A study on effect of morphological filters on computer-aided medical image diagnosis

N. Homma, S. Shimoyama, Y. Kawai, T. Ishibashi, M. Yoshizawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We develop several morphological image filters that can be useful for computer-aided medical image diagnosis. Some computer-aided diagnosis (CAD) systems for lung cancer and breast cancer have been developed to assist radiologist's diagnosis work. The CAD systems for lung cancer can automatically detect pathological changes (pulmonary nodules) with a high true positive rate (TP) even under low false positive rate (FP) conditions. On the other hand, the conventional CAD systems for breast cancer can automatically detect some pathological changes (calcifications and masses), but TP for other changes such as architectural distortion is still very low. Motivated by the radiologist's cognitive process to increase TP for breast cancer, we propose new methods to extract novelmorphological features from X-ray mammography. Simulation results demonstrate the effectiveness of the morphological methods for detecting tumor shadows.

Original languageEnglish
Title of host publicationProceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09
Pages472-475
Number of pages4
Publication statusPublished - 2009
Event14th International Symposium on Artificial Life and Robotics, AROB 14th'09 - Oita, Japan
Duration: 2008 Feb 52009 Feb 7

Publication series

NameProceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09

Other

Other14th International Symposium on Artificial Life and Robotics, AROB 14th'09
Country/TerritoryJapan
CityOita
Period08/2/509/2/7

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'A study on effect of morphological filters on computer-aided medical image diagnosis'. Together they form a unique fingerprint.

Cite this