A Systematic Review on Recent Advancements in Deep Learning and Mathematical Modeling for Efficient Detection of Glioblastoma

In medical facilities, the glioblastoma detection and growth patterns are critical yet challenging tasks. It is important for early diagnosis and therapy planning to save lives. Glioblastoma, also known as astrocytoma grade IV, is a high-grade glioma and is an extremely aggressive, rapidly growing brain tumor. Only a few research reviews have been accomplished to detect glioblastoma. However, an in-depth analysis of mathematical modeling and deep learning for the detection of glioblastoma and its treatment against proliferation are not emphasized. For this purpose, in this review work, emphasis is given to these factors. Moreover, priorities are also given to the analysis of recent developments in mathematical modeling and deep learning for glioblastoma detection and progression. In addition, the advantages and disadvantages of various deep learning and mathematical modeling are discussed. Furthermore, the clinical utilities of several mathematical models are also analyzed. A critical analysis is carried out to provide a comprehensive understanding of the most recent research in this field. Finally, some challenging issues and future possibilities are covered, which motivate readers to reflect on novel concepts in this area of research.