Please use this identifier to cite or link to this item:
Title: Automatic scoring of multiple semantic attributes with multi-task feature leverage : a study on pulmonary nodules in CT images
Authors: Chen, SH
Qin, J 
Ji, X 
Lei, BY
Wang, TF
Ni, D
Cheng, JZ
Keywords: Computer-aided diagnosis (CAD)
Lung nodule
Computed tomography (CT)
Multi-task learning
Deep learning
Feature learning
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on medical imaging, 2017, v. 36, no. 3, p. 802-814 How to cite?
Journal: IEEE transactions on medical imaging 
Abstract: The gap between the computational and semantic features is the one of major factors that bottlenecks the computer-aided diagnosis (CAD) performance from clinical usage. To bridge this gap, we exploit three multi-task learning (MTL) schemes to leverage heterogeneous computational features derived from deep learning models of stacked denoising autoencoder (SDAE) and convolutional neural network (CNN), as well as hand-crafted Haar-like and HoG features, for the description of 9 semantic features for lung nodules in CT images. We regard that there may exist relations among the semantic features of "spiculation", "texture", "margin", etc., that can be explored with the MTL. The Lung Image Database Consortium (LIDC) data is adopted in this study for the rich annotation resources. The LIDC nodules were quantitatively scored w.r.t. 9 semantic features from 12 radiologists of several institutes in U.S.A. By treating each semantic feature as an individual task, the MTL schemes select and map the heterogeneous computational features toward the radiologists' ratings with cross validation evaluation schemes on the randomly selected 2400 nodules from the LIDC dataset. The experimental results suggest that the predicted semantic scores from the three MTL schemes are closer to the radiologists' ratings than the scores from single-task LASSO and elastic net regression methods. The proposed semantic attribute scoring scheme may provide richer quantitative assessments of nodules for better support of diagnostic decision and management. Meanwhile, the capability of the automatic association of medical image contents with the clinical semantic terms by our method may also assist the development of medical search engine.
ISSN: 0278-0062
EISSN: 1558-254X
DOI: 10.1109/TMI.2016.2629462
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Oct 10, 2018


Last Week
Last month
Citations as of Oct 20, 2018

Page view(s)

Last Week
Last month
Citations as of Oct 15, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.