A systematic review of deep learning-based segmentation techniques for brain tumor detection (2013-2023).

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Neurology

Background:

• Brain tumors remain a significant health challenge requiring advanced diagnostic tools.
• Deep learning (DL) techniques have shown promise in medical image analysis, particularly for segmentation tasks.
• Accurate segmentation of brain tumors is crucial for diagnosis, treatment planning, and outcome prediction.

Purpose of the Study:

• To systematically review and analyze publication trends in deep learning-based image segmentation for brain tumor detection.
• To identify key stakeholders, influential research, and prevalent research themes in this domain.
• To map the research landscape and publication dynamics from 2013 to 2023.

Main Methods:

• Systematic review adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.
• Bibliometric analysis of publications from Scopus, PubMed, and Web of Science (2013-2023).
• Analysis included publication trends, stakeholder identification, citation analysis, and keyword co-occurrence using VOSviewer and R Studio.

Main Results:

• A total of 931 documents were analyzed, with a substantial increase in publications from 1 to 310 annually.
• Tongxue Zhou emerged as the most prolific author; key institutions included Imperial College of London and Harvard Medical School.
• Keyword co-occurrence analysis confirmed the prominence of "deep learning brain tumor image segmentation" as a central theme.

Conclusions:

• The research landscape of deep learning for brain tumor image segmentation is rapidly expanding.
• Identified trends, stakeholders, and themes provide valuable insights for future research and policy.
• Findings highlight the multidisciplinary nature and evolving opportunities within brain tumor image segmentation research.