eLearning

Low-level segmentation of 3-D magnetic resonance brain images-a rule-based system

S. P. Raya IEEE Transactions on Medical Imaging, 1990

A rule-based, low-level segmentation system that can automatically identify the space occupied by different structures of the brain by magnetic resonance imaging (MRI) is described. Given three-dimensional image data as a stack of slices, it can extract brain parenchyma, cerebro-spinal fluid, and high- intensity abnormalities. The multiple feature environment of MR imaging is used to comput several low-level features to ...

A Conceptual Model for Segmentation of Multiple Scleroses Lesions in Magnetic Resonance Images Using Massive Training Artificial Neural Network

Hassan Khastavaneh; Habibollah Haron 2014 5th International Conference on Intelligent Systems, Modelling and Simulation, 2014

Detecting abnormalities in medical images is one application of image segmentation. MRI as an imaging technique sensitive to soft tissues such as brain shows Multiple Scleroses lesions as hyper-intense or hypo-intense signals. As manual segmentation of these lesions is a laborious and time consuming task, many methods for automatic brain lesion segmentation have been proposed. To tackle difficulties of Multiple ...

Deformation analysis to detect and quantify active lesions in three-dimensional medical image sequences

J. -P. Thirion; G. Calmon IEEE Transactions on Medical Imaging, 1999

Evaluating precisely the temporal variations of lesion volumes is very important for at least three types of practical applications: pharmaceutical trials, decision making for drug treatment or surgery, and patient follow-up. Here, the authors present a volumetric analysis technique, combining precise rigid registration of three-dimensional (3-D) (volumetric) medical images, nonrigid deformation computation, and flow-field analysis. Their analysis technique has two ...

Detection of hyperintense regions on MR brain images using a Mamdani type Fuzzy Rule-Based System: Application to the detection of small multiple sclerosis lesions

F. X. Aymerich; P. Sobrevilla; E. Montseny; A. Rovira 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011), 2011

In this paper we present an algorithm for detecting hyperintense regions in brain images acquired by Magnetic Resonance Imaging. The work is part of a more general research oriented to the design of support tools that assist the healthcare experts in their research activities on brain diseases. The algorithm has been focused on the detection of small multiple sclerosis lesions ...

Haptic linear paths for arm rehabilitation in MS patients

Joan De Boeck; Sofie Notelaers; Chris Raymaekers; Karin Coninx 2009 IEEE International Workshop on Haptic Audio visual Environments and Games, 2009

Force feedback in the context of a rehabilitation program may have its benefits. The generated forces can be used to assist, support or oppose the patients according to their personal needs and abilities. Using the Phantom haptic device, we conducted a pilot study focussing on the rehabilitation of the upper limbs in MS patients. Apart from the promising clinical results, ...

More eLearning Resources

IEEE-USA E-Books

• Propagation of the Action Potential

  There are two types of regenerating nerve fibers: unmyelinated and myelinated. Unmyelinated fibers are generally small (diameter up to 0.0013 mm or 0.00005 in.) and have a slow speed [up to 1.5 meters/second (m/s) or 3.2 mph]. Two- thirds of the fibers in the body are of this type; they are used for chores for which low speed is adequate, such as the reporting of pain and temperature. A regenerating axon fires (starts to generate an action potential [AP]) when the voltage across the membrane rises above a threshold level such as 8 mV. The AP propagates like an ocean wave; the conduction speed of an unmyelinated fiber is determined by the forward speed of the wavefront at the 8-mV level. Myelinated fibers are relatively large (diameter up to 0.022 mm or 0.0009 in.) and have a high speed (up to 130 m/s or 290 miles per hour [mph]). They are used for the retrieval and processing of information where high speed is vital. A myelinated fiber is high speed because its membrane is relatively thick, but it is interrupted by nodes at which the AP is regenerated. The conduction speed is determined by the time taken for the AP to reach the 8-mV level from one node to the next. This time is approximately constant, 17 µs, regardless of nerve fiber diameter. Nonregenerative or weakly regenerative sections of nerve fiber are reflected in lower-than-normal conduction speeds; this is important clinical evidence for nerve dysfunction, such as in multiple sclerosis.

• Robot-Assisted Neurorehabilitation

  This chapter addresses the use of robots to facilitate the recovery of neuromotor functions. Early approaches to robot-based therapy were mostly empirical and limited by the available hardware, designed for industrial applications. More recent applications build on the current understanding of the physiology of the reorganization of the nervous system following a lesion. The chapter focuses on rehabilitation of the upper limb, but similar principles are applicable to the lower limb. It addresses the neuromotor recovery of chronic stroke survivors and examines two case studies in more detail. Then, the chapter discusses the available evidence on the efficacy of robot therapy. Finally, it suggests that robots may be potentially useful in the context of other neurological diseases, for example, multiple sclerosis and cerebral palsy.

• Diseases and Injuries of the Central Nervous System Leading to Sensory-Motor Impairment

  Damage to the central and peripheral nervous systems is associated with a loss of motor drive and a defective afferent input to the central nervous system (CNS). This chapter starts with a presentation of neuron injury. The injuries are categorized based on the extent and type of damage to the nerve and the surrounding connective tissue. The chapter addresses sensory - motor deficits that are caused by neuron injury or disease: (a) cerebrovascular accident (CVA), or stroke, which causes impairments due to changes in blood supply to the brain; (b) spinal cord injuries (SCIs), which result in total or partial obstruction of flow of both sensory and motor information between the peripheral and central nervous systems; (c) nontraumatic disorders of the CNS (amyotrophic lateral sclerosis and multiple sclerosis); and (d) cerebral palsy (CP). Finally, the chapter presents the incidence of CNS diseases.