Source:http://linkedlifedata.com/resource/pubmed/id/16293441
Switch to
| Predicate | Object |
|---|---|
| rdf:type | |
| lifeskim:mentions | |
| pubmed:issue |
2
|
| pubmed:dateCreated |
2006-2-8
|
| pubmed:abstractText |
A computer algorithm for nodule detection in chest radiographs is presented. The algorithm consists of four main steps: (i) image preprocessing; (ii) nodule candidate detection; (iii) feature extraction; (iv) candidate classification. Two optional extensions to this scheme are tested: candidate selection and candidate segmentation. The output of step (ii) is a list of circles, which can be transformed into more detailed contours by the extra candidate segmentation step. In addition, the candidate selection step (which is a classification step using a small number of features) can be used to reduce the list of nodule candidates before step (iii). The algorithm uses multi-scale techniques in several stages of the scheme: Candidates are found by looking for local intensity maxima in Gaussian scale space; nodule boundaries are detected by tracing edge points found at large scales down to pixel scale; some of the features used for classification are taken from a multi-scale Gaussian filterbank. Experiments with this scheme (with and without the segmentation and selection steps) are carried out on a previously characterized, publicly available database, that contains a large number of very subtle nodules. For this database, counting as detections only those nodules that were indicated with a confidence level of 50% or more, radiologists previously detected 70% of the nodules. For our algorithm, it turns out that the selection step does have an added value for the system, while segmentation does not lead to a clear improvement. With the scheme with the best performance, accepting on average two false positives per image results in the identification of 51% of all nodules. For four false positives, this increases to 67%. This is close to the previously reported 70% detection rate of the radiologists.
|
| pubmed:language |
eng
|
| pubmed:journal | |
| pubmed:citationSubset |
IM
|
| pubmed:status |
MEDLINE
|
| pubmed:month |
Apr
|
| pubmed:issn |
1361-8415
|
| pubmed:author | |
| pubmed:issnType |
Print
|
| pubmed:volume |
10
|
| pubmed:owner |
NLM
|
| pubmed:authorsComplete |
Y
|
| pubmed:pagination |
247-58
|
| pubmed:dateRevised |
2008-11-21
|
| pubmed:meshHeading |
pubmed-meshheading:16293441-Algorithms,
pubmed-meshheading:16293441-Artificial Intelligence,
pubmed-meshheading:16293441-Cluster Analysis,
pubmed-meshheading:16293441-Databases, Factual,
pubmed-meshheading:16293441-Humans,
pubmed-meshheading:16293441-Imaging, Three-Dimensional,
pubmed-meshheading:16293441-Lung Neoplasms,
pubmed-meshheading:16293441-Medical Records Systems, Computerized,
pubmed-meshheading:16293441-Pattern Recognition, Automated,
pubmed-meshheading:16293441-Radiographic Image Enhancement,
pubmed-meshheading:16293441-Radiographic Image Interpretation, Computer-Assisted,
pubmed-meshheading:16293441-Radiography, Thoracic,
pubmed-meshheading:16293441-Reproducibility of Results,
pubmed-meshheading:16293441-Sensitivity and Specificity,
pubmed-meshheading:16293441-Solitary Pulmonary Nodule
|
| pubmed:year |
2006
|
| pubmed:articleTitle |
A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database.
|
| pubmed:affiliation |
Image Sciences Institute, University Medical Center Utrecht, The Netherlands. arnold@isi.uu.nl
|
| pubmed:publicationType |
Journal Article,
Evaluation Studies,
Validation Studies
|