Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation

TL;DR

This paper reviews the integration of deep learning and statistical models in 3D MRI brain tumor segmentation, highlighting their combined potential for advancing automated clinical oncology tools.

Contribution

It provides a comprehensive review of statistical and deep learning methods in MRI brain tumor segmentation, emphasizing their integration for improved clinical applications.

Findings

Deep learning has become standard in medical imaging.

Combining statistical and deep learning models enhances automation.

Integrated approaches show promise for clinical oncology.

Abstract

Clinical diagnostic and treatment decisions rely upon the integration of patient-specific data with clinical reasoning. Cancer presents a unique context that influence treatment decisions, given its diverse forms of disease evolution. Biomedical imaging allows noninvasive assessment of disease based on visual evaluations leading to better clinical outcome prediction and therapeutic planning. Early methods of brain cancer characterization predominantly relied upon statistical modeling of neuroimaging data. Driven by the breakthroughs in computer vision, deep learning became the de facto standard in the domain of medical imaging. Integrated statistical and deep learning methods have recently emerged as a new direction in the automation of the medical practice unifying multi-disciplinary knowledge in medicine, statistics, and artificial intelligence. In this study, we critically review major statistical and deep learning models and their applications in brain imaging research with a focus on MRI-based brain tumor segmentation. The results do highlight that model-driven classical statistics and data-driven deep learning is a potent combination for developing automated systems in clinical oncology.