Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review
Malignant brain tumors pose a substantial burden on morbidity and mortality. As clinical data collection improves, along with the capacity to analyze it, novel predictive clinical tools may improve prognosis prediction. Deep learning (DL) holds promise for integrating clinical data of various modali...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-01-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/15/2/545 |
_version_ | 1797444792225890304 |
---|---|
author | Kaitlyn Alleman Erik Knecht Jonathan Huang Lu Zhang Sandi Lam Michael DeCuypere |
author_facet | Kaitlyn Alleman Erik Knecht Jonathan Huang Lu Zhang Sandi Lam Michael DeCuypere |
author_sort | Kaitlyn Alleman |
collection | DOAJ |
description | Malignant brain tumors pose a substantial burden on morbidity and mortality. As clinical data collection improves, along with the capacity to analyze it, novel predictive clinical tools may improve prognosis prediction. Deep learning (DL) holds promise for integrating clinical data of various modalities. A systematic review of the DL-based prognostication of gliomas was performed using the Embase (Elsevier), PubMed MEDLINE (National library of Medicine), and Scopus (Elsevier) databases, in accordance with PRISMA guidelines. All included studies focused on the prognostication of gliomas, and predicted overall survival (13 studies, 81%), overall survival as well as genotype (2 studies, 12.5%), and response to immunotherapy (1 study, 6.2%). Multimodal analyses were varied, with 6 studies (37.5%) combining MRI with clinical data; 6 studies (37.5%) integrating MRI with histologic, clinical, and biomarker data; 3 studies (18.8%) combining MRI with genomic data; and 1 study (6.2%) combining histologic imaging with clinical data. Studies that compared multimodal models to unimodal-only models demonstrated improved predictive performance. The risk of bias was mixed, most commonly due to inconsistent methodological reporting. Overall, the use of multimodal data in DL assessments of gliomas leads to a more accurate overall survival prediction. However, due to data limitations and a lack of transparency in model and code reporting, the full extent of multimodal DL as a resource for brain tumor patients has not yet been realized. |
first_indexed | 2024-03-09T13:16:39Z |
format | Article |
id | doaj.art-99ae23aa8a444506baac8bac62fbd028 |
institution | Directory Open Access Journal |
issn | 2072-6694 |
language | English |
last_indexed | 2024-03-09T13:16:39Z |
publishDate | 2023-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Cancers |
spelling | doaj.art-99ae23aa8a444506baac8bac62fbd0282023-11-30T21:35:23ZengMDPI AGCancers2072-66942023-01-0115254510.3390/cancers15020545Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic ReviewKaitlyn Alleman0Erik Knecht1Jonathan Huang2Lu Zhang3Sandi Lam4Michael DeCuypere5Chicago Medical School, Rosalind Franklin University of Science and Medicine, Chicago, IL 60064, USAChicago Medical School, Rosalind Franklin University of Science and Medicine, Chicago, IL 60064, USADivision of Pediatric Neurosurgery, Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USADivision of Pediatric Neurosurgery, Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USADivision of Pediatric Neurosurgery, Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USADivision of Pediatric Neurosurgery, Ann and Robert H. Lurie Children’s Hospital of Chicago, Chicago, IL 60611, USAMalignant brain tumors pose a substantial burden on morbidity and mortality. As clinical data collection improves, along with the capacity to analyze it, novel predictive clinical tools may improve prognosis prediction. Deep learning (DL) holds promise for integrating clinical data of various modalities. A systematic review of the DL-based prognostication of gliomas was performed using the Embase (Elsevier), PubMed MEDLINE (National library of Medicine), and Scopus (Elsevier) databases, in accordance with PRISMA guidelines. All included studies focused on the prognostication of gliomas, and predicted overall survival (13 studies, 81%), overall survival as well as genotype (2 studies, 12.5%), and response to immunotherapy (1 study, 6.2%). Multimodal analyses were varied, with 6 studies (37.5%) combining MRI with clinical data; 6 studies (37.5%) integrating MRI with histologic, clinical, and biomarker data; 3 studies (18.8%) combining MRI with genomic data; and 1 study (6.2%) combining histologic imaging with clinical data. Studies that compared multimodal models to unimodal-only models demonstrated improved predictive performance. The risk of bias was mixed, most commonly due to inconsistent methodological reporting. Overall, the use of multimodal data in DL assessments of gliomas leads to a more accurate overall survival prediction. However, due to data limitations and a lack of transparency in model and code reporting, the full extent of multimodal DL as a resource for brain tumor patients has not yet been realized.https://www.mdpi.com/2072-6694/15/2/545machine learningdeep learningmultimodalbrain tumorgliomaradiomics |
spellingShingle | Kaitlyn Alleman Erik Knecht Jonathan Huang Lu Zhang Sandi Lam Michael DeCuypere Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review Cancers machine learning deep learning multimodal brain tumor glioma radiomics |
title | Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review |
title_full | Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review |
title_fullStr | Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review |
title_full_unstemmed | Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review |
title_short | Multimodal Deep Learning-Based Prognostication in Glioma Patients: A Systematic Review |
title_sort | multimodal deep learning based prognostication in glioma patients a systematic review |
topic | machine learning deep learning multimodal brain tumor glioma radiomics |
url | https://www.mdpi.com/2072-6694/15/2/545 |
work_keys_str_mv | AT kaitlynalleman multimodaldeeplearningbasedprognosticationingliomapatientsasystematicreview AT erikknecht multimodaldeeplearningbasedprognosticationingliomapatientsasystematicreview AT jonathanhuang multimodaldeeplearningbasedprognosticationingliomapatientsasystematicreview AT luzhang multimodaldeeplearningbasedprognosticationingliomapatientsasystematicreview AT sandilam multimodaldeeplearningbasedprognosticationingliomapatientsasystematicreview AT michaeldecuypere multimodaldeeplearningbasedprognosticationingliomapatientsasystematicreview |