Analyzing pediatric tumors may be more challenging than for adults for multiple reasons, including the rarity of these conditions, their unique characteristics compared to adults, and the developing brain of children. These challenges have negatively impacted technological and methodological progress in pediatric neuro-oncology. As a result, there is currently no accessible and standardized computational infrastructure that can perform quantitative analysis of brain tumors at the point of care of affected children. To address this issue, there has been a growing focus on the development of automated, robust, and versatile tools. By leveraging such tools, we can significantly improve the accuracy of diagnosis, treatment planning, and response assessment for patients with gliomas. This amplifies the urgency for advancements in brain tumor analysis. To achieve our objectives, we have developed a multi-disciplinary team with extensive experience in clinical pediatric neuro-oncology, neuroradiology, machine learning (ML) and artificial intelligence (AI). We propose to create a robust platform based on advanced and explainable AI methods, tailored for the comprehensive analysis of pediatric brain tumors.
– CBTN images will be Develop tools for automated tumor segmentation and treatment response assessment.
– Predict Treatment Response Based on Pre- and Post-treatment mp-MRI Scans.
– Validate the clinical decision support automated tool
