Effect of Image Variation on Computer Aided Detection Systems
2014 (English)In: Proceedings of SPIE, the International Society for Optical Engineering, ISSN 0277-786X, Vol. 9035, 90352H- p.Article in journal (Refereed) Published
As the importance of Computer Aided Detection (CAD) systems application is rising in medical imaging field due to the advantages they generate; it is essential to know their weaknesses and try to find a proper solution for them. A common possible practical problem that affects CAD systems performance is: dissimilar training and testing datasets declines the efficiency of CAD systems. In this paper normalizing images is proposed, three different normalization methods are applied on chest radiographs namely (1) Simple normalization (2) Local Normalization (3) Multi Band Local Normalization. The supervised lung segmentation CAD system performance is evaluated on normalized chest radiographs with these three different normalization methods in terms of Jaccard index. As a conclusion the normalization enhances the performance of CAD system and among these three normalization methods Local Normalization and Multi band Local normalization improve performance of CAD system more significantly than the simple normalization.
Place, publisher, year, edition, pages
2014. Vol. 9035, 90352H- p.
Image Normalization, Local normalization, Multi band local normalization, Chest Radiography, Lung segmentation, Computer Aided Detection
Radiology, Nuclear Medicine and Medical Imaging
IdentifiersURN: urn:nbn:se:kth:diva-148192DOI: 10.1117/12.2043520ISI: 000337842400084ScopusID: 2-s2.0-84902097104OAI: oai:DiVA.org:kth-148192DiVA: diva2:736675
Medical Imaging 2014: Computer-Aided Diagnosis; San Diego, CA; United States; 18 February 2014 through 20 February 2014
QC 201408082014-08-082014-08-042014-08-08Bibliographically approved