Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ https://hal.inria.fr...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
https://hal.inria.fr/hal-01913...
Part of book or chapter of book
License: CC BY
Data sources: UnpayWall
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
HAL Arts et Métiers
Conference object . 2018
License: CC BY
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
https://doi.org/10.1007/978-3-...
Part of book or chapter of book . 2018 . Peer-reviewed
License: Springer Nature TDM
Data sources: Crossref
https://dx.doi.org/10.60692/be...
Other literature type . 2018
Data sources: Datacite
https://dx.doi.org/10.60692/q2...
Other literature type . 2018
Data sources: Datacite
versions View all 5 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Conjugate Gradient Method for Brain Magnetic Resonance Images Segmentation

طريقة التدرج المترافق لتقسيم صور الرنين المغناطيسي للدماغ
Authors: El-Hachemi Guerrout; Samy Ait-Aoudia; Dominique Michelucci; Ramdane Mahiou;

Conjugate Gradient Method for Brain Magnetic Resonance Images Segmentation

Abstract

La segmentation de l'image est le processus de partitionnement de l'image en régions d'intérêt afin de fournir une représentation significative de l'information. De nos jours, la segmentation est devenue une nécessité dans de nombreuses méthodes d'imagerie médicale pratiques comme la localisation des tumeurs et des maladies. Le modèle de champ aléatoire de Markov caché est l'une des nombreuses techniques utilisées dans la segmentation d'images. Il fournit un moyen élégant de modéliser le processus de segmentation. Cette modélisation conduit à la minimisation d'une fonction objectif. L'algorithme de gradient conjugué (CG) est l'une des techniques d'optimisation les plus connues. Cet article propose l'utilisation de l'algorithme non linéaire de gradient conjugué (CG) pour la segmentation d'image, en combinaison avec la modélisation du champ aléatoire de Hidden Markov. Étant donné que les dérivées ne sont pas disponibles pour cette expression, des différences finies sont utilisées dans l'algorithme CG pour approcher la dérivée première. L'approche est évaluée à l'aide d'un certain nombre d'images accessibles au public, où la vérité sur le terrain est connue. Le coefficient de dés est utilisé comme critère objectif pour mesurer la qualité de la segmentation. Les résultats montrent que l'approche CG proposée se compare favorablement à d'autres variantes des algorithmes de segmentation des champs aléatoires de Hidden Markov.

La segmentación de imágenes es el proceso de dividir la imagen en regiones de interés para proporcionar una representación significativa de la información. Hoy en día, la segmentación se ha convertido en una necesidad en muchos métodos prácticos de imagen médica como la localización de tumores y enfermedades. El modelo de campo aleatorio oculto de Markov es una de las varias técnicas utilizadas en la segmentación de imágenes. Proporciona una forma elegante de modelar el proceso de segmentación. Este modelado conduce a la minimización de una función objetivo. El algoritmo de gradiente conjugado (CG) es una de las técnicas de optimización más conocidas. Este documento propone el uso del algoritmo no lineal de gradiente conjugado (CG) para la segmentación de imágenes, en combinación con la modelización del campo aleatorio oculto de Markov. Dado que las derivadas no están disponibles para esta expresión, se utilizan diferencias finitas en el algoritmo CG para aproximar la primera derivada. El enfoque se evalúa utilizando una serie de imágenes disponibles públicamente, donde se conoce la verdad del terreno. El coeficiente de dados se utiliza como criterio objetivo para medir la calidad de la segmentación. Los resultados muestran que el enfoque de CG propuesto se compara favorablemente con otras variantes de algoritmos de segmentación de campos aleatorios ocultos de Markov.

Image segmentation is the process of partitioning the image into regions of interest in order to provide a meaningful representation of information. Nowadays, segmentation has become a necessity in many practical medical imaging methods as locating tumors and diseases. Hidden Markov Random Field model is one of several techniques used in image segmentation. It provides an elegant way to model the segmentation process. This modeling leads to the minimization of an objective function. Conjugate Gradient algorithm (CG) is one of the best known optimization techniques. This paper proposes the use of the nonlinear Conjugate Gradient algorithm (CG) for image segmentation, in combination with the Hidden Markov Random Field modelization. Since derivatives are not available for this expression, finite differences are used in the CG algorithm to approximate the first derivative. The approach is evaluated using a number of publicly available images, where ground truth is known. The Dice Coefficient is used as an objective criterion to measure the quality of segmentation. The results show that the proposed CG approach compares favorably with other variants of Hidden Markov Random Field segmentation algorithms.

تجزئة الصورة هي عملية تقسيم الصورة إلى مناطق ذات أهمية من أجل توفير تمثيل هادف للمعلومات. في الوقت الحاضر، أصبح التقسيم ضرورة في العديد من طرق التصوير الطبي العملي مثل تحديد موقع الأورام والأمراض. نموذج حقل ماركوف العشوائي المخفي هو واحد من العديد من التقنيات المستخدمة في تجزئة الصور. يوفر طريقة أنيقة لنمذجة عملية التجزئة. تؤدي هذه النمذجة إلى تقليل وظيفة موضوعية. تعد خوارزمية التدرج المترافق (CG) واحدة من أفضل تقنيات التحسين المعروفة. تقترح هذه الورقة استخدام خوارزمية التدرج المتقارن غير الخطي (CG) لتجزئة الصور، بالاقتران مع نمذجة حقل ماركوف العشوائي المخفي. نظرًا لأن المشتقات غير متوفرة لهذا التعبير، يتم استخدام اختلافات محدودة في خوارزمية CG لتقريب المشتق الأول. يتم تقييم النهج باستخدام عدد من الصور المتاحة للجمهور، حيث تكون الحقيقة الأرضية معروفة. يستخدم معامل النرد كمعيار موضوعي لقياس جودة التجزئة. تظهر النتائج أن نهج CG المقترح يقارن بشكل إيجابي مع المتغيرات الأخرى لخوارزميات تجزئة الحقل العشوائي لماركوف المخفي.

Keywords

Artificial intelligence, Scale-space segmentation, MRI Segmentation, Markov chain, Brain image segmentation, Image Retrieval, [INFO] Computer Science [cs], Conjugate gradient method, Image Segmentation, Pattern recognition (psychology), Segmentation, Image Feature Retrieval and Recognition Techniques, Segmentation-based object categorization, Machine learning, FOS: Mathematics, Image Segmentation Techniques, Image Recognition, Image segmentation, Markov random field, The Conjugate Gradient algorithm, Statistics, Computer science, Algorithm, Dice Coefficient metric, Hidden Markov Random Field, Computer Science, Physical Sciences, Random field, Deep Learning in Computer Vision and Image Recognition, Semantic Segmentation, Computer vision, Computer Vision and Pattern Recognition, Mathematics

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    1
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
1
Average
Average
Average
Green