Abed Malti | Université Abou Bekr Belkaid Tlemcen (original) (raw)

Papers by Abed Malti

International Journal of Computer Assisted Radiology and Surgery, Jan 25, 2023

International Journal for Numerical Methods in Biomedical Engineering

In this paper, we propose a new method to reduce the computational complexity of calculating the ... more In this paper, we propose a new method to reduce the computational complexity of calculating the tangential stiffness matrix in a nonlinear finite element formulation. Our approach consists in partially updating the tangential stiffness matrix during a classic Newton–Raphson iterative process. The complexity of such an update process has the order of the number of mesh vertices to the power of two. With our approach, this complexity is reduced to the power of two of only the number of updated vertices. We numerically study the convergence of the solution with our modified algorithm. We describe the deformation through a strain energy density function which is defined with respect to the Lagrangian strain. We derive the conditions of convergence for a given tangential stiffness matrix and a given set of updated vertices. We use nonlinear geometric deformation and the nonlinear Mooney‐Rivilin model with both tetrahedron and hexahedron element meshing. We provide extensive results usin...

In this work, we propose to use recurrent neural network (RNN) architecture to provide a dynamic ... more In this work, we propose to use recurrent neural network (RNN) architecture to provide a dynamic evaluation of performing surgery tasks. The task is considered to be known and is represented by a sequence of kinematic data recorded from DaVinci Robot. The sequence of output represents a dynamic evaluation which gets updated while the sequence of input is feeded to the RNN. To train the RNN we use three levels of skills: expert, intermediate and novice to which we associate three scores: 1, 0.7 and 0.4 respectively. We test the performance of the proposed method on three different surgical gestures: knot tying, needle passing and suturing. We use one RNN per-gesture which we train with the corresponding data from JIGSAWS; a publicly available dataset of surgery tasks. We compare this approach with a static method that uses Deep Neural Network which provides a global score of the whole surgery task.

Magnification-continuous static calibration model of a scanning-electron microscope

arXiv: Computer Vision and Pattern Recognition, Jul 9, 2019

In this paper, we address the problem of exact recovery condition in retrieving 3D human motion f... more In this paper, we address the problem of exact recovery condition in retrieving 3D human motion from 2D landmark motion. We use a skeletal kinematic model to represent the 3D human motion as a vector of angular articulation motion. We address this problem based on the observation that at high tracking rate, regardless of the global rigid motion, only few angular articulations have non-zero motion. We propose a first ideal formulation with 0-norm to minimize the cardinal of non-zero angular articulation motion given an equality constraint on the time-differentiation of the reprojection error. The second relaxed formulation relies on an 1-norm to minimize the sum of absolute values of the angular articulation motion. This formulation has the advantage of being able to provide 3D motion even in the under-determined case when twice the number of 2D landmarks is smaller than the number of angular articulations. We define a specific property which is the Projective Kinematic Space Property (PKSP) that takes into account the reprojection constraint and the kinematic model. We prove that for the relaxed formulation we are able to recover the exact 3D human motion from 2D landmarks if and only if the PKSP property is verified. We further demonstrate that solving the relaxed formulation provides the same ground-truth solution as the ideal formulation if and only if the PKSP condition is filled. Results with simulated sparse skeletal angular motion show the ability of the proposed method to recover exact location of angular motion. We provide results on publicly available real data (HUMAN3.6M, PANOPTIC and MPI-I3DHP).

Advanced Intelligent Systems for Sustainable Development (AI2SD’2020), 2022

Advances in Intelligent Systems and Computing, 2019

Many studies on surgical skill analysis have reported results on classification of different skil... more Many studies on surgical skill analysis have reported results on classification of different skills. However, regardless of the classification problem, only few of them have addressed the problem of task evaluation. In this paper, we propose a simple and computationally lightweight neural network to provide evaluation scores on a given surgery task. The used neural network has three hidden layers and one output node. The output is trained so that it fits average scores of performance on a single known surgery task. Three levels of performance are used: expert, intermediate and novice. We evaluate the performance of the proposed approach on three different surgical gestures: knot-tying, needle passing and suturing. To each surgery gesture, we associate one instantiation of the designed network, which is trained with the corresponding data. We show that this method gives evaluation scores that are more plausible than a single network, which is requested to provide evaluation scores for different tasks.

The International Journal of Medical Robotics and Computer Assisted Surgery, 2013

Background In this paper, we propose a non-linear calibration method for handeye system equipped ... more Background In this paper, we propose a non-linear calibration method for handeye system equipped with a camera undergoing radial distortion as the rigid endoscope. Whereas classic methods propose either a separated estimation of the camera intrinsics and the hand-eye transform or a mixed non-linear estimation of both hand-eye and camera intrinsics assuming a pin-hole model, the proposed approach enables a simultaneous refinement of the hand-eye and the camera parameters including the distortion factor with only three frames of the calibrated pattern. Methods Our approach relies on three steps: (i) linear initial estimates of hand-eye and radial distortion with minimum number of frames: one single image to estimate the radial distortion and three frames to estimate the initial hand-eye transform, (ii) we propose to express the camera extrinsic with respect to hand-eye and world-grid transforms and (iii) we run bundle adjustment on the reprojection error with respect to the distortion parameters, the camera intrinsics and the hand-eye transform. Results Our method is quantitatively compared with state-of-the-art linear and non-linear methods. We show that our method provides a 3D reconstruction error of approximately 5% of the size of the 3D shape. Conclusions Our experimental results show the effectiveness of simultaneously estimating hand-eye and distortion parameters for 3D reconstruction.

IEEE Transactions on Biomedical Engineering, 2014

We propose a new monocular 3-D reconstruction method adapted for reconstructing organs in the abd... more We propose a new monocular 3-D reconstruction method adapted for reconstructing organs in the abdominal cavity. It combines both motion and shading cues. The former uses a conformal deformation prior and the latter the Cook-Torrance reflectance model. Our method runs in two phases: first, a 3-D geometric and photometric template of the organ at rest is reconstructed in vivo. The geometric shape is reconstructed using rigid shape-from-motion while the surgeon is exploring-but not deforming-structures in the abdominal cavity. This geometric template is then used to retrieve the photometric properties. A nonparametric model of the light's direction of the laparoscope and the Cook-Torrance reflectance model of the organ's tissue are estimated. Second, the surgeon manipulates and deforms the environment. Here, the 3-D template is conformally deformed to globally match a set of few correspondences between the 2-D image data provided by the monocular laparoscope and the 3-D template. Then, the coarse 3-D shape is refined using shading cues to obtain a final 3-D deformed shape. This second phase only relies on a single image. Therefore, it copes with both sequential processing and selfrecovery from tracking failure. The proposed approach has been validated using 1) ex vivo and in vivo data with ground-truth, and 2) in vivo laparoscopic videos of a patient's uterus. Our experimental results illustrate the ability of our method to reconstruct natural 3-D deformations typical in real surgical procedures.

One of the current limits of laparosurgery is the absence of a 3D vision facility for standard la... more One of the current limits of laparosurgery is the absence of a 3D vision facility for standard laparoscopes. While there has been significant progress made in visual SLAM (Simultaneous Localization And Mapping) with a single camera, most of the current approaches relies on the assumption that the tissues are rigid or undergo a cyclic deformation. However, in laparoscopic surgery none of these assumptions commonly apply, due to unpredictable and non-isometric deformation of the tissues. Our main contribution in this paper is a new sequential 3D reconstruction method well-adapted to the peritoneal environment. We draw on recent computer vision results exploiting a template of the environment. The state-of-the-art methods assume that the environment can be modeled as an isometric developable surface, i.e. which deforms isometrically to a plane. While this assumption holds for paper-like surfaces, it certainly does not fit for peritoneal surfaces. Our new method tackle these limits: it uses a full 3D template and copes with non-isometric 3D deformations, thanks to two phases. First the 3D template is reconstructed using rigid SfM (Shape-from-Motion) while the surgeon is exploring-but not deforming-the peritoneal environment. Second the 3D template is used during surgery to infer a quasi-conformal deformation to the current 3D shape from a single laparoscopic image only. This makes both sequential processing and effective self-recovery from tracking errors possible. The proposed approach has been validated on in-vivo laparoscopic videos of the abdominal wall and a uterus. Experimental results illustrate the ability of our method to deal with extensible deformations of the tissues.

Lecture Notes in Computer Science, 2012

Shape-from-Shading (SfS) is one of the fundamental techniques to recover depth from a single view... more Shape-from-Shading (SfS) is one of the fundamental techniques to recover depth from a single view. Such a method has shown encouraging but limited results in laparoscopic surgery due to the complex reflectance properties of the organ tissues. On the other hand, Template-Based Deformable-Shape-from-Motion (DSfM) has been recently used to recover a coarse 3D shape in laparoscopy. We propose to combine both geometric and photometric cues to robustly reconstruct 3D human organs. Our method is dubbed Deformable-Shape-from-Motionand-Shading (DSfMS). It tackles the limits of classical SfS and DSfM methods: First the photometric template is reconstructed using rigid SfM (Shape-from-Motion) while the surgeon is exploring-but not deforming-the peritoneal environment. Second a rough 3D deformed shape is computed using a recent method for elastic surface from a single laparoscopic image. Third a fine 3D deformed shape is recovered using shading and specularities. The proposed approach has been validated on both synthetic data and in-vivo laparoscopic videos of a uterus. Experimental results illustrate its effectiveness compared to SfS and DSfM.

Resources, Conservation and Recycling, 2018

Abstract The circular economy system represents the generation of opportunities in production cha... more Abstract The circular economy system represents the generation of opportunities in production chains. This is to ensure that product development can adjust to natural cycles, seeking minimization of the negative externalities of production processes. In Brazil, circular economy models are still incipient and need identification and articulation of actions that will be coordinated by companies. Starting with the endogenous characteristics of interaction and cooperation related to the composition of local arrangements, this study aims to contribute to the expansion of the circular economy in Brazil by identifying the challenges and opportunities for a furniture cluster. Methodological strategies included data triangulation using document analyses, observation of visual communication materials, and inquiry in companies of local productive arrangements of furniture. The study encompasses 23 companies specializing in wooden furniture situated in five different cities, and it uses a local furniture company as the benchmark. The results indicate the extent to which companies adhere to the strategic guidelines for a circular economy in the cluster context and identify the disposal mode and final destination for the main solid residues generated by the industries. This approach makes it possible to certify the potential for development and consolidation of the circular economy actions in the local productive arrangement.

We propose a new approach for template-based extensi-ble surface reconstruction from a single vie... more We propose a new approach for template-based extensi-ble surface reconstruction from a single view. We extend the method of isometric surface reconstruction and more recent work on conformal surface reconstruction. Our approach relies on the minimization of a proposed stretching energy formalized with respect to the Poisson ratio parameter of the surface. We derive a patch-based formulation of this stretching energy by assuming local linear elasticity. This formulation unifies geometrical and mechanical constraints in a single energy term. We prevent local scale ambiguities by imposing a set of fixed boundary 3D points. We experi-mentally prove the sufficiency of this set of boundary points and demonstrate the effectiveness of our approach on differ-ent developable and non-developable surfaces with a wide range of extensibility. 1.

The study of anatomy has always been reliant on the imagination as images don’t convey enough inf... more The study of anatomy has always been reliant on the imagination as images don’t convey enough information and the creation of realistic models can be too expensive. A Virtual Reality (VR) application can be an excellent gap filling solution to this issue. It allows the students to interact with 3D realistic models of any organ. It displays several cases on each organ with minimal cost. In this paper, we propose a fully developed VR platform for academic training in human anatomy. We draw the complete pipeline from organ’s data acquisition to multi-user interface in VR environment. The final software allows full interactivity student-organ and student-tutor or student-student.

Planifier un chemin geometrique pour un robot d'une configuration initiale a une configuratio... more Planifier un chemin geometrique pour un robot d'une configuration initiale a une configuration initiale est aujourd'hui un probleme quasiment resolu moyennant une representation geometrique de l'environnement statique du robot, une modelisation de la chaine cinematique du robot et de ses contraintes cinematiques. L'execution de tels chemins en environnement reel est en revanche un probleme qui est loin d'etre resolu malgre une litterature fournie sur le sujet. De nombreuses raisons expliquent cette difficulte parmi lesquelles l'inexactitude des modeles d'environnement utilises et des moyens de localisation. L'objectif de notre travail est de proposer une approche generique de planification de mouvements references sur des amers. Le principe de notre approche consiste a associer a une trajectoire geometrique sans collision des couples amers-capteurs qui pendant l'execution sont utilises pour asservir localement le mouvement du robot. Cette approche...

SfS (Shape-from-Shading) and view synthesis systems gener ally assume a diffuse reflection model ... more SfS (Shape-from-Shading) and view synthesis systems gener ally assume a diffuse reflection model of the in-vivo tissues where t he light is equally reflected in all directions. In other words, they approximat e the tissue’s BRDF (Bidirectional Reflectance Distribution Function) by the L ambertian model. This is however a coarse assumption since most tissues cast specu larities. We propose a method to estimate the reflectance properties of ti sues from invivo laparoscopic images. We use the Cook-Torrance BRDF mod el in order to take into account both diffuse and specular properties of th e tissues. Our method estimates online both the BRDF parameters of the observed or gan and the light model of the laparoscope. Such an estimation requires the kn owledge of the 3D shape and some geometric priors on the light source. For thes e rea ons, our estimation method relies on two assumptions: firstly, that the ti ssues undergoes rigid motion when the surgeon only explores it, and secondly tha...

Current Elastic SfT (Shape from Template) methods are based on l2-norm minimization. None can acc... more Current Elastic SfT (Shape from Template) methods are based on l2-norm minimization. None can accurately recover the spatial location of the acting forces since l2-norm based minimization tends to find the best tradeoff among noisy data to fit an elastic model. In this work, we study shapes that are deformed with spatially sparse set of forces. We propose two formulations for a new class of SfT problems dubbed here SLE-SfT (Sparse Linear Elastic-SfT). The First ideal formulation uses an l0-norm to minimize the cardinal of non-zero components of the deforming forces. The second relaxed formulation uses an l1-norm to minimize the sum of absolute values of force components. These new formulations do not use Solid Boundary Constraints (SBC) which are usually needed to rigidly position the shape in the frame of the deformed image. We introduce the Projective Elastic Space Property (PESP) that jointly encodes the reprojection constraint and the elastic model. We prove that filling this pr...