Automatic detection of solitary lung nodules using quality threshold clustering, genetic algorithm and diversity index

The present work has the objective of developing an automatic methodology for the detection of lung nodules. The proposed methodology is based on image processing and pattern recognition techniques and can be summarized in three stages. In the first stage, the extraction and reconstruction of the pu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Artificial intelligence in medicine Jg. 60; H. 3; S. 165 - 177
Hauptverfasser: de Carvalho Filho, Antonio Oseas, de Sampaio, Wener Borges, Silva, Aristófanes Corrêa, de Paiva, Anselmo Cardoso, Nunes, Rodolfo Acatauassú, Gattass, Marcelo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 01.03.2014
Elsevier
Schlagworte:
Algorithms
Animal tumors. Experimental tumors
Applied sciences
Artificial Intelligence
Biological and medical sciences
Cluster Analysis
Computer science; control theory; systems
Computer-aided detection
Data processing. List processing. Character string processing
Exact sciences and technology
Experimental respiratory system tumors
Genetic algorithm
Humans
Image Processing, Computer-Assisted
Information systems. Data bases
Internal Medicine
Lung - diagnostic imaging
Lung cancer
Lung Neoplasms - diagnosis
Medical image
Medical sciences
Memory organisation. Data processing
Nodule detection
Other
Pattern Recognition, Automated
Pattern recognition. Digital image processing. Computational geometry
Quality threshold
Radiographic Image Interpretation, Computer-Assisted - methods
Sensitivity and Specificity
Software
Solitary Pulmonary Nodule - diagnosis
Support vector machine
Tomography, X-Ray Computed - methods
Tumors
Genetic algorithm
Lung cancer
Medical image
Quality threshold
Support vector machine
Nodule detection
Computer-aided detection
Cluster analysis
Image recognition
Image processing
Lung
Respiratory system
Vector support machine
Diagnosis
Pattern extraction
Computer vision
Data analysis
Texture analysis
Mortality
Image databank
Genetic diversity
Pattern recognition
Failure rate
Survival
Automatic measurement
Medical imagery
ISSN:0933-3657, 1873-2860, 1873-2860
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The present work has the objective of developing an automatic methodology for the detection of lung nodules. The proposed methodology is based on image processing and pattern recognition techniques and can be summarized in three stages. In the first stage, the extraction and reconstruction of the pulmonary parenchyma is carried out and then enhanced to highlight its structures. In the second stage, nodule candidates are segmented. Finally, in the third stage, shape and texture features are extracted, selected and then classified using a support vector machine. In the testing stage, with 140 new exams from the Lung Image Database Consortium image collection, 80% of which are for training and 20% are for testing, good results were achieved, as indicated by a sensitivity of 85.91%, a specificity of 97.70% and an accuracy of 97.55%, with a false positive rate of 1.82 per exam and 0.008 per slice and an area under the free response operating characteristic of 0.8062. Lung cancer presents the highest mortality rate in addition to one of the smallest survival rates after diagnosis. An early diagnosis considerably increases the survival chance of patients. The methodology proposed herein contributes to this diagnosis by being a useful tool for specialists who are attempting to detect nodules.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0933-3657
1873-2860
1873-2860
DOI:10.1016/j.artmed.2013.11.002