Spatial-temporal variability of radiomic features and its effect on the classification of lung cancer histology.

Thumbnail Image



Journal Title

Journal ISSN

Volume Title

Repository Usage Stats


Citation Stats


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.





Published Version (Please cite this version)


Publication Info

Lafata, Kyle, Jing Cai, Chunhao Wang, Julian Hong, Chris R Kelsey and Fang-Fang Yin (2018). Spatial-temporal variability of radiomic features and its effect on the classification of lung cancer histology. Physics in medicine and biology, 63(22). p. 225003. 10.1088/1361-6560/aae56a Retrieved from

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.



Kyle Jon Lafata

Thaddeus V. Samulski Associate Professor of Radiation Oncology

Kyle Lafata is the Thaddeus V. Samulski Associate 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 applied mathematics. His dissertation work focused on the applied analysis of stochastic differential equations and high-dimensional radiomic phenotyping, where he developed physics-based computational methods and soft-computing paradigms to interrogate images. These included stochastic modeling, self-organization, and quantum machine learning (i.e., an emerging branch of research that explores the methodological and structural similarities between quantum systems and learning systems). 

Prof. Lafata has worked in various areas of computational medicine and biology, resulting in 39 peer-reviewed journal publications, 15 invited talks, and more than 50 national conference presentations. At Duke, the Lafata Lab focuses on the theory, development, and application of multiscale computational biomarkers. Using computational and mathematical methods, they study the appearance and behavior of disease across different physical length-scales (i.e., radiomics ~10−3 m, pathomics ~10−6 m, and genomics ~10−9 m) and time-scales (e.g., the natural history of disease, response to treatment). The overarching goal of the lab is to develop and apply new technology that transforms imaging into basic science findings and computational biomarker discovery.


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.


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


Christopher Ryan Kelsey

Professor of Radiation Oncology

I specialize in the treatment of hematologic and thoracic malignancies. I have a special research interest in optimizing radiation therapy in lymphomas and leukemias, particularly consolidation radiation therapy in diffuse large B-cell lymphoma and total body irradiation in the setting of allogeneic stem cell transplantation. Other academic interests include cardiac toxicity after radiation therapy for lung cancer and optimizing stereotactic body radiation therapy for stage I non-small cell lung cancer.

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.