Artificial Intelligence and Big Data Analysis in Brain Tumors Research

Background

Over the years, brain tumor research has faced several challenges that produced a negative impact on the early detection, diagnosis, treatment, and progression of brain tumors.

These challenges include (i) the complex nature of the brain, (ii) the heterogeneity of different types of brain tumors, (iii) the presence of the brain blood barriers, (iv) late detection and diagnosis, (v) lack of biomarkers and (vi) limited access to biopsies due to the invasive nature of this procedure.

Although brain tumor research started in the 1900s and more than 100 thousand articles have been published, innovative and feasible research is yet to be conducted to develop novel approaches for the early detection of brain tumors and facilitate noninvasive methods of investigation.

A noticeable increase was observed in the number of publications about artificial intelligence (AI) and big data analytics to tackle the challenges that are associated with brain tumors (Figure 1). It seems that future research will focus on these advanced techniques to navigate through the delicate elements of brain tumors using transformative and noninvasive strategies.

Designs and protocols

Imaging segmentation is one of the key protocols that uses patients’ MRI and CT images to identify the features and boundaries of the brain tumors. In addition, Computer–Aided Diagnosis (CAD) systems enhance the ability to illustrate the features of the tumor, and with additional predictive modeling techniques, management plans will be more feasible and effective.

Furthermore, Natural Language Processing (NLP) represents an important method in text mining and information extraction of medical records and clinical notes to provide a comprehensive understanding of the patient’s medical history, treatments, and outcomes (Figure 2).

Selected free full-text articles

• Chen T, Hu L, Lu Q, Xiao F, Xu H, Li H, Lu L. A computer-aided diagnosis system for brain tumors based on artificial intelligence algorithms. Front Neurosci. 2023 Jul 7;17:1120781. doi: 10.3389/fnins.2023.1120781. PMID: 37483342; PMCID: PMC10360168. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10360168/
  
  
• Sakly H, Said M, Seekins J, Guetari R, Kraiem N, Marzougui M. Brain Tumor Radiogenomic Classification of O6-Methylguanine-DNA Methyltransferase Promoter Methylation in Malignant Gliomas-Based Transfer Learning. Cancer Control. 2023 Jan-Dec;30:10732748231169149. doi: 10.1177/10732748231169149. PMID: 37078100; PMCID: PMC10126792. https://pubmed.ncbi.nlm.nih.gov/37078100/
  
  
• Jean-Quartier C, Jeanquartier F, Holzinger A. Open Data for Differential Network Analysis in Glioma. Int J Mol Sci. 2020 Jan 15;21(2):547. doi: 10.3390/ijms21020547. PMID: 31952211; PMCID: PMC7013918. https://pubmed.ncbi.nlm.nih.gov/31952211/
  
  
• Wu YP, Lin YS, Wu WG, Yang C, Gu JQ, Bai Y, Wang MY. Semiautomatic Segmentation of Glioma on Mobile Devices. J Healthc Eng. 2017;2017:8054939. doi: 10.1155/2017/8054939. Epub 2017 Jun 27. PMID: 29065648; PMCID: PMC5504950. https://pubmed.ncbi.nlm.nih.gov/29065648/
  
  
• Dundar TT, Yurtsever I, Pehlivanoglu MK, Yildiz U, Eker A, Demir MA, Mutluer AS, Tektaş R, Kazan MS, Kitis S, Gokoglu A, Dogan I, Duru N. Machine Learning-Based Surgical Planning for Neurosurgery: Artificial Intelligent Approaches to the Cranium. Front Surg. 2022 Apr 29;9:863633. doi: 10.3389/fsurg.2022.863633. PMID: 35574559; PMCID: PMC9099011. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9099011/