Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles

Rathore, Saima; Iftikhar, Muhammad A.; Chaddad, Ahmad; Singh, Ashish; Gillani, Zeeshan; Abdulkadir, Ahmed

doi:10.1016/j.cmpb.2023.107812

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles
Authors:	Rathore, Saima Iftikhar, Muhammad A. Chaddad, Ahmad Singh, Ashish Gillani, Zeeshan Abdulkadir, Ahmed
et. al:	No
DOI:	10.1016/j.cmpb.2023.107812
Published in:	Computer Methods and Programs in Biomedicine
Volume(Issue):	242
Issue:	107812
Issue Date:	16-Sep-2023
Publisher / Ed. Institution:	Elsevier
ISSN:	0169-2607 1872-7565
Language:	English
Subjects:	Clinical measure; Digital histopathology image; Genomic marker; Glioma; Machine learning; Multi-omics; Radiographic image
Subject (DDC):	006: Special computer methods 610.28: Biomedicine, biomedical engineering
Abstract:	Background: Magnetic resonance imaging (MRI), digital pathology imaging (PATH), demographics, and IDH mutation status predict overall survival (OS) in glioma. Identifying and characterizing predictive features in the different modalities may improve OS prediction accuracy. Purpose: To evaluate the OS prediction accuracy of combinations of prognostic markers in glioma patients. Materials and methods: Multi-contrast MRI, comprising T1-weighted, T1-weighted post-contrast, T2-weighted, T2 fluid-attenuated-inversion-recovery, and pathology images from glioma patients (n = 160) were retrospectively collected (1983–2008) from TCGA alongside age and sex. Phenotypic profiling of tumors was performed by quantifying the radiographic and histopathologic descriptors extracted from the delineated region-of-interest in MRI and PATH images. A Cox proportional hazard model was trained with the MRI and PATH features, IDH mutation status, and basic demographic variables (age and sex) to predict OS. The performance was evaluated in a split-train-test configuration using the concordance-index, computed between the predicted risk score and observed OS. Results: The average age of patients was 51.2years (women: n = 77, age-range=18–84years; men: n = 83, age-range=21–80years). The median OS of the participants was 494.5 (range,3–4752), 481 (range,7–4752), and 524.5 days (range,3–2869), respectively, in complete dataset, training, and test datasets. The addition of MRI or PATH features improved prediction of OS when compared to models based on age, sex, and mutation status alone or their combination (p < 0.001). The full multi-omics model integrated MRI, PATH, clinical, and genetic profiles and predicted the OS best (c-index= 0.87). Conclusion: The combination of imaging, genetic, and clinical profiles leads to a more accurate prognosis than the clinical and/or mutation status.
URI:	https://digitalcollection.zhaw.ch/handle/11475/28968
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Centre for Artificial Intelligence (CAI)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

There are no files associated with this item.

Show full item record

Rathore, S., Iftikhar, M. A., Chaddad, A., Singh, A., Gillani, Z., & Abdulkadir, A. (2023). Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles. Computer Methods and Programs in Biomedicine, 242(107812). https://doi.org/10.1016/j.cmpb.2023.107812

Rathore, S. et al. (2023) ‘Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles’, Computer Methods and Programs in Biomedicine, 242(107812). Available at: https://doi.org/10.1016/j.cmpb.2023.107812.

S. Rathore, M. A. Iftikhar, A. Chaddad, A. Singh, Z. Gillani, and A. Abdulkadir, “Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles,” Computer Methods and Programs in Biomedicine, vol. 242, no. 107812, Sep. 2023, doi: 10.1016/j.cmpb.2023.107812.

RATHORE, Saima, Muhammad A. IFTIKHAR, Ahmad CHADDAD, Ashish SINGH, Zeeshan GILLANI und Ahmed ABDULKADIR, 2023. Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles. Computer Methods and Programs in Biomedicine. 16 September 2023. Bd. 242, Nr. 107812. DOI 10.1016/j.cmpb.2023.107812

Rathore, Saima, Muhammad A. Iftikhar, Ahmad Chaddad, Ashish Singh, Zeeshan Gillani, and Ahmed Abdulkadir. 2023. “Imaging Phenotypes Predict Overall Survival in Glioma More Accurate than Basic Demographic and Cell Mutation Profiles.” Computer Methods and Programs in Biomedicine 242 (107812). https://doi.org/10.1016/j.cmpb.2023.107812.

Rathore, Saima, et al. “Imaging Phenotypes Predict Overall Survival in Glioma More Accurate than Basic Demographic and Cell Mutation Profiles.” Computer Methods and Programs in Biomedicine, vol. 242, no. 107812, Sept. 2023, https://doi.org/10.1016/j.cmpb.2023.107812.