Share Email Print
cover

Proceedings Paper

Deep radiomic precision CT imaging for prognostic biomarkers for interstitial lung diseases
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We developed a novel survival analysis model for images, called pix2surv, based on a conditional generative adversarial network (cGAN). The performance of the model was evaluated in the prediction of the overall survival of patients with rheumatoid arthritis-associated interstitial lung disease (RA-ILD) based on the radiomic 4D-curvature of lung CT images. The architecture of the pix2surv model is based on that of a pix2pix cGAN, in which a generator is configured to generate an estimated survival time image from an input radiomic image of a patient, and a discriminator attempts to differentiate the “fake pair” of the input radiomic image and a generated survival-time image from a “true pair” of the input radiomic image and the observed survival-time image of the patient. For evaluation, we retrospectively identified 71 RA-ILD patients with lung CT images and pulmonary function tests. The 4D-curvature images computed from the CT images were subjected to the pix2surv model for evaluation of their predictive performance with that of an established clinical prognostic biomarker known as the GAP index. Also, principal-curvature images and average principal curvatures were individually subjected, in place of the 4D-curvature images, to the pix2surv model for performance comparison. The evaluation was performed by use of bootstrapping with concordance index (C-index) and relative absolute error (RAE) as metrics of prediction performance. Preliminary result showed that the use of 4D-curvature images yielded C-index and RAE values that statistically significantly outperformed the use of the clinical biomarker as well as the other radiomic images and features, indicating the effectiveness of 4D-curvature images with pix2surv as a prognostic imaging biomarker for the survival of patients with RA-ILD.

Paper Details

Date Published: 27 March 2019
PDF: 6 pages
Proc. SPIE 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, 109541E (27 March 2019); doi: 10.1117/12.2512058
Show Author Affiliations
Tomoki Uemura, Massachusetts General Hospital and Harvard Medical School (United States)
Mikio Matsuhiro, Massachusetts General Hospital and Harvard Medical School (United States)
Yamaguchi Univ. (Japan)
Chinatsu Watari, Massachusetts General Hospital and Harvard Medical School (United States)
Janne J. Näppi, Massachusetts General Hospital and Harvard Medical School (United States)
Radin A. Nasirudin, Massachusetts General Hospital and Harvard Medical School (United States)
Toru Hironaka, Massachusetts General Hospital and Harvard Medical School (United States)
Yoshiki Kawata, Yamaguchi Univ. (Japan)
Noboru Niki, Yamaguchi Univ. (Japan)
Hiroyuki Yoshida, Massachusetts General Hospital and Harvard Medical School (United States)


Published in SPIE Proceedings Vol. 10954:
Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications
Po-Hao Chen; Peter R. Bak, Editor(s)

© SPIE. Terms of Use
Back to Top