Lungs Segmentation and Nodule Detection using Machine Learning | Medical Image Segmentation and Classification using Machine Learning

Arfan Jaffar (u. a.)

ISBN 10: 3639342801 / ISBN 13: 9783639342802

Published by VDM Verlag Dr. Müller, 2011

About this Item

Lungs Segmentation and Nodule Detection using Machine Learning | Medical Image Segmentation and Classification using Machine Learning | Arfan Jaffar (u. a.) | Taschenbuch | Englisch | VDM Verlag Dr. Müller | EAN 9783639342802 | Verantwortliche Person für die EU: VDM Verlag Dr. Müller, Brivibas Gatve 197, 1039 RIGA, LETTLAND, customerservice[at]vdm-vsg[dot]de | Anbieter: preigu.

Seller Inventory # 107037240

Bibliographic Details

• Title: Lungs Segmentation and Nodule Detection using Machine Learning | Medical Image Segmentation and Classification using Machine Learning
• Publisher: VDM Verlag Dr. Müller
• Publication Date: 2011
• Language: English
• ISBN 10: 3639342801
• ISBN 13: 9783639342802
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 10W x 150H x 220D millimeters 10 millimeters width by 150 millimeters height by 220 millimeters depth
• Weight: 235 grams
• Seller catalogs:
  • Bücher

About this title

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.

About the Author

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.