Towards Radiomics-based automated disease progression assessment for glioblastoma patients
Loading...
Author (Corporation)
Publication date
2024
Typ of student thesis
Course of study
Collections
Type
04B - Conference paper
Editor (Corporation)
Supervisor
Parent work
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. 9th International Workshop, BrainLes 2023, and 3rd International Workshop, SWITCH 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8 and 12, 2023, Revised Selected Papers
Special issue
DOI of the original publication
Link
Series
Lecture Notes in Computer Science
Series number
14668
Volume
Issue / Number
Pages / Duration
36-47
Patent number
Publisher / Publishing institution
Springer
Place of publication / Event location
Vancouver
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
Glioblastoma is a highly infiltrative brain tumor with fast progression and poor prognosis for patients. Due to the rapid growth,
close treatment response monitoring is key. In this study, we benchmark different machine learning approaches for automated progression classiu0002fication with various radiomic feature sets extracted from longitudinal magnetic resonance imaging and classifiers. Our experiments show difu0002ferences in robustness and performance and offer insights into common failure modes. The best ROC-AUC was achieved with a random forest classifier without feature selection (0.748), and the best F1 score was at 0.792 for an XGBoost classifier where features of the current time point and the change from the reference time point were provided. Anau0002lyzing misclassifications shows different behavior for statistical machine learning classifiers and Residual Neural Networks.
Keywords
Subject (DDC)
Event
The 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)
Exhibition start date
Exhibition end date
Conference start date
08.10.2023
Conference end date
12.10.2023
Date of the last check
ISBN
978-3-031-76159-1
978-3-031-76160-7
978-3-031-76160-7
ISSN
Language
English
Created during FHNW affiliation
No
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Closed
License
Citation
Suter, Y., Schuhmacher, F., Ermis, E., Knecht, U., Schucht, P., Wiest, R., & Reyes, M. (2024). Towards Radiomics-based automated disease progression assessment for glioblastoma patients. In U. Baid, R. Dorent, S. Malec, M. Pytlarz, R. Su, N. Wijethilake, S. Bakas, & A. Crimi (Eds.), Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. 9th International Workshop, BrainLes 2023, and 3rd International Workshop, SWITCH 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8 and 12, 2023, Revised Selected Papers (pp. 36–47). Springer. https://doi.org/10.1007/978-3-031-76160-7_4