Brain Tumor Segmentation, Grading and Patient Survival Prediction

All primary brain and other central nervous system (CNS) tumors affect 23 people per 100,000 population. Patients with these tumors have very low survival rates (29-35%), and the median survival for is 12-15 months. Gliomas are the most common forms of primary neoplasm in the CNS that originate from resident glial cells. The World Health Organization’s (WHO) grading scale defines four grades (I-IV) of gliomas depending on recurrence rate, aggressiveness, and infiltration. Diffuse low-grade gliomas (LGG) are WHO Grade II and III gliomas. They are infiltrative in their nature and arising from glial cells (astrocytes or oligodendrocytes) of the CNS. Recurrence and malicious progression are possible because the difficulty in complete tumor resection. A group of these tumors may also develop into more aggressive glioblastoma (GBM). An updated classification of diffuse LGG was included in the 2016 WHO Classification of Tumors of the CNS. The new classification of the diffuse LGG depends on the genetic driver mutations. This new classification correlates well with patients’ treatment and survival. Therefore, accurate segmentation and grading of brain tumors are important for prognosis, patient survival and treatment planning. 

With the recent advances in radiomics, pathomics, genomics and deep learning, there is an increasing interest in the analysis of brain tumors from medical images. In this Research Topic, we welcome state-of-the art advances in this area. The topics of submission will include but are not limited to the following:

- Advances in brain tumor imaging
- Radiomics for GBM and other brain gliomas
- Genomics for brain tumor
- Co-analysis of radiomics, genomics, proteomics and pathomics for tumor grading
- Molecular mechanisms and genomics mutations for brain tumor
- Deep learning techniques for segmentation, grading and patient survival
- Evaluation of brain image analysis techniques
- Translation of brain image analysis methods