Evaluating Autoencoders for Dimensionality Reduction of MRI-derived Radiomics and Classification of Malignant Brain Tumors

Mikayla Biggs; Yaohua Wang; Neetu Soni; Sarv Priya; Girish Bathla; Guadalupe M Canahuate

doi:10.1145/3603719.3603737

Back

Evaluating Autoencoders for Dimensionality Reduction of MRI-derived Radiomics and Classification of Malignant Brain Tumors

Conference proceeding

Open access

Evaluating Autoencoders for Dimensionality Reduction of MRI-derived Radiomics and Classification of Malignant Brain Tumors

Mikayla Biggs, Yaohua Wang, Neetu Soni, Sarv Priya, Girish Bathla and Guadalupe M Canahuate

SSDBM '23: Proceedings of the 35th International Conference on Scientific and Statistical Database Management, pp.1-11

08/27/2023

DOI: 10.1145/3603719.3603737

PMCID: PMC10853989

PMID: 38344216

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1145/3603719.3603737View

Published (Version of record) Open Access

Abstract

Malignant brain tumors including parenchymal metastatic (MET) lesions, glioblastomas (GBM), and lymphomas (LYM) account for 29.7% of brain cancers. However, the characterization of these tumors from MRI imaging is difficult due to the similarity of their radiologically observed image features. Radiomics is the extraction of quantitative imaging features to characterize tumor intensity, shape, and texture. Applying machine learning over radiomic features could aid diagnostics by improving the classification of these common brain tumors. However, since the number of radiomic features is typically larger than the number of patients in the study, dimensionality reduction is needed to balance feature dimensionality and model complexity. Autoencoders are a form of unsupervised representation learning that can be used for dimensionality reduction. It is similar to PCA but uses a more complex and non-linear model to learn a compact latent space. In this work, we examine the effectiveness of autoencoders for dimensionality reduction on the radiomic feature space of multiparametric MRI images and the classification of malignant brain tumors: GBM, LYM, and MET. We further aim to address the class imbalances imposed by the rarity of lymphomas by examining different approaches to increase overall predictive performance through multiclass decomposition strategies.

dimensionality reduction

radiomics

autoencoders

malignant brain tumors

UIOWA OA Agreement

Details

Title: Subtitle: Evaluating Autoencoders for Dimensionality Reduction of MRI-derived Radiomics and Classification of Malignant Brain Tumors
Creators: Mikayla Biggs
Yaohua Wang - University of Iowa
Neetu Soni - University of Rochester Medical Center
Sarv Priya - University of Iowa, Radiology
Girish Bathla
Guadalupe M Canahuate - University of Iowa, Electrical and Computer Engineering
Resource Type: Conference proceeding
Publication Details: SSDBM '23: Proceedings of the 35th International Conference on Scientific and Statistical Database Management, pp.1-11
DOI: 10.1145/3603719.3603737
PMID: 38344216
PMCID: PMC10853989
Publisher: Association for Computing Machinery (ACM)
Language: English
Date published: 08/27/2023
Academic Unit: Radiology; Electrical and Computer Engineering; Internal Medicine
Record Identifier: 9984473236902771

Metrics

12 Record Views