Deep Learning AI Applications in the Imaging of Glioma

Abstract

This manuscript will review emerging applications of artificial intelligence, specifically deep learning, and its application to glioblastoma multiforme (GBM), the most common primary malignant brain tumor. Current deep learning approaches, commonly convolutional neural networks (CNNs), that take input data from MR images to grade gliomas (high grade from low grade) and predict overall survival will be shown. There will be more in-depth review of recent articles that have applied different CNNs to predict the genetics of glioma on pre-operative MR images, specifically 1p19q codeletion, MGMT promoter, and IDH mutations, which are important criteria for the diagnosis, treatment management, and prognostication of patients with GBM. Finally, there will be a brief mention of current challenges with DL techniques and their application to image analysis in GBM.

Chromatin insulation dynamics in glioblastoma: challenges and future perspectives of precision oncology

“…Computer science leading the incorporation of artificial intelligence into clinical nomograms to generate integrative systems for medicine is changing our approaches to analyze large-scale and complex datasets. Machine learning algorithms are already changing the field of cancer diagnosis and prognosis by exploring diverse data types, including imaging, histology, and multi-omics, to efficiently classify various clinically relevant GBM traits [ 85 – 88 ]. These advances will undoubtedly bring novel and more personalized diagnostic and therapeutic alternatives for patients with GBM.…”

Satellitosis, a Crosstalk between Neurons, Vascular Structures and Neoplastic Cells in Brain Tumours; Early Manifestation of Invasive Behaviour

“…Recent developments in advanced MR and PET scanning have improved CNS imaging, up to the point that now we can collect specific information within brain TME compartments [ 105 , 106 , 107 ]. Nevertheless, a careful histo-morphological evaluation of tumour tissue by pathologists is still of fundamental importance, and features such as Scherer’s secondary structures are still a valuable clue into the diagnosis of diffuse, possibly high-grade gliomas.…”

Satellitosis, a Crosstalk Between Neurons, Vascular Structures and Neoplastic Cells in Brain Tumours; Early Manifestation of Invasive Behaviour

“…Recent developments in advanced MR and PET scanning have improved CNS imaging, up to the point that now we can collect specific information within brain TME compartments [110][111][112]. Nevertheless, a careful histo-morphological evaluation of tumour tissue by pathologists is still of GB cells interact with BBB:…”