Lungs Segmentation and Nodule Detection using Machine Learning: Medical Image Segmentation and Classification using Machine Learning - Couverture souple

Jaffar, Arfan; M. Mirza, Anwar; Sun Choi, Tae

 
9783639342802: Lungs Segmentation and Nodule Detection using Machine Learning: Medical Image Segmentation and Classification using Machine Learning
Couverture souple
ISBN 10 : 3639342801 ISBN 13 : 9783639342802
Editeur : VDM Verlag Dr. Müller, 2011

Synopsis

Segmentation of images has become an important and effective tool for many technological applications like lungs segmentation from CT scan images. The objective of this book is to develop a new fully automated system that segment the lungs part from CT scan images and detect nodules automatically. A fully automatic un-supervised strategy has been developed for the segmentation of lungs. Technique employs a novel background removal operator based on histogram of the image to remove the background very intelligently and automatically. The methodology utilizes spatial Fuzzy C-Mean (FCM) clustering to ensure robustness against the noise. Also a fuzzy histogram based image filtering technique has been used to remove the noise, which preserves the image details for low as well as highly corrupted images. Segments have been validated by using different cluster validity functions. The proposed technique finds out optimal and dynamic threshold by using fuzzy entropy and genetic algorithms. A directional approach has been used to extract the Region of Interests (ROIs) and FCM have been used to classify ROIs that contain nodule.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

Segmentation of images has become an important and effective tool for many technological applications like lungs segmentation from CT scan images. The objective of this book is to develop a new fully automated system that segment the lungs part from CT scan images and detect nodules automatically. A fully automatic un-supervised strategy has been developed for the segmentation of lungs. Technique employs a novel background removal operator based on histogram of the image to remove the background very intelligently and automatically. The methodology utilizes spatial Fuzzy C-Mean (FCM) clustering to ensure robustness against the noise. Also a fuzzy histogram based image filtering technique has been used to remove the noise, which preserves the image details for low as well as highly corrupted images. Segments have been validated by using different cluster validity functions. The proposed technique finds out optimal and dynamic threshold by using fuzzy entropy and genetic algorithms. A directional approach has been used to extract the Region of Interests (ROIs) and FCM have been used to classify ROIs that contain nodule.

Biographie de l'auteur

I am interested in conducting research in areas related with image processing, machine learning, computer vision, artificial intelligence and medical imaging. I am specially interests in biologically inspired ideas like genetic algorithms, artificial neural networks, and soft-computing applications in Medial Imaging and Image processing.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
VDM Verlag Dr. Müller
Date d'édition
2011
Langue
anglais
ISBN 10 
3639342801
ISBN 13 
9783639342802
Reliure
Broché
Nombre de pages
164
Coordonnées du fabricant
non disponible
Personne responsable
non disponible