Share Email Print
cover

Proceedings Paper

Lung lesion detection in FDG-PET/CT with Gaussian process regression
Author(s): Ryosuke Kamesawa; Issei Sato; Shouhei Hanaoka; Yukihiro Nomura; Mitsutaka Nemoto; Naoto Hayashi; Masashi Sugiyama
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this study, we propose a novel method of lung lesion detection in FDG-PET/CT volumes without labeling lesions. In our method, the probability distribution over normal standardized uptake values (SUVs) is estimated from the features extracted from the corresponding volume of interest (VOI) in the CT volume, which include gradient-based and texture-based features. To estimate the distribution, we use Gaussian process regression with an automatic relevance determination kernel, which provides the relevance of feature values to estimation. Our model was trained using FDG-PET/CT volumes of 121 normal cases. In the lesion detection phase, the actual SUV is judged as normal or abnormal by comparison with the estimated SUV distribution. According to the validation using 28 FDG-PET/CT volumes with 34 lung lesions, the sensitivity of the proposed method at 5.0 false positives per case was 81.9%.

Paper Details

Date Published: 3 March 2017
PDF: 7 pages
Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101340C (3 March 2017); doi: 10.1117/12.2255588
Show Author Affiliations
Ryosuke Kamesawa, The Univ. of Tokyo (Japan)
The Univ. of Tokyo Hospital (Japan)
Issei Sato, The Univ. of Tokyo (Japan)
The Univ. of Tokyo Hospital (Japan)
Shouhei Hanaoka, The Univ. of Tokyo Hospital (Japan)
Yukihiro Nomura, The Univ. of Tokyo Hospital (Japan)
Mitsutaka Nemoto, The Univ. of Tokyo Hospital (Japan)
Naoto Hayashi, The Univ. of Tokyo Hospital (Japan)
Masashi Sugiyama, The Univ. of Tokyo (Japan)


Published in SPIE Proceedings Vol. 10134:
Medical Imaging 2017: Computer-Aided Diagnosis
Samuel G. Armato; Nicholas A. Petrick, Editor(s)

© SPIE. Terms of Use
Back to Top