Pre-processing For Medical Images / Asma Annad  

Public ISBD Titre : Pre-processing For Medical Images Type de document : texte imprimé Auteurs : Asma Annad, Auteur ; Hibat Errahmene Belmahdi, Auteur ; Kara-mohamed, Chafia, Directeur de thèse Editeur : Setif:UFA Année de publication : 2023 Importance : 1 vol (105 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Medical Images (MI) Index. décimale : 004 - Informatique Résumé : Medical Images (MI) are special in the sense that they deal with the human body which is so complex and they are generated by specialised hardware. Medical Images Processing by computers(MIP)is an active research field. Due to their complexity, MI need to be pre-processed. This pre-processing step is important for preparing the images to different Machine Learning (ML) models like classification, identification to cite few. Image Segmentation is a pre-processing step where an input image is divided into segments: parts that exhibit some similarity character. Segmentation in medical images can for example isolate tumours. Different approaches were applied to design different segmentation methods. Clustering, a ML approach, where different data points are grouped in clusters such that points in a cluster presents more similarity that to any other point in other clusters. In our work, we implement two clustering-based segmentation algorithms, FCM and K-means. MI also differ based on the acquisition mode used to generate them. We have usedFCM and K-means on MRI and X-Ray datasets. In our work we have compared the two algorithms’ performance based on different evaluation metrics and then we have compared them based on two image modalities to highlight the effect of the image type on the algorithm. Results show that k-means outperforms FCM. Côte titre : MAI/0756 En ligne : https://drive.google.com/file/d/1SS6bbey7TYiuo162Yo3SACM24sZPKgxe/view?usp=drive [...] Format de la ressource électronique : pdf Pre-processing For Medical Images [texte imprimé] / Asma Annad, Auteur ; Hibat Errahmene Belmahdi, Auteur ; Kara-mohamed, Chafia, Directeur de thèse . - [S.l.] : Setif:UFA, 2023 . - 1 vol (105 f .) ; 29 cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Medical Images (MI) Index. décimale : 004 - Informatique Résumé : Medical Images (MI) are special in the sense that they deal with the human body which is so complex and they are generated by specialised hardware. Medical Images Processing by computers(MIP)is an active research field. Due to their complexity, MI need to be pre-processed. This pre-processing step is important for preparing the images to different Machine Learning (ML) models like classification, identification to cite few. Image Segmentation is a pre-processing step where an input image is divided into segments: parts that exhibit some similarity character. Segmentation in medical images can for example isolate tumours. Different approaches were applied to design different segmentation methods. Clustering, a ML approach, where different data points are grouped in clusters such that points in a cluster presents more similarity that to any other point in other clusters. In our work, we implement two clustering-based segmentation algorithms, FCM and K-means. MI also differ based on the acquisition mode used to generate them. We have usedFCM and K-means on MRI and X-Ray datasets. In our work we have compared the two algorithms’ performance based on different evaluation metrics and then we have compared them based on two image modalities to highlight the effect of the image type on the algorithm. Results show that k-means outperforms FCM. Côte titre : MAI/0756 En ligne : https://drive.google.com/file/d/1SS6bbey7TYiuo162Yo3SACM24sZPKgxe/view?usp=drive [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0756	MAI/0756	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)