Pulmonary nodule detection in PET/CT images: improved approach using combined nodule detection and hybrid FP reduction

Atsushi Teramoto; Hiroshi Fujita; Yoya Tomita; Katsuaki Takahashi; Osamu Yamamuro; Tsuneo Tamaki

doi:10.1117/12.912102

23 February 2012 Pulmonary nodule detection in PET/CT images: improved approach using combined nodule detection and hybrid FP reduction

Atsushi Teramoto, Hiroshi Fujita, Yoya Tomita, Katsuaki Takahashi, Osamu Yamamuro, Tsuneo Tamaki

Author Affiliations +

Proceedings Volume 8315, Medical Imaging 2012: Computer-Aided Diagnosis; 83152V (2012) https://doi.org/10.1117/12.912102
Event: SPIE Medical Imaging, 2012, San Diego, California, United States

Abstract

In this study, an automated scheme for detecting pulmonary nodules in PET/CT images has been proposed using combined detection and hybrid false-positive (FP) reduction techniques. The initial nodule candidates were detected separately from CT and PET images. FPs were then eliminated in the initial candidates by using support vector machine with characteristic values obtained from CT and PET images. In the experiment, we evaluated proposed method using 105 cases of PET/CT images that were obtained in the cancer-screening program. We evaluated true positive fraction (TPF) and FP / case. As a result, TPFs of CT and PET detections were 0.76 and 0.44, respectively. However, by integrating the both results, TPF was reached to 0.82 with 5.14 FPs/case. These results indicate that our method may be of practical use for the detection of pulmonary nodules using PET/CT images.

Citation Download Citation

Atsushi Teramoto, Hiroshi Fujita, Yoya Tomita, Katsuaki Takahashi, Osamu Yamamuro, and Tsuneo Tamaki "Pulmonary nodule detection in PET/CT images: improved approach using combined nodule detection and hybrid FP reduction", Proc. SPIE 8315, Medical Imaging 2012: Computer-Aided Diagnosis, 83152V (23 February 2012); https://doi.org/10.1117/12.912102

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available