Brain Tumor Radiogenomic Classification of O⁶-Methylguanine-DNA Methyltransferase Promoter Methylation in Malignant Gliomas-Based Transfer Learning

Abstract

Artificial Intelligence (AI) is the subject of a challenge and attention in the field of oncology and raises many promises for preventive diagnosis, but also fears, some of which are based on highly speculative visions for the classification and detection of tumors. A brain tumor that is malignant is a life-threatening disorder. Glioblastoma is the most prevalent kind of adult brain cancer and the 1 with the poorest prognosis, with a median survival time of less than a year. The presence of O6 -methylguanine-DNA methyltransferase (MGMT) promoter methylation, a particular genetic sequence seen in tumors, has been proven to be a positive prognostic indicator and a significant predictor of recurrence. This strong revival of interest in AI is modeled in particular to major technological advances which have significantly increased the performance of the predicted model for medical decision support. Establishing reliable forecasts remains a significant challenge for electronic health records (EHRs). By enhancing clinical practice, precision medicine promises to improve healthcare delivery. The goal is to produce improved prognosis, diagnosis, and therapy through evidence-based sub stratification of patients, transforming established clinical pathways to optimize care for each patient’s individual requirements. The abundance of today’s healthcare data, dubbed “big data,” provides great resources for new knowledge discovery, potentially advancing precision treatment. The latter necessitates multidisciplinary initiatives that will use the knowledge, skills, and medical data of newly established organizations with diverse backgrounds and expertise. The aim of this paper is to use magnetic resonance imaging (MRI) images to train and evaluate your model to detect the presence of MGMT promoter methylation in this competition to predict the genetic subtype of glioblastoma based transfer learning. Our objective is to emphasize the basic problems in the developing disciplines of radiomics and radiogenomics, as well as to illustrate the computational challenges from the perspective of big data analytics.

Adaptive fine-tuning based transfer learning for the identification of MGMT promoter methylation status

“…The difference could also be attributed to our reproduction as the original study only mentioned the names of the features and what classification models were used, but there was not further information on how the images were processed before calculating the features and there were not any comments on what hyper-parameters were used, necessitating our own parameter tuning, and producing radiomics features using images that were not necessarily pre-processed in the same way. From these results, along with the results from Capuozzo et al ( 2022 ) who used an external dataset, even though our results do not necessarily perform as well as the studies mentioned in the introduction section, (Han et al 2018 , Li et al 2018 , Le et al 2020 , Zlochower et al 2020 , Do et al 2022 , Sakly et al 2023 ), it is important to note that the differences in datasets make direct comparisons difficult. This denotes a need for an increase in reproducibility and data availability to determine the actual relative performance between these different models.…”

“…Several previous studies have explored potential in using deep learning to predict methylation status on MR imaging. Depending on the data used, there has been some success with using convolutional neural networks (CNNs) to predict the methylation status with a receiver operating characteristic (ROC) area under the curve (AUC) ranging from 0.58 − 0.91, but due to the size of many of these study’s datasets, ranging from 53 − 498 patients, it is difficult to assess their generalizability, but they indicate promise in using machine learning techniques to identify features correlated with MGMT methylation (Han et al 2018 , Li et al 2018 , Le et al 2020 , Zlochower et al 2020 , Adam Flanders 2021 , Do et al 2022 , Sakly et al 2023 ). There are two analyses that we have found that use the same dataset as this study.…”

“…With regards to its performance, in its initial conception, SpotTune was compared against other fine-tuning models in the Visual Decathlon challenge, and achieved the highest score based on its performance in 10 different image datasets (Guo et al 2018 ). To the best of our knowledge, this study represents the first use of transfer learning with adaptive fine-tuning in MGMT promoter methylation status, while other studies have only considered traditional transfer learning (Sakly et al 2023 ).…”

Transfer Learning in Cancer Genetics, Mutation Detection, Gene Expression Analysis, and Syndrome Recognition

“…The O6-methylguanine DNA methyltransferase (MGMT) promotor methylation decreases the gene expression and improves glioma response to radiotherapy and alkylating agents [ 95 , 96 ]. Sakly et al (2023) [ 80 ] used a pre-trained CNN model to predict the MGMT promotor methylation status based on the multimodal MRI images of glioma patients. They used the TL to transfer the convolutional layers of the CNN model and build a new classifier for this task.…”

“…They used the TL to transfer the convolutional layers of the CNN model and build a new classifier for this task. They used two models (ResNet-50 and DenseNet-201), reaching an accuracy of 100%, but the ResNet50 model had fewer layers and took less elapsed time [ 80 ].…”