Document Detail


Lung nodule detection in low-dose and thin-slice computed tomography.
MedLine Citation:
PMID:  18342844     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
A computer-aided detection (CAD) system for the identification of small pulmonary nodules in low-dose and thin-slice CT scans has been developed. The automated procedure for selecting the nodule candidates is mainly based on a filter enhancing spherical-shaped objects. A neural approach based on the classification of each single voxel of a nodule candidate has been purposely developed and implemented to reduce the amount of false-positive findings per scan. The CAD system has been trained to be sensitive to small internal and sub-pleural pulmonary nodules collected in a database of low-dose and thin-slice CT scans. The system performance has been evaluated on a data set of 39 CT containing 75 internal and 27 sub-pleural nodules. The FROC curve obtained on this data set shows high values of sensitivity to lung nodules (80-85% range) at an acceptable level of false positive findings per patient (10-13 FP/scan).
Authors:
A Retico; P Delogu; M E Fantacci; I Gori; A Preite Martinez
Related Documents :
2484904 - Spontaneous degeneration of autonomously functioning thyroid nodules, potential therape...
22022334 - Multimodality imaging can help to doubt, diagnose and follow-up cardiac mass.
2791664 - Kaposi's sarcoma. ct-radiographic correlation.
18806154 - Solitary necrotic nodules of the liver: cross-sectional imaging findings and follow-up ...
17419524 - Height and shape of the skull base as risk factors for skull base penetration during en...
15973064 - Early revascularization in a patient with perfusion computed tomography/diffusion-weigh...
Publication Detail:
Type:  Journal Article; Randomized Controlled Trial; Research Support, Non-U.S. Gov't     Date:  2008-03-14
Journal Detail:
Title:  Computers in biology and medicine     Volume:  38     ISSN:  0010-4825     ISO Abbreviation:  Comput. Biol. Med.     Publication Date:  2008 Apr 
Date Detail:
Created Date:  2008-03-31     Completed Date:  2008-09-22     Revised Date:  2008-11-21    
Medline Journal Info:
Nlm Unique ID:  1250250     Medline TA:  Comput Biol Med     Country:  United States    
Other Details:
Languages:  eng     Pagination:  525-34     Citation Subset:  IM    
Affiliation:
Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, Largo Pontecorvo 3, 56127 Pisa, Italy. retico@df.unipi.it
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Artificial Intelligence*
Diagnosis, Computer-Assisted*
Humans
Image Processing, Computer-Assisted*
Imaging, Three-Dimensional*
Italy
Lung / radiography
Lung Neoplasms / radiography*
Mass Screening
Neural Networks (Computer)
Pattern Recognition, Automated
ROC Curve
Radiation Dosage
Sensitivity and Specificity
Software
Solitary Pulmonary Nodule / radiography*
Tomography, Spiral Computed*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  On stent-graft models in thoracic aortic endovascular repair: a computational investigation of the h...
Next Document:  Texture analysis on MRI images of non-Hodgkin lymphoma.