Related Experiment Video
Updated: May 22, 2026
06:48
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
Semi-automatic segmentation software for quantitative clinical brain glioblastoma evaluation.
Ying Zhu1, Geoffrey S Young, Zhong Xue
1Department of Systems Medicine and Bioengineering, The Methodist Hospital Research Institute, Weill Cornell Medical College, Houston, TX, USA.
Academic Radiology
|May 18, 2012
Summary
AFINITI software offers semi-automatic segmentation for glioblastoma (GBM) tumors. This tool accurately segments GBM on MRI scans, aiding in tracking disease progression and treatment response.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Oncology
Background:
- Accurate quantitative measurement is crucial for monitoring glioblastoma multiforme (GBM) progression and treatment efficacy.
- Current segmentation methods may require significant manual input, impacting efficiency and consistency.
Purpose of the Study:
- To present and validate AFINITI (Assisted Follow-up in NeuroImaging of Therapeutic Intervention), a novel software pipeline for semi-automatic GBM segmentation.
- To assess the performance of AFINITI using clinical data from GBM patients.
Main Methods:
- AFINITI integrates state-of-the-art voxel-based and deformable shape-based segmentation algorithms.
- The pipeline utilizes T1- and T2-weighted MRI data for automatic segmentation, refined with minimal manual input.
Main Results:
- AFINITI processed 26 clinical GBM patient MRI scans, comparing results against manual segmentation.
- The software features a graphical user interface for visualizing segmentation outcomes.
Conclusions:
- AFINITI demonstrated a high correlation with manual annotations in clinical GBM data.
- The pipeline provides more accurate GBM segmentation than traditional voxel-wise methods, aiding neuroradiological interpretation.
