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/ Journal of Computer ...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/
Journal of Computer Science
Article . 2017 . Peer-reviewed
Data sources: Crossref
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/
Journal of Computer Science
Article
License: CC BY
Data sources: UnpayWall
https://dx.doi.org/10.60692/g2...
Other literature type . 2017
Data sources: Datacite
https://dx.doi.org/10.60692/pw...
Other literature type . 2017
Data sources: Datacite
DBLP
Article . 2017
Data sources: DBLP
versions View all 4 versions
addClaim

Medical Images Registration based on Normalized Dissimilarity Index

تسجيل الصور الطبية على أساس مؤشر الاختلاف الطبيعي
Authors: Amina Kharbach; Mouad El Omari; Amar Mardani; Benaïssa Bellach; Mohammed Rahmoun;

Medical Images Registration based on Normalized Dissimilarity Index

Abstract

L'enregistrement des images est une étape essentielle dans un grand nombre de chaînes de traitement des images médicales. Il est utilisé pour aligner deux images prises à des moments différents et à partir de capteurs différents également. Dans cet article, nous nous intéressons aux mesures d'enregistrement et de similarité rigides. Nous décrivons une nouvelle approche d'enregistrement, basée sur l'indice de dissimilarité normalisé qui résulte de la carte de dissimilarité locale (LDP). Ce LDP est obtenu à partir de la transformée de distance appliquée aux images en échelle de gris, pour enregistrer, en subissant une binarisation. Nous évaluons les performances de notre méthode par rapport aux mesures d'enregistrement classiques telles que la corrélation et l'information mutuelle, sur une base de données d'images médicales. Nous montrons que l'erreur quadratique moyenne de notre approche est plus précise par rapport aux méthodes d'enregistrement classiques auxquelles les chercheurs adhèrent encore. La robustesse de notre indice proposé est validée en ce qui concerne la variation de luminance et la présence du « poivre et du sel » autant que du « bruit gaussien ».

El registro de imágenes es un paso esencial en una gran cantidad de cadenas de procesamiento de imágenes médicas. Se utiliza para alinear dos imágenes tomadas en diferentes momentos y también desde diferentes sensores. En este documento, nos interesan las medidas rígidas de registro y similitud. Describimos un nuevo enfoque de registro, basado en el índice de disimilitud normalizado que resulta del mapa de disimilitud local (LDP). Este LDP se obtiene a partir de la transformación de distancia aplicada a imágenes en escala de grises, para registrar, sometiéndonos a una binarización. Evaluamos el rendimiento de nuestro método en comparación con las mediciones de registro clásicas, como la correlación y la información mutua, en una base de datos de imágenes médicas. Mostramos que el error cuadrático medio de nuestro enfoque es más preciso en comparación con los métodos de registro clásicos a los que los investigadores aún se adhieren. La solidez de nuestro índice propuesto se valida con respecto a la variación de luminancia y la presencia de "la pimienta y la sal" tanto como el ruido "gaussiano".

Image registration is an essential step in a large number of processing chains for medical images.It is used to align two images taken at different times and from different sensors as well.In this paper, we are interested in the rigid registration and similarity measures.We describe a new registration approach, based on the normalized dissimilarity index that results from the local dissimilarity map (LDP).This LDP is obtained from distance transform applied to gray-scale images, to register, undergoing a binarization.We evaluate the performance of our method compared to the classical registration measurements such as correlation and mutual information, on a medical images database.We show that the mean squared error of our approach is more accurate in comparison to the classical registration methods to which researchers still adhere.The robustness of our proposed index is validated regarding the luminance variation and the presence of "the Pepper and Salt" as much as "the Gaussian" noise.

يعد تسجيل الصور خطوة أساسية في عدد كبير من سلاسل المعالجة للصور الطبية. يتم استخدامه لمحاذاة صورتين تم التقاطهما في أوقات مختلفة ومن مستشعرات مختلفة أيضًا. في هذه الورقة، نحن مهتمون بمقاييس التسجيل والتشابه الصارمة. نحن نصف نهج تسجيل جديد، استنادًا إلى مؤشر الاختلاف الطبيعي الذي ينتج عن خريطة الاختلاف المحلية (LDP). يتم الحصول على LDP هذا من تحويل المسافة المطبق على الصور ذات المقياس الرمادي، للتسجيل، الخضوع للثنائية. نقوم بتقييم أداء طريقتنا مقارنة بقياسات التسجيل الكلاسيكية مثل الارتباط والمعلومات المتبادلة، على قاعدة بيانات الصور الطبية. نظهر أن متوسط الخطأ التربيعي في نهجنا أكثر دقة مقارنة بطرق التسجيل الكلاسيكية التي لا يزال الباحثون يلتزمون بها. يتم التحقق من صحة قوة مؤشرنا المقترح فيما يتعلق بتباين الإضاءة ووجود "الفلفل والملح" بقدر ضوضاء "جاوسيان".

Keywords

Artificial intelligence, Shape Matching, Robustness (evolution), Image Segmentation, Pattern recognition (psychology), Biochemistry, Quantum mechanics, Gene, Grayscale, Image Feature Retrieval and Recognition Techniques, Shape Matching and Object Recognition, Image (mathematics), FOS: Mathematics, Image Segmentation Techniques, Similarity (geometry), Image registration, Physics, Statistics, Deformable Image Registration, Computer science, Mutual information, Chemistry, Computer Science, Physical Sciences, Gaussian, Medical Image Analysis, Mean squared error, 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).
    2
    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!
2
Average
Average
Average
gold