessment of WKS variance parameter for intelligent 3D shape recognition and matching based on MPSO
2016
This paper presents an improved wave kernel signature (WKS) using the modified particle swarm optimization (MPSO)-based intelligent recognition and matching on 3D shapes. We select the first feature vector from WKS, which represents the 3D shape over the first energy scale. The choice of this vector is to reinforce robustness against non-rigid 3D shapes. Furthermore, an optimized WKS-based method for extracting key-points from objects is introduced. Due to its discriminative power, the associated optimized WKS values with each point remain extremely stable, which allows for efficient salient features extraction. To assert our method regarding its robustness against topological deformations,…
Controlling muscular force by functional electrical stimulation using intelligent PID
2015
Functional Electrical Stimulation (FES) appears as a way of extremely promising research today to solve numerous pathology connected to the deficiencies of the nervous system. It is usually used for the rehabilitation of people with neurological disorders. Generally, skeletal muscles are activated by using Constant Frequency Trains (CFTs) with a fixed amplitude and inter-pulse duration. In addition, the systems of electrical stimulation do not adapt the parameters stimulation to obtain a desired force response during the rehabilitation session. The purpose of this study is to adapt automatically the stimulation parameters to the force desired by the clinician with an intelligent PID control…
A 3D deep learning approach based on Shape Prior for automatic segmentation of myocardial diseases
2020
Accurate three-dimensional (3D) cardiac segmentation from late gadolinium enhancement (LGE)-MRI plays a critical role in designing a structure of reference for diagnosing many cardiac pathologies such as ischemia, myocarditis and myocardial infarction. This segmentation is however still a non-trivial task, due to the motion artifacts during acquisition, and heterogeneous intensity distributions. In this study, we develop a fully 3D automated model based on deep neural networks (DNN) for LGE-MRI myocardial pathologies (scar and No-reflow tissues) segmentation in a new expert annotated dataset. Considering that damaged tissue constitutes a small area of the whole LGE-MRI, we concentrated on m…
Model Free Control for muscular force by Functional Electrical Stimulation using pulse width modulation
2016
International audience; Functional Electrical Stimulation (FES) is a useful technique for restoring functions for patients with neurological disorders. Muscle activities can be artificially driven through delivery of electrical pulses to skeletal muscles. Typically, muscles are activated by using constant stimulation train with a fixed parameters (amplitude, frequency and pulse width). In addition, the FES systems do not adapt the parameters stimulation to obtain a desired force response during the rehabilitation session. The purpose of this study is to investigate a real-time FES system for adapting automatically the stimulation parameters (stimulation pulse width) to track a desired force…
Model predictive control for continuous lactide ring‐opening polymerization processes
2020
International audience; Polylactic acid (PLA) is an attractive environment-friendly thermoplastic that is bio-sourced and biodegradable. PLA is industrially produced by the ring-opening polymerization of Lactide. This reaction is sensitive to drifts in the operating conditions and impurities in the raw materials that may affect the reaction rate as well as the polymer properties, which can be very costly in continuous processes. It is therefore crucial to employ a control strategy that allows recovering the nominal conditions and maintaining the desired properties and conversion level in case of drift. Three control strategies are discussed in this paper: Proportional-Integral controller (P…
A more distinctive representation for 3D shape descriptors using principal component analysis
2015
Many researchers have used the Heat Kernel Signature (or HKS) for characterizing points on non-rigid three-dimensional shapes and Classical Multidimensional Scaling (Classical MDS) method in object classification which we quote, in particular, the example of Jian Sun et al. (2009) [1]. However, in this paper, the main focuses on classification that we propose a concise and provably factorial method by invoking Principal Component Analysis (PCA) as a classifier to improve the scheme of 3D shape classification. To avoid losing or disordering information after extracting features from the mesh, PCA is used instead of the Classical MDS to discriminate-as much as possible-feature points for each…
A 3D Network Based Shape Prior for Automatic Myocardial Disease Segmentation in Delayed-Enhancement MRI
2021
Abstract Objectives: In this work, a new deep learning model for relevant myocardial infarction segmentation from Late Gadolinium Enhancement (LGE)-MRI is proposed. Moreover, our novel segmentation method aims to detect microvascular-obstructed regions accurately. Material and methods: We first segment the anatomical structures, i.e., the left ventricular cavity and the myocardium, to achieve a preliminary segmentation. Then, a shape prior based framework that fuses the 3D U-Net architecture with 3D Autoencoder segmentation framework to constrain the segmentation process of pathological tissues is applied. Results: The proposed network reached outstanding myocardial segmentation compared wi…
Dynamic optimization of a continuous Lactide ring-opening polymerization process
2019
An increasing attention has been paid to the production of the polylactic acid (PLA) in recent years, owing to its properties as a biodegradable thermoplastic besides the fact that it is derived from renewable resources. PLA is industrially produced by ring opening polymerization of lactide. This reaction is sensitive to deviations in the operating conditions that highly affect the reaction rate and the polymer properties. Therefore, a process monitoring and control policy is crucial in order to restore the nominal conditions in case of drift. In this paper, a continuous PLA process is considered with three cascade reactors, two tubular and one loop reactor, that is described by partial dif…
Estimation of the mean crystal size and the moments of the crystal size distribution in batch crystallization processes
2016
International audience; A cascade high gain observer is designed to estimate the first four leading moments of the crystal size distribution (CSD) and the mean crystal size in batch crystallization processes. The proposed observer is based on a well-known transformation of the partial differential equation describing the CSD to a set of ordinary differential equations (the method of moments). Due to numerical difficulties resulting from the important differences in the magnitudes of the moments, a set of new variables is computed to allow a good estimation of the moments and thus the mean crystal size. In this work, only solute concentration and crystallizer temperature are used to estimate…
A deep learning approach for the segmentation of myocardial diseases
2021
Cardiac left ventricular (LV) segmentation is a paramount essential step for both diagnosis and treatment of cardiac pathologies such as ischemia, myocardial infarction, arrhythmia and myocarditis. However, this segmentation is challenging due to high variability across patients and the potential lack of contrast between structures. In this work, we propose and evaluate a (2.5D) SegU-Net model based on the fusion of two deep learning segmentation techniques (U-Net and Seg-Net) for automated LGE-MRI (Late gadolinium enhanced magnetic resonance imaging) myocardial disease (infarct core and no-reflow region) quantification in a new multifield expert annotated dataset. Given that the scar tissu…
Efficient 3D Deep Learning for Myocardial Diseases Segmentation
2021
Automated myocardial segmentation from late gadolinium enhancement magnetic resonance images (LGE-MRI) is a critical step in the diagnosis of cardiac pathologies such as ischemia and myocardial infarction. This paper proposes a deep learning framework for improved myocardial diseases segmentation. In the first step, we build an encoder-decoder segmentation network that generates myocardium and cavity segmentations from the whole volume, followed by a 3D U-Net based on Shape prior to identifying myocardial infarction and myocardium ventricular obstruction (MVO) segmentations from the encoder-decoder prediction. The proposed network achieves good segmentation performance, as computed by avera…