Journal article
Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: a comparison of diagnostic performance across different MRI sequences and machine learning techniques
European radiology, Vol.31(11), pp.8703-8713
04/23/2021
DOI: 10.1007/s00330-021-07845-6
PMID: 33890149
Abstract
Despite the robust diagnostic performance of MRI-based radiomic features for differentiating between glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) reported on prior studies, the best sequence or a combination of sequences and model performance across various machine learning pipelines remain undefined. Herein, we compare the diagnostic performance of multiple radiomics-based models to differentiate GBM from PCNSL.
Our retrospective study included 94 patients (34 with PCNSL and 60 with GBM). Model performance was assessed using various MRI sequences across 45 possible model and feature selection combinations for nine different sequence permutations. Predictive performance was assessed using fivefold repeated cross-validation with five repeats. The best and worst performing models were compared to assess differences in performance.
The predictive performance, both using individual and a combination of sequences, was fairly robust across multiple top performing models (AUC: 0.961-0.977) but did show considerable variation between the best and worst performing models. The top performing individual sequences had comparable performance to multiparametric models. The best prediction model in our study used a combination of ADC, FLAIR, and T1-CE achieving the highest AUC of 0.977, while the second ranked model used T1-CE and ADC, achieving a cross-validated AUC of 0.975.
Radiomics-based predictive accuracy can vary considerably, based on the model and feature selection methods as well as the combination of sequences used. Also, models derived from limited sequences show performance comparable to those derived from all five sequences.
• Radiomics-based diagnostic performance of various machine learning models for differentiating glioblastoma and PCNSL varies considerably. • ML models using limited or multiple MRI sequences can provide comparable performance, based on the chosen model. • Embedded feature selection models perform better than models using a priori feature reduction.
Details
- Title: Subtitle
- Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: a comparison of diagnostic performance across different MRI sequences and machine learning techniques
- Creators
- Girish Bathla - Department of Radiology, University of Iowa Hospitals and Clinics, 200 Hawkins Drive, Iowa City, IA, 52242, USASarv Priya - Department of Radiology, University of Iowa Hospitals and Clinics, 200 Hawkins Drive, Iowa City, IA, 52242, USA. sarv-priya@uiowa.eduYanan Liu - College of Engineering, University of Iowa, Iowa City, IA, USACaitlin Ward - Department of Biostatistics, University of Iowa, Iowa City, IA, USANam H Le - College of Engineering, University of Iowa, Iowa City, IA, USARavishankar Pillenahalli Maheshwarappa - Department of Radiology, University of Iowa Hospitals and Clinics, 200 Hawkins Drive, Iowa City, IA, 52242, USANeetu Soni - Department of Radiology, University of Iowa Hospitals and Clinics, 200 Hawkins Drive, Iowa City, IA, 52242, USAVarun Monga - Department of Medicine, University of Iowa Hospitals and Clinics, Iowa City, IA, USAHonghai Zhang - College of Engineering, University of Iowa, Iowa City, IA, USAMilan Sonka - College of Engineering, University of Iowa, Iowa City, IA, USA
- Resource Type
- Journal article
- Publication Details
- European radiology, Vol.31(11), pp.8703-8713
- DOI
- 10.1007/s00330-021-07845-6
- PMID
- 33890149
- NLM abbreviation
- Eur Radiol
- ISSN
- 0938-7994
- eISSN
- 1432-1084
- Language
- English
- Date published
- 04/23/2021
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Hematology, Oncology, and Blood & Marrow Transplantation; Radiation Oncology; Nursing; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Internal Medicine; Ophthalmology and Visual Sciences
- Record Identifier
- 9984101223102771
Metrics
56 Record Views