Abstract
| Originalsprog | Engelsk |
|---|---|
| Tidsskrift | Medical Image Analysis |
| Vol/bind | 10 |
| Udgave nummer | 12 |
| Sider (fra-til) | 247-258 |
| ISSN | 1361-8415 |
| Status | Udgivet - 2006 |
| Udgivet eksternt | Ja |
Bibliografisk note
Paper id:: 10.1016/j.media.2005.09.003Citationsformater
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS
I: Medical Image Analysis, Bind 10, Nr. 12, 2006, s. 247-258.
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review
}
TY - JOUR
T1 - A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database
AU - Schilham, Arnold M.R.
AU - Ginneken, Bram van
AU - Loog, Marco
N1 - Paper id:: 10.1016/j.media.2005.09.003
PY - 2006
Y1 - 2006
N2 - 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.
AB - 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.
M3 - Journal article
SN - 1361-8415
VL - 10
SP - 247
EP - 258
JO - Medical Image Analysis
JF - Medical Image Analysis
IS - 12
ER -