Spatial-temporal variability of radiomic features and its effect on the classification of lung cancer histology.
Abstract
The purpose of this research was to study the sensitivity of Computed Tomography (CT)
radiomic features to motion blurring and signal-to-noise ratios (SNR), and investigate
its downstream effect regarding the classification of non-small cell lung cancer (NSCLC)
histology. Forty-three radiomic features were considered and classified into one of
four categories: Morphological, Intensity, Fine Texture, and Coarse Texture. First,
a series of simulations were used to study feature-sensitivity to changes in spatial-temporal
resolution. A dynamic digital phantom was used to generate images with different breathing
amplitudes and SNR, from which features were extracted and characterized relative
to initial simulation conditions. Stage I NSCLC patients were then retrospectively
identified, from which three different acquisition-specific feature-spaces were generated
based on free-breathing (FB), average-intensity-projection (AIP), and end-of-exhalation
(EOE) CT images. These feature-spaces were derived to cover a wide range of spatial-temporal
tradeoff. Normalized percent differences and concordance correlation coefficients
(CCC) were used to assess the variability between the 3D and 4D acquisition techniques.
Subsequently, three corresponding acquisition-specific logistic regression models
were developed to classify lung tumor histology. Classification performance was compared
between the different data-dependent models. Simulation results demonstrated strong
linear dependences (p > 0.95) between respiratory motion and morphological features,
as well as between SNR and texture features. The feature Short Run Emphasis was found
to be particularly stable to both motion blurring and changes in SNR. When comparing
FB-to-EOE, 37% of features demonstrated high CCC agreement (CCC > 0.8), compared
to only 30% for FB-to-AIP. In classifying tumor histology, EoE images achieved an
average AUC, Accuracy, Sensitivity, and Specificity of [Formula: see text], respectively.
FB images achieved respective values of [Formula: see text], and AIP images achieved
respective values of [Formula: see text]. Several radiomic features have been identified
as being relatively robust to spatial-temporal variations based on both simulation
data and patient data. In general, features that were sensitive to motion blurring
were not necessarily the same features that were sensitive to changes in SNR. Our
modeling results suggest that the EoE phase of a 4DCT acquisition may provide useful
radiomic information, particularly for features that are highly sensitive to respiratory
motion.
Type
Journal articleSubject
Science & TechnologyTechnology
Life Sciences & Biomedicine
Engineering, Biomedical
Radiology, Nuclear Medicine & Medical Imaging
Engineering
radiomics
quantitative imaging
feature variability
STABILITY
INFORMATION
IMAGES
Permalink
https://hdl.handle.net/10161/19227Published Version (Please cite this version)
10.1088/1361-6560/aae56aPublication Info
Lafata, Kyle; Cai, Jing; Wang, Chunhao; Hong, Julian; Kelsey, Chris R; & Yin, Fang-Fang (2018). Spatial-temporal variability of radiomic features and its effect on the classification
of lung cancer histology. Physics in medicine and biology, 63(22). pp. 225003. 10.1088/1361-6560/aae56a. Retrieved from https://hdl.handle.net/10161/19227.This is constructed from limited available data and may be imprecise. To cite this
article, please review & use the official citation provided by the journal.
Collections
More Info
Show full item recordScholars@Duke
Jing Cai
Adjunct Associate Professor in the Radiation Oncology
Image-guided Radiation Therapy (IGRT), Magnetic Resonance Imaging (MRI), Tumor Motion
Management, Four-Dimensional Radiation Therapy (4DRT), Stereotatic-Body Radiation
Therapy (SBRT), Brachytherapy, Treatment Planning, Lung Cancer, Liver Cancer, Cervical
Cancer.
Julian Hong
Research Scholar
I am a current resident physician in radiation oncology and will be completing residency
in June 2019. I will be starting as faculty in the Department of Radiation Oncology
and in the Bakar Computational Sciences Health Institute at the University of California,
San Francisco in September 2019.
Christopher Ryan Kelsey
Professor of Radiation Oncology
Clinical trials that are currently enrolling patients include a study investigating
lower doses of radiation therapy for patients with diffuse large B-cell lymphoma,
with the goal of maintaining excellent tumor control but decreasing the risk of long-term
side effects of treatment. I also have an interest in genetic determinants of radiation
sensitivity, predictors of local recurrence after surgery for lung cancer, radiation-induced
lung injury, and the role of radiation therapy in
Kyle Jon Lafata
Thaddeus V. Samulski Assistant Professor of Radiation Oncology
Kyle Lafata is the Thaddeus V. Samulski Assistant Professor at Duke University in
the Departments of Radiation Oncology, Radiology, Medical Physics, and Electrical
& Computer Engineering. After earning his PhD in Medical Physics in 2018, he completed
postdoctoral training at the U.S. Department of Veterans Affairs in the Big Data Scientist
Training Enhancement Program. Prof. Lafata has broad expertise in imaging science,
digital pathology, computer vision, biophysics, and
Chunhao Wang
Assistant Professor of Radiation Oncology
Deep learning methods for image-based radiotherapy outcome prediction and assessment
Machine learning in outcome modelling
Automation in radiotherapy planning and delivery
Fang-Fang Yin
Gustavo S. Montana Distinguished Professor of Radiation Oncology
Stereotactic radiosurgery, Stereotactic body radiation therapy, treatment planning
optimization, knowledge guided radiation therapy, intensity-modulated radiation therapy,
image-guided radiation therapy, oncological imaging and informatics
Alphabetical list of authors with Scholars@Duke profiles.

Articles written by Duke faculty are made available through the campus open access policy. For more information see: Duke Open Access Policy
Rights for Collection: Scholarly Articles
Works are deposited here by their authors, and represent their research and opinions, not that of Duke University. Some materials and descriptions may include offensive content. More info