1
|
Al-Rahbi A, Al-Mahrouqi O, Al-Saadi T. Uses of artificial intelligence in glioma: A systematic review. MEDICINE INTERNATIONAL 2024; 4:40. [PMID: 38827949 PMCID: PMC11140312 DOI: 10.3892/mi.2024.164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Accepted: 04/26/2024] [Indexed: 06/05/2024]
Abstract
Glioma is the most prevalent type of primary brain tumor in adults. The use of artificial intelligence (AI) in glioma is increasing and has exhibited promising results. The present study performed a systematic review of the applications of AI in glioma as regards diagnosis, grading, prediction of genotype, progression and treatment response using different databases. The aim of the present study was to demonstrate the trends (main directions) of the recent applications of AI within the field of glioma, and to highlight emerging challenges in integrating AI within clinical practice. A search in four databases (Scopus, PubMed, Wiley and Google Scholar) yielded a total of 42 articles specifically using AI in glioma and glioblastoma. The articles were retrieved and reviewed, and the data were summarized and analyzed. The majority of the articles were from the USA (n=18) followed by China (n=11). The number of articles increased by year reaching the maximum number in 2022. The majority of the articles studied glioma as opposed to glioblastoma. In terms of grading, the majority of the articles were about both low-grade glioma (LGG) and high-grade glioma (HGG) (n=23), followed by HGG/glioblastoma (n=13). Additionally, three articles were about LGG only; two articles did not specify the grade. It was found that one article had the highest sample size among the other studies, reaching 897 samples. Despite the limitations and challenges that face AI, the use of AI in glioma has increased in recent years with promising results, with a variety of applications ranging from diagnosis, grading, prognosis prediction, and reaching to treatment and post-operative care.
Collapse
Affiliation(s)
- Adham Al-Rahbi
- College of Medicine and Health Sciences, Sultan Qaboos University, Muscat 123, Sultanate of Oman
| | - Omar Al-Mahrouqi
- College of Medicine and Health Sciences, Sultan Qaboos University, Muscat 123, Sultanate of Oman
| | - Tariq Al-Saadi
- Department of Neurosurgery, Khoula Hospital, Muscat 123, Sultanate of Oman
- Department of Neurology and Neurosurgery-Montreal Neurological Institute, Faculty of Medicine, McGill University, Montreal, QC H3A 2B4, Canada
| |
Collapse
|
3
|
Kertels O, Delbridge C, Sahm F, Ehret F, Acker G, Capper D, Peeken JC, Diehl C, Griessmair M, Metz MC, Negwer C, Krieg SM, Onken J, Yakushev I, Vajkoczy P, Meyer B, Zips D, Combs SE, Zimmer C, Kaul D, Bernhardt D, Wiestler B. Imaging meningioma biology: Machine learning predicts integrated risk score in WHO grade 2/3 meningioma. Neurooncol Adv 2024; 6:vdae080. [PMID: 38957161 PMCID: PMC11217900 DOI: 10.1093/noajnl/vdae080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/04/2024] Open
Abstract
Background Meningiomas are the most common primary brain tumors. While most are benign (WHO grade 1) and have a favorable prognosis, up to one-fourth are classified as higher-grade, falling into WHO grade 2 or 3 categories. Recently, an integrated risk score (IRS) pertaining to tumor biology was developed and its prognostic relevance was validated in a large, multicenter study. We hypothesized imaging data to be reflective of the IRS. Thus, we assessed the potential of a machine learning classifier for its noninvasive prediction using preoperative magnetic resonance imaging (MRI). Methods In total, 160 WHO grade 2 and 3 meningioma patients from 2 university centers were included in this study. All patients underwent surgery with histopathological workup including methylation analysis. Preoperative MRI scans were automatically segmented, and radiomic parameters were extracted. Using a random forest classifier, 3 machine learning classifiers (1 multiclass classifier for IRS and 2 binary classifiers for low-risk and high-risk prediction, respectively) were developed in a training set (120 patients) and independently tested in a hold-out test set (40 patients). Results Multiclass IRS classification had a test set area under the curve (AUC) of 0.7, mostly driven by the difficulties in clearly separating medium-risk from high-risk patients. Consequently, a classifier predicting low-risk IRS versus medium-/high-risk showed a very high test accuracy of 90% (AUC 0.88). In particular, "sphericity" was associated with low-risk IRS classification. Conclusion The IRS, in particular molecular low-risk, can be predicted from imaging data with high accuracy, making this important prognostic classification accessible by imaging.
Collapse
Affiliation(s)
- Olivia Kertels
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Claire Delbridge
- Department of Neuropathology, School of Medicine, Institute of Pathology, Technical University of Munich, Munich, Germany
| | - Felix Sahm
- Department of Neuropathology, Institute of Pathology, University Hospital Heidelberg, Heidelberg, Germany
- Clinical Cooperation Unit Neuropathology, German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Felix Ehret
- German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Güliz Acker
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
- Department of Neurosurgery, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - David Capper
- German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Department of Neuropathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Jan C Peeken
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Christian Diehl
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Michael Griessmair
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Marie-Christin Metz
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Chiara Negwer
- Department of Neurosurgery, Technical University of Munich, School of Medicine, Klinikum rechts der Isar, Munich, Germany
| | - Sandro M Krieg
- Department of Neurosurgery, University Hospital Heidelberg, Heidelberg, Germany
| | - Julia Onken
- Department of Neurosurgery, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Igor Yakushev
- Department of Nuclear Medicine, Klinikum Rechts der Isar, Technical University of Munich, München, Germany
| | - Peter Vajkoczy
- Department of Neurosurgery, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Bernhard Meyer
- Department of Neurosurgery, Technical University of Munich, School of Medicine, Klinikum rechts der Isar, Munich, Germany
| | - Daniel Zips
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Stephanie E Combs
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Claus Zimmer
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - David Kaul
- Faculty of Medicine, HMU Health and Medical University, Potsdam, Germany
- Department of Radiation Oncology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Denise Bernhardt
- Department of Radiation Oncology, Klinikum rechts der Isar, Technische Universität München, Institut für Innovative Radiotherapy (iRT), Munich, Germany
| | - Benedikt Wiestler
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
- TranslaTUM, Center for Translational Cancer Research, Technical University of Munich, Munich, Germany
| |
Collapse
|
4
|
Deng S, Zhu Y. Prediction of Glioma Grade by Tumor Heterogeneity Radiomic Analysis Based on Multiparametric MRI. INT J COMPUT INT SYS 2023. [DOI: 10.1007/s44196-023-00230-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/08/2023] Open
Abstract
AbstractPredicting glioma grade plays a pivotal role in treatment and prognosis. However, several current methods for grading depend on the characteristics of the whole tumor. Predicting grade by analyzing tumor subregions has not been thoroughly investigated, which aims to improve the prediction performance. To predict glioma grade via analysis of tumor heterogeneity with features extracted from tumor subregions, it is mainly divided into four magnetic resonance imaging (MRI) sequences, including T2-weighted (T2), fluid-attenuated inversion recovery (FLAIR), pre-gadolinium T1-weighted (T1), and post-gadolinium T1-weighted methods. This study included the data of 97 patients with glioblastomas and 42 patients with low-grade gliomas before surgery. Three subregions, including enhanced tumor (ET), non-enhanced tumor, and peritumoral edema, were obtained based on segmentation labels generated by the GLISTRBoost algorithm. One hundred radiomic features were extracted from each subregion. Feature selection was performed using the cross-validated recursive feature elimination with a support vector machine (SVM) algorithm. SVM classifiers with grid search were established to predict glioma grade based on unparametric and multiparametric MRI. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the classifiers, and the performance of the subregions was compared with the results of the whole tumor. In uniparametric analysis, the features from the ET subregion yielded a higher AUC value of 0.8697, 0.8474, and 0.8474 than those of the whole tumor of FLAIR, T1, and T2. In multiparametric analysis, the ET subregion achieved the best performance (AUC = 0.8755), which was higher than the uniparametric results. Radiomic features from the tumor subregion can potentially be used as clinical markers to improve the predictive accuracy of glioma grades.
Collapse
|
5
|
AlRayahi J, Alwalid O, Mubarak W, Maaz AUR, Mifsud W. Pediatric Brain Tumors in the Molecular Era: Updates for the Radiologist. Semin Roentgenol 2023; 58:47-66. [PMID: 36732011 DOI: 10.1053/j.ro.2022.09.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Revised: 08/28/2022] [Accepted: 09/30/2022] [Indexed: 11/10/2022]
Affiliation(s)
- Jehan AlRayahi
- Department of Pediatric Radiology, Sidra Medicine, Doha, Qatar.
| | - Osamah Alwalid
- Department of Pediatric Radiology, Sidra Medicine, Doha, Qatar
| | - Walid Mubarak
- Department of Pediatric Radiology, Sidra Medicine, Doha, Qatar
| | - Ata Ur Rehman Maaz
- Department of Pediatric Hematology-Oncology, Sidra Medicine, Doha, Qatar
| | | |
Collapse
|
6
|
Convolutional Neural Networks to Detect Vestibular Schwannomas on Single MRI Slices: A Feasibility Study. Cancers (Basel) 2022; 14:cancers14092069. [PMID: 35565199 PMCID: PMC9104481 DOI: 10.3390/cancers14092069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2022] [Revised: 03/30/2022] [Accepted: 04/19/2022] [Indexed: 02/04/2023] Open
Abstract
Simple Summary Due to the fact that they take inter-slice information into account, 3D- and 2.5D-convolutional neural networks (CNNs) potentially perform better in tumor detection tasks than 2D-CNNs. However, this potential benefit is at the expense of increased computational power and the need for segmentations as an input. Therefore, in this study we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. We retrained (539 patients) and internally validated (94 patients) a pretrained CNN using contrast-enhanced MRI slices from one institution. Furthermore, we externally validated the CNN using contrast-enhanced MRI slices from another institution. This resulted in an accuracy of 0.949 (95% CI 0.935–0.963) and 0.912 (95% CI 0.866–0.958) for the internal and external validation, respectively. Our findings indicate that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased requirement for computational power and the fact that there is no need for segmentations. Abstract In this study. we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. A pretrained CNN (ResNet-34) was retrained and internally validated using contrast-enhanced T1-weighted (T1c) MRI slices from one institution. In a second step, the model was externally validated using T1c- and T1-weighted (T1) slices from a different institution. As a substitute, bisected slices were used with and without tumors originating from whole transversal slices that contained part of the unilateral VS. The model predictions were assessed based on the categorical accuracy and confusion matrices. A total of 539, 94, and 74 patients were included for training, internal validation, and external T1c validation, respectively. This resulted in an accuracy of 0.949 (95% CI 0.935–0.963) for the internal validation and 0.912 (95% CI 0.866–0.958) for the external T1c validation. We suggest that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased demand for computational power and the fact that there is no need for segmentations. However, further research is needed on the difference between 2D-CNNs and more complex architectures.
Collapse
|