With the aim of reducing the radiologists' subjectivity and the high degree of inter-observer variability, Content-based
Image Retrieval (CBIR) systems have been proposed to provide visual comparisons of a given lesion to a
collection of similar lesions of known pathology. In this paper, we present the effectiveness of shape features versus
texture features for calculating lung nodules' similarity in Computed Tomography (CT) studies. In our study, we used
eighty-five cases of thoracic CT data from the Lung Image Database Consortium (LIDC). To encode the shape
information, we used the eight most commonly used shape features for pulmonary nodule detection and diagnosis by
existent CAD systems. For the texture, we used co-occurrence, Gabor, and Markov features implemented in our previous
CBIR work. Our preliminary results give low overall precision results for shape compared to texture, showing that shape
features are not effective by themselves at capturing all the information we need to compare the lung nodules.
Useful diagnosis of lung lesions in computed tomography (CT) depends on many factors including the ability of
radiologists to detect and correctly interpret the lesions. Computer-aided Diagnosis (CAD) systems can be used to
increase the accuracy of radiologists in this task. CAD systems are, however, trained against ground truth and the
mechanisms employed by the CAD algorithms may be distinctly different from the visual perception and analysis tasks
of the radiologist. In this paper, we present a framework for finding the mappings between human descriptions and
characteristics and computed image features. The data in our study were generated from 29 thoracic CT scans collected
by the Lung Image Database Consortium (LIDC). Every case was annotated by up to 4 radiologists by marking the
contour of nodules and assigning nine semantic terms to each identified nodule; fifty-nine image features were extracted
from each segmented nodule. Correlation analysis and stepwise multiple regression were applied to find correlations
among semantic characteristics and image features and to generate prediction models for each characteristic based on
image features. From our preliminary experimental results, we found high correlations between different semantic terms
(margin, texture), and promising mappings from image features to certain semantic terms (texture, lobulation,
spiculation, malignancy). While the framework is presented with respect to the interpretation of pulmonary nodules in
CT images, it can be easily extended to find mappings for other modalities in other anatomical structures and for other
image features.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.