Paper Info
Title
Searching similar images for classification of pulmonary nodules in three-dimensional CT images
Abstract
This paper aims at obtaining diagnosis and prognosis information by searching similar images into a three-dimensional (3-D) CT image database of pulmonary nodules for which diagnosis is known. For this purpose, we propose an automatic method to retrieve nodule candidates with similar characteristicsftom the database. Each pulmonary nodule image is represented by the distribution pattern of CT density and 3-D curvature index. The nodule representation is then applied to a similarity measure such as a correlation coefficient. Our database is composed of 248 pulmonary nodules with associated clinical information. For each new case, we sort all the nodules of the database from most to less similar ones. Applying the retrieval method to our database, we present its feasibility to search the similar 3-D nodule images.
Year
DOI
Venue
2002
10.1109/ISBI.2002.1029225
ISBI
Keywords
Field
DocType
cancer,computerised tomography,image classification,lung,medical image processing,3-D curvature index,CT density,associated clinical information,automatic method,correlation coefficient,database retrieval method,imaging technology advances,medical diagnostic imaging,nodule candidates retrieval,prognosis,pulmonary nodules classification,similarity measure,three-dimensional CT images
Computer vision,Pattern recognition,Similarity measure,Computer science,Image segmentation,Computed tomography,Artificial intelligence,Clinical diagnosis,Image database,Contextual image classification
Conference
Citations 
PageRank 
References 
3
0.47
4
Authors
10
Name
Order
Citations
PageRank
Yoshiki Kawata119254.44
Noboru Niki218866.10
Hironobu Ohmatsu313845.23
masahiko kusumoto44616.28
Ryutaro Kakinuma59724.90
Kensaku Mori61125160.28
Hiroyuki Nishiyama730.47
Kenji Eguchi812942.78
Masahiro Kaneko9276.78
Noriyuki Moriyama1014850.47