Paper Info
Title
Integrating 3D image descriptors of margin sharpness and texture on a GPU-optimized similar pulmonary nodule retrieval engine.
Abstract
Due to the difficulty to diagnose lung cancer, it is important to integrate content-based image retrieval methods with the pulmonary nodule classification process, since they are capable of retrieving similar cases from large image databases that were previously diagnosed. The goal of this paper is to evaluate an integrated image feature vector, composed of 3D attributes of margin sharpness and texture, on similar pulmonary nodule retrieval, and to optimize the runtime of nodule comparison process with a graphics processing unit (GPU). Retrieval efficiency was evaluated on the ten most similar cases, on different multiprocessor architectures. Results showed that integrated attributes obtained higher efficiency on similar nodule retrieval, with an increase of up to 2.6 percentage points compared to isolated margin sharpness and texture descriptors. Results also showed that GPU increased nodule retrieval performance with a speedup of 23.7$$\\times $$× on nodule comparison runtime.
Year
DOI
Venue
2017
10.1007/s11227-016-1818-4
The Journal of Supercomputing
Keywords
Field
DocType
Pulmonary nodule,Content-based image retrieval,Parallel computing,Graphics processing unit
Computer vision,Feature vector,Computer science,Image retrieval,Multiprocessing,Artificial intelligence,Graphics processing unit,Content-based image retrieval,Speedup,3d image
Journal
Volume
Issue
ISSN
73
8
0920-8542
Citations 
PageRank 
References 
3
0.37
17
Authors
3
Name
Order
Citations
PageRank
José Raniery Ferreira Jr.130.37
Marcelo Costa Oliveira2435.19
Paulo Mazzoncini de Azevedo Marques3598.41