Deep and statistical learning in biomedical imaging: State of the art in 3D MRI brain tumor segmentation

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

Automated summary

Clinical diagnosis and treatment decisions require the integration of patient-specific data and clinical reasoning. Cancer, with its diverse forms of disease evolution, presents a unique context influencing treatment decisions. Biomedical imaging, especially deep learning, has become the standard for non-invasive disease assessment, improving clinical outcome prediction and therapeutic planning.