Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Aug 4:14:61.
doi: 10.3389/fncom.2020.00061. eCollection 2020.

Overall Survival Prediction in Glioblastoma With Radiomic Features Using Machine Learning

Ujjwal Baid  1 , Swapnil U Rane  2 , Sanjay Talbar  1 , Sudeep Gupta  3 , Meenakshi H Thakur  4 , Aliasgar Moiyadi  5 , Abhishek Mahajan  4
Affiliations

Overall Survival Prediction in Glioblastoma With Radiomic Features Using Machine Learning

Ujjwal Baid et al. Front Comput Neurosci. .

Abstract

Glioblastoma is a WHO grade IV brain tumor, which leads to poor overall survival (OS) of patients. For precise surgical and treatment planning, OS prediction of glioblastoma (GBM) patients is highly desired by clinicians and oncologists. Radiomic research attempts at predicting disease prognosis, thus providing beneficial information for personalized treatment from a variety of imaging features extracted from multiple MR images. In this study, first-order, intensity-based volume and shape-based and textural radiomic features are extracted from fluid-attenuated inversion recovery (FLAIR) and T1ce MRI data. The region of interest is further decomposed with stationary wavelet transform with low-pass and high-pass filtering. Further, radiomic features are extracted on these decomposed images, which helped in acquiring the directional information. The efficiency of the proposed algorithm is evaluated on Brain Tumor Segmentation (BraTS) challenge training, validation, and test datasets. The proposed approach achieved 0.695, 0.571, and 0.558 on BraTS training, validation, and test datasets. The proposed approach secured the third position in BraTS 2018 challenge for the OS prediction task.

Keywords: brain tumor; glioblastoma; machine learning; overall survival; radiomic.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Multi-modal data with four channels provided in BraTS 2018 challenge dataset along with ground truth (GT). Subtumor parts are represented as follows: green, edema; blue, enhancing tumor; red, necrosis. BraTS, Brain Tumor Segmentation; FLAIR, fluid-attenuated inversion recovery.
Figure 2
Figure 2
Top row: original input MR slice and slice after biased field correction. Bottom row: corresponding histograms of original slice and histogram after biased field correction. The horizontal X-axis of the histogram is intensity, and the vertical Y axis is frequency.
Figure 3
Figure 3
Proposed three-step framework for overall survival prediction in glioblastoma (GBM).
Figure 4
Figure 4
Representative diagram for stationary wavelet decomposition. LPF, low-pass filter; HPF, high-pass filter.
Figure 5
Figure 5
Distribution of survival groups identified using two-step clustering and correlation with age. Left: the age is in years and overall survival in given days. Right: on the X-axis of two-step cluster, Group 1, Group 2, and Group 3 are represented.
Figure 6
Figure 6
Performance summary of the overall survival (OS) prediction algorithm. (A) Predicted pseudoprobabilities across the three prediction categories. (B) Area under the receiver operating characteristic curve (AUC) for the three categories. (C) Dot plot of predicted and actual survival in days. (D) Residual vs. predicted plots for the survival prediction in days.
Figure 7
Figure 7
K-fold cross-validation analysis. X-axis, fold number; Y-axis, accuracy.
See this image and copyright information in PMC

References

    1. Baid U., Talbar S., Rane S., Gupta S., Thakur M. H., Moiyad A., et al. (2019). Deep learning radiomics algorithm for gliomas (DRAG) model: a novel approach using 3D UNET based deep convolutional neural network for predicting survival in gliomas, in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (Granada: ), 369–379.
    1. Baid U., Talbar S., Rane S., Gupta S., Thakur M. H., Moiyadi A., et al. (2020). A novel approach for fully automatic intra-tumor segmentation with 3D U-Net architecture for gliomas. Front Comput Neurosci. 14:10. 10.3389/fncom.2020.00010 - DOI - PMC - PubMed
    1. Bakas S., Akbari H., Sotiras A., Bilello M., Rozycki M., Kirby J. S., et al. (2017a). Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4, 1–13. 10.1038/sdata.2017.117 - DOI - PMC - PubMed
    1. Bakas S., Akbari H., Sotiras A., Bilello M., Rozycki M., Kirby J. S., et al. (2017b). Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection. Cancer Imaging Arch. 286. 10.7937/K9/TCIA.2017.KLXWJJ1Q - DOI
    1. Bakas S., Reyes M., Jakab A., Bauer S., Rempfler M. (2019). Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv Prepr. arXiv1811.01328.

LinkOut - more resources