Comparison of feature selection in radiomics for the prediction of overall survival after radiotherapy for hepatocellular carcinoma

Published on Jul 1, 2020 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
· DOI :10.1109/EMBC44109.2020.9176724
Pierre Fontaine3
Estimated H-index: 3
,
Francois-Georges Riet1
Estimated H-index: 1
+ 4 AuthorsOscar Acosta21
Estimated H-index: 21
(French Institute of Health and Medical Research)
Sources
Abstract
Hepatocellular carcinoma (HCC) is the sixth more frequent cancer worldwide. This type of cancer has a poor overall survival rate mainly due to underlying cirrhosis and risk of recurrence outside the treated lesion. Quantitative imaging within a radiomics workflow may help assessing the probability of survival and potentially may allow tailoring personalized treatments. In radiomics a large amount of features can be extracted, which may be correlated across a population and very often can be surrogates of the same physiopathology. This issues are more pronounced and difficult to tackle with imbalanced data. Feature selection strategies are therefore required to extract the most informative with the increased predictive capabilities. In this paper, we compared different unsupervised and supervised strategies for feature selection in presence of imbalanced data and optimize them within a machine learning framework. Multi-parametric Magnetic Resonance Images from 81 individuals (19 deceased) treated with stereotactic body radiation therapy (SBRT) for inoperable (HCC) were analyzed. Pre-selection of a reduced set of features based on Affinity Propagation clustering (non supervised) achieved a significant improvement in AUC compared to other approaches with and without feature pre-selection. By including the synthetic minority over-sampling technique (SMOTE) for imbalanced data and Random Forest classification this workflow emerges as an appealing feature selection strategy for survival prediction within radiomics studies.
📖 Papers frequently viewed together
104 Citations
2019
8 Authors (Zhenwei Shi, ..., Leonard Wee)
References13
Newest
#1Alex Zwanenburg (DKFZ: German Cancer Research Center)H-Index: 18
#2Martin Vallières (McGill University)H-Index: 18
Last. Steffen LöckH-Index: 24
view all 63 authors...
The Image Biomarker Standardization Initiative validated consensus-based reference values for 169 radiomics features, thus enabling calibration and verification of radiomics software.
354 CitationsSource
#1Peter R. Galle (University of Mainz)H-Index: 28
#2Alejandro Forner (European Organisation for Research and Treatment of Cancer)H-Index: 1
Last. Valérie VilgrainH-Index: 95
view all 8 authors...
Summary Liver cancer is the fifth most common cancer and the second most frequent cause of cancer-related death globally. Hepatocellular carcinoma represents about 90% of primary liver cancers and constitutes a major global health problem. The following Clinical Practice Guidelines will give up-to-date advice for the clinical management of patients with hepatocellular carcinoma, as well as providing an in-depth review of all the relevant data leading to the conclusions herein.
4,163 CitationsSource
#1Ryan Clay (Mayo Clinic)H-Index: 6
#2Benjamin R. Kipp (Mayo Clinic)H-Index: 42
Last. Tobias Peikert (Mayo Clinic)H-Index: 31
view all 10 authors...
Computer-Aided Nodule Assessment and Risk Yield (CANARY) is quantitative imaging analysis software that predicts the histopathological classification and post-treatment disease-free survival of patients with adenocarcinoma of the lung. CANARY characterizes nodules by the distribution of nine color-coded texture-based exemplars. We hypothesize that quantitative computed tomography (CT) analysis of the tumor and tumor-free surrounding lung facilitates non-invasive identification of clinically-rele...
4 CitationsSource
#1Xi Zhang (Fourth Military Medical University)H-Index: 13
#2Xiaopan Xu (Fourth Military Medical University)H-Index: 10
Last. Hongbing Lu (Fourth Military Medical University)H-Index: 28
view all 10 authors...
PURPOSE: To 1) describe textural features from diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) maps that can distinguish low-grade bladder cancer from high-grade, and 2) propose a radiomics-based strategy for cancer grading using texture features. MATERIALS AND METHODS: In all, 61 patients with bladder cancer (29 in high- and 32 in low-grade groups) were enrolled in this retrospective study. Histogram- and gray-level co-occurrence matrix (GLCM)-based radiomics features w...
62 CitationsSource
#1Robert J. GilliesH-Index: 106
#2Paul E. Kinahan (UW: University of Washington)H-Index: 69
Last. Hedvig Hricak (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 137
view all 3 authors...
This report describes the process of radiomics, its challenges, and its potential power to facilitate better clinical decision making, particularly in the care of patients with cancer.
2,108 CitationsSource
#1Chintan Parmar (ISI: Indian Statistical Institute)H-Index: 24
#2Patrick Grossmann (Harvard University)H-Index: 16
Last. Hugo J.W.L. Aerts (Harvard University)H-Index: 65
view all 5 authors...
Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pretreatment computed tom...
427 CitationsSource
#1Chintan Parmar (ISI: Indian Statistical Institute)H-Index: 24
#2Ralph T.H. Leijenaar (UM: Maastricht University)H-Index: 29
Last. Hugo J.W.L. Aerts (Harvard University)H-Index: 65
view all 10 authors...
Radiomic feature clusters and Prognostic Signatures specific for Lung and Head & Neck cancer
255 CitationsSource
#1Jonathan Klein (U of T: University of Toronto)H-Index: 9
#2Laura A. Dawson (U of T: University of Toronto)H-Index: 81
Hepatocellular carcinoma (HCC) is a leading cause of global cancer death. Curative therapy is not an option for most patients, often because of underlying liver disease. Experience in radiation therapy (RT) for HCC is rapidly increasing. Conformal RT can deliver tumoricidal doses to focal HCC with low rates of toxicity and sustained local control in HCC unsuitable for other locoregional treatments. Stereotactic body RT and particle therapy have been used with long-term control in early HCC or as...
132 CitationsSource
#1W.Y. Huang (NDMC: National Defense Medical Center)H-Index: 6
#2Yee Min Jen (NDMC: National Defense Medical Center)H-Index: 7
Last. Yao Wen Chang (NDMC: National Defense Medical Center)H-Index: 1
view all 13 authors...
Purpose To examine the safety and efficacy of Cyberknife stereotactic body radiation therapy (SBRT) and its effect on survival in patients of recurrent hepatocellular carcinoma (HCC). Methods and Materials This was a matched-pair study. From January 2008 to December 2009, 36 patients with 42 lesions of unresectable recurrent HCC were treated with SBRT. The median prescribed dose was 37 Gy (range, 25 to 48 Gy) in 4–5 fractions over 4–5 consecutive working days. Another 138 patients in the histori...
126 CitationsSource
#1Brendan J. Frey (U of T: University of Toronto)H-Index: 74
#2Delbert Dueck (U of T: University of Toronto)H-Index: 8
Clustering data by identifying a subset of representative examples is important for processing sensory signals and detecting patterns in data. Such "exemplars" can be found by randomly choosing an initial subset of data points and then iteratively refining it, but this works well only if that initial choice is close to a good solution. We devised a method called "affinity propagation," which takes as input measures of similarity between pairs of data points. Real-valued messages are exchanged be...
5,911 CitationsSource
Cited By0
Newest
Our objective was to establish a random forest model and to evaluate its predictive capability of the treatment effect of neoadjuvant chemotherapy–radiation therapy. This retrospective study included 82 patients with locally advanced cervical cancer who underwent scanning from March 2013 to May 2018. The random forest model was established and optimised based on the open source toolkit scikit-learn. Byoptimising of the number of decision trees in the random forest, the criteria for selecting the...
Source