MGMT promoter methylation status prediction using MRI scans? An extensive experimental evaluation of deep learning models

被引:9
|
作者
Saeed, Numan [1 ]
Ridzuan, Muhammad [1 ]
Alasmawi, Hussain [1 ]
Sobirov, Ikboljon [2 ]
Yaqub, Mohammad [2 ]
机构
[1] Mohamed Bin Zayed Univ Artificial Intelligence, Dept Machine Learning, Abu Dhabi, U Arab Emirates
[2] Mohamed Bin Zayed Univ Artificial Intelligence, Dept Comp Vis, Abu Dhabi, U Arab Emirates
关键词
Radiogenomics; MGMT promoter; Glioblastoma; Deep learning; Interpretability; CLASSIFICATION; TEMOZOLOMIDE; BRAIN;
D O I
10.1016/j.media.2023.102989
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The number of studies on deep learning for medical diagnosis is expanding, and these systems are often claimed to outperform clinicians. However, only a few systems have shown medical efficacy. From this perspective, we examine a wide range of deep learning algorithms for the assessment of glioblastoma - a common brain tumor in older adults that is lethal. Surgery, chemotherapy, and radiation are the standard treatments for glioblastoma patients. The methylation status of the MGMT promoter, a specific genetic sequence found in the tumor, affects chemotherapy's effectiveness. MGMT promoter methylation improves chemotherapy response and survival in several cancers. MGMT promoter methylation is determined by a tumor tissue biopsy, which is then genetically tested. This lengthy and invasive procedure increases the risk of infection and other complications. Thus, researchers have used deep learning models to examine the tumor from brain MRI scans to determine the MGMT promoter's methylation state. We employ deep learning models and one of the largest public MRI datasets of 585 participants to predict the methylation status of the MGMT promoter in glioblastoma tumors using MRI scans. We test these models using Grad-CAM, occlusion sensitivity, feature visualizations, and training loss landscapes. Our results show no correlation between these two, indicating that external cohort data should be used to verify these models' performance to assure the accuracy and reliability of deep learning systems in cancer diagnosis.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] Quality assessment of the MRI-radiomics studies for MGMT promoter methylation prediction in glioma: a systematic review and meta-analysis
    Doniselli, Fabio M.
    Pascuzzo, Riccardo
    Mazzi, Federica
    Padelli, Francesco
    Moscatelli, Marco
    Akinci D'Antonoli, Tugba
    Cuocolo, Renato
    Aquino, Domenico
    Cuccarini, Valeria
    Sconfienza, Luca Maria
    EUROPEAN RADIOLOGY, 2024, 34 (9) : 5802 - 5815
  • [32] Deep learning classification of MGMT status of glioblastomas using multiparametric MRI with a novel domain knowledge augmented mask fusion approach
    Koska, Ilker Ozgur
    Koska, Cagan
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [33] Fusion Radiomics Features from Conventional MRI Predict MGMT Promoter Methylation Status in Lower Grade Gliomas
    Jiang, Chendan
    Kong, Ziren
    Liu, Sirui
    Feng, Shi
    Zhang, Yiwei
    Zhu, Ruizhe
    Chen, Wenlin
    Wang, Yuekun
    Lyu, Yuelei
    You, Hui
    Zhao, Dachun
    Wang, Renzhi
    Wang, Yu
    Ma, Wenbin
    Feng, Feng
    EUROPEAN JOURNAL OF RADIOLOGY, 2019, 121
  • [34] Ensemble learning of multiview CNN models for survival time prediction of brain tumor patients using multimodal MRI scans
    Mossa, Abdela Ahmed
    Cevik, Ulus
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2021, 29 (02) : 616 - 631
  • [35] Blockchain-Based Deep CNN for Brain Tumor Prediction Using MRI Scans
    Mohammad, Farah
    Al Ahmadi, Saad
    Al Muhtadi, Jalal
    DIAGNOSTICS, 2023, 13 (07)
  • [36] Simple and Fast Convolutional Neural Network Applied to Median Cross Sections for Predicting the Presence of MGMT Promoter Methylation in FLAIR MRI Scans
    Chen, Daniel Tianming
    Chen, Allen Tianle
    Wang, Haiyan
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES, BRAINLES 2021, PT I, 2022, 12962 : 227 - 238
  • [37] Improving MGMT methylation status prediction of glioblastoma through optimizing radiomics features using genetic algorithm-based machine learning approach
    Duyen Thi Do
    Yang, Ming-Ren
    Luu Ho Thanh Lam
    Nguyen Quoc Khanh Le
    Wu, Yu-Wei
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [38] Rheumatoid arthritis classification and prediction by consistency-based deep learning using extremity MRI scans
    Li, Yanli
    Hassanzadeh, Tahereh
    Shamonin, Denis P.
    Reijnierse, Monique
    van der Helm-van Mil, Annette H. M.
    Stoel, Berend C.
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 91
  • [39] Discriminating MGMT promoter methylation status in patients with glioblastoma employing amide proton transfer-weighted MRI metrics
    Jiang, Shanshan
    Rui, Qihong
    Wang, Yu
    Heo, Hye-Young
    Zou, Tianyu
    Yu, Hao
    Zhang, Yi
    Wang, Xianlong
    Du, Yongxing
    Wen, Xinrui
    Chen, Fangyao
    Wang, Jihong
    Eberhart, Charles G.
    Zhou, Jinyuan
    Wen, Zhibo
    EUROPEAN RADIOLOGY, 2018, 28 (05) : 2115 - 2123
  • [40] Discriminating MGMT promoter methylation status in patients with glioblastoma employing amide proton transfer-weighted MRI metrics
    Shanshan Jiang
    Qihong Rui
    Yu Wang
    Hye-Young Heo
    Tianyu Zou
    Hao Yu
    Yi Zhang
    Xianlong Wang
    Yongxing Du
    Xinrui Wen
    Fangyao Chen
    Jihong Wang
    Charles G. Eberhart
    Jinyuan Zhou
    Zhibo Wen
    European Radiology, 2018, 28 : 2115 - 2123