Share Email Print

Proceedings Paper

Correlative hierarchical clustering-based low-rank dimensionality reduction of radiomics-driven phenotype in non-small cell lung cancer
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Background: Lung cancer is one of the most common cancers in the United States and the most fatal, with 142,670 deaths in 2019. Accurately determining tumor response is critical to clinical treatment decisions, ultimately impacting patient survival. To better differentiate between non-small cell lung cancer (NSCLC) responders and non-responders to therapy, radiomic analysis is emerging as a promising approach to identify associated imaging features undetectable by the human eye. However, the plethora of variables extracted from an image may actually undermine the performance of computer-aided prognostic assessment, known as the curse of dimensionality. In the present study, we show that correlative-driven hierarchical clustering improves high-dimensional radiomics-based feature selection and dimensionality reduction, ultimately predicting overall survival in NSCLC patients. Methods: To select features for high-dimensional radiomics data, a correlation-incorporated hierarchical clustering algorithm automatically categorizes features into several groups. The truncation distance in the resulting dendrogram graph is used to control the categorization of the features, initiating low-rank dimensionality reduction in each cluster, and providing descriptive features for Cox proportional hazards (CPH)-based survival analysis. Using a publicly available non- NSCLC radiogenomic dataset of 204 patients’ CT images, 429 established radiomics features were extracted. Low-rank dimensionality reduction via principal component analysis (PCA) was employed (𝒌 = 𝟏, 𝒏 < 𝟏) to find the representative components of each cluster of features and calculate cluster robustness using the relative weighted consistency metric. Results: Hierarchical clustering categorized radiomic features into several groups without primary initialization of cluster numbers using the correlation distance metric (as a function) to truncate the resulting dendrogram into different distances. The dimensionality was reduced from 429 to 67 features (for truncation distance of 0.1). The robustness within the features in clusters was varied from -1.12 to -30.02 for truncation distances of 0.1 to 1.8, respectively, which indicated that the robustness decreases with increasing truncation distance when smaller number of feature classes (i.e., clusters) are selected. The best multivariate CPH survival model had a C-statistic of 0.71 for truncation distance of 0.1, outperforming conventional PCA approaches by 0.04, even when the same number of principal components was considered for feature dimensionality. Conclusions: Correlative hierarchical clustering algorithm truncation distance is directly associated with robustness of the clusters of features selected and can effectively reduce feature dimensionality while improving outcome prediction.

Paper Details

Date Published: 15 March 2019
PDF: 8 pages
Proc. SPIE 10954, Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications, 1095416 (15 March 2019); doi: 10.1117/12.2515609
Show Author Affiliations
Bardia Yousefi, Univ. of Pennsylvania (United States)
Nariman Jahani, Univ. of Pennsylvania (United States)
Michael J. LaRiviere , Univ. of Pennsylvania (United States)
Eric Cohen, Univ. of Pennsylvania (United States)
Meng-Kang Hsieh, Univ. of Pennsylvania (United States)
José Marcio Luna, Univ. of Pennsylvania (United States)
Rhea D. Chitalia, Univ. of Pennsylvania (United States)
Jeffrey C. Thompson , Univ. of Pennsylvania Perelman School of Medicine (United States)
Erica L. Carpenter , Univ. of Pennsylvania Perelman School of Medicine (United States)
Sharyn I. Katz M.D., Univ. of Pennsylvania Perelman School of Medicine (United States)
Despina Kontos, Univ. of Pennsylvania (United States)

Published in SPIE Proceedings Vol. 10954:
Medical Imaging 2019: Imaging Informatics for Healthcare, Research, and Applications
Po-Hao Chen; Peter R. Bak, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?