Related Experiment Video
Updated: Jun 19, 2026
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
Towards consistency in pediatric brain tumor measurements: Challenges, solutions, and the role of artificial
Ariana M Familiar1,2, Anahita Fathi Kazerooni1,2,3,4, Arastoo Vossough5,1
1Center for Data-Driven Discovery in Biomedicine (D3b), Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA.
Abstract:
MR imaging is central to the assessment of tumor burden and changes over time in neuro-oncology. Several response assessment guidelines have been set forth by the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working groups in different tumor histologies; however, the visual delineation of tumor components using MRIs is not always straightforward, and complexities not currently addressed by these criteria can introduce inter- and intra-observer variability in manual assessments. Differentiation of non-enhancing tumors from peritumoral edema, mild enhancement from absence of enhancement, and various cystic components can be challenging; particularly given a lack of sufficient and uniform imaging protocols in clinical practice. Automated tumor segmentation with artificial intelligence (AI) may be able to provide more objective delineations, but rely on accurate and consistent training data created manually (ground truth). Herein, this paper reviews existing challenges and potential solutions to identifying and defining subregions of pediatric brain tumors (PBTs) that are not explicitly addressed by current guidelines. The goal is to assert the importance of defining and adopting criteria for addressing these challenges, as it will be critical to achieving standardized tumor measurements and reproducible response assessment in PBTs, ultimately leading to more precise outcome metrics and accurate comparisons among clinical studies.
Insights
Challenges in pediatric brain tumor imaging assessment persist due to subjective MRI interpretations. This review highlights issues and proposes solutions for standardized tumor measurement and reproducible response assessment in pediatric brain tumors (PBTs).
Area of Science:
- Neuro-oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Magnetic Resonance (MR) imaging is crucial for evaluating tumor burden in neuro-oncology.
- Current Response Assessment in Pediatric Neuro-Oncology (RAPNO) guidelines face challenges with subjective MRI interpretations.
- Variability in manual assessments stems from difficulties in differentiating tumor components and lack of standardized imaging protocols.
Purpose of the Study:
- To review current challenges in identifying and defining subregions of pediatric brain tumors (PBTs) not covered by existing guidelines.
- To explore potential solutions, including artificial intelligence (AI), for objective tumor delineation.
- To emphasize the need for standardized criteria for reproducible response assessment in PBTs.
Main Methods:
- Review of existing literature on MR imaging challenges in pediatric neuro-oncology.
- Analysis of complexities in manual tumor segmentation and response assessment.
- Discussion of the role of AI in automated tumor segmentation and the need for accurate training data.
Main Results:
- Current MR imaging assessment of PBTs suffers from inter- and intra-observer variability.
- Difficulties include differentiating non-enhancing tumors from edema, mild enhancement, and cystic components.
- AI-driven segmentation offers potential for objectivity but requires high-quality, standardized ground truth data.
Conclusions:
- Standardized criteria are essential to address current limitations in PBT imaging assessment.
- Adopting clear definitions for tumor subregions will improve measurement accuracy and reproducibility.
- Enhanced standardization will lead to more precise outcome metrics and reliable comparisons across clinical studies.
