An investigation of machine learning methods in delta-radiomics feature analysis.
Date
2019-01
Editors
Journal Title
Journal ISSN
Volume Title
Repository Usage Stats
views
downloads
Citation Stats
Abstract
PURPOSE:This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS:The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS:For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS:The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.
Type
Department
Description
Provenance
Subjects
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Chang, Yushi, Kyle Lafata, Wenzheng Sun, Chunhao Wang, Zheng Chang, John P Kirkpatrick and Fang-Fang Yin (2019). An investigation of machine learning methods in delta-radiomics feature analysis. PloS one, 14(12). p. e0226348. 10.1371/journal.pone.0226348 Retrieved from https://hdl.handle.net/10161/20269.
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
Scholars@Duke
Kyle Jon Lafata
Kyle Lafata is the Thaddeus V. Samulski Associate Professor at Duke University with faculty appointments in Radiation Oncology, Radiology, Pathology, Medical Physics, and Electrical & Computer Engineering. He joined the faculty at Duke in 2020 following postdoctoral training at the US Department of Veterans Affairs. His dissertation work focused on the applied analysis of stochastic partial differential equations and high-dimensional image 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 over 55 academic papers, 20 invited talks, and more than 60 national conference presentations. At Duke, the Lafata Laboratory focuses on the theory, development, and application of computational oncology. The lab interrogates disease at different length-scales of its biological organization via high-performance computing, multiscale modeling, advanced imaging technology, and the applied analysis of stochastic partial differential equations. Current research interests include tumor topology, cellular dynamics, tumor immune microenvironment, drivers of radiation resistance and immune dysregulation, molecular insight into tissue heterogeneity, and biologically-guided adaptative treatment strategies.
Chunhao Wang
- Deep learning methods for image-based radiotherapy outcome prediction and assessment
- Machine learning in outcome modelling
- Automation in radiotherapy planning and delivery
Zheng Chang
Dr. Chang's research interests include radiation therapy treatment assessment using MR quantitative imaging, image guided radiation therapy (IGRT), fast MR imaging using parallel imaging and strategic phase encoding, and motion management for IGRT.
John P. Kirkpatrick
Malignant and benign tumors of the brain, spine and base of skull. Mathematical modelling of tumor metabolism, mass transfer and the response to ionizing radiation. Enhancing clinical outcome in stereotactic radiosurgery, fractionated stereotactic radiotherapy and stereotactic body radiotherapy.
Fang-Fang Yin
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
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.