Related Experiment Video
Updated: Apr 18, 2026
High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
Published on: November 10, 2015
Statistical validation of automatic methods for hippocampus segmentation in MR images of epileptic patients
Abstract:
Hippocampus segmentation is a key step in the evaluation of mesial Temporal Lobe Epilepsy (mTLE) by MR images. Several automated segmentation methods have been introduced for medical image segmentation. Because of multiple edges, missing boundaries, and shape changing along its longitudinal axis, manual outlining still remains the benchmark for hippocampus segmentation, which however, is impractical for large datasets due to time constraints. In this study, four automatic methods, namely FreeSurfer, Hammer, Automatic Brain Structure Segmentation (ABSS), and LocalInfo segmentation, are evaluated to find the most accurate and applicable method that resembles the bench-mark of hippocampus. Results from these four methods are compared against those obtained using manual segmentation for T1-weighted images of 157 symptomatic mTLE patients. For performance evaluation of automatic segmentation, Dice coefficient, Hausdorff distance, Precision, and Root Mean Square (RMS) distance are extracted and compared. Among these four automated methods, ABSS generates the most accurate results and the reproducibility is more similar to expert manual outlining by statistical validation. By considering p-value<;0.05, the results of performance measurement for ABSS reveal that, Dice is 4%, 13%, and 17% higher, Hausdorff is 23%, 87%, and 70% lower, precision is 5%, -5%, and 12% higher, and RMS is 19%, 62%, and 65% lower compared to LocalInfo, FreeSurfer, and Hammer, respectively.
Insights
Automatic Brain Structure Segmentation (ABSS) is the most accurate method for hippocampus segmentation in mesial Temporal Lobe Epilepsy (mTLE) patients. This automated approach closely mimics manual outlining, offering a practical solution for large datasets.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Epilepsy Research
Background:
- Hippocampus segmentation is crucial for evaluating mesial Temporal Lobe Epilepsy (mTLE) using MR images.
- Manual segmentation, while the benchmark, is time-consuming and impractical for large datasets.
- Existing automated methods face challenges due to complex anatomical features like multiple edges and shape variations.
Purpose of the Study:
- To evaluate and compare four automated hippocampus segmentation methods: FreeSurfer, Hammer, Automatic Brain Structure Segmentation (ABSS), and LocalInfo.
- To identify the most accurate and applicable automated method that approximates manual segmentation benchmarks.
- To assess the performance of these methods on T1-weighted MR images from 157 mTLE patients.
Main Methods:
- Four automated segmentation algorithms (FreeSurfer, Hammer, ABSS, LocalInfo) were applied to T1-weighted MR images of 157 mTLE patients.
- Performance was evaluated by comparing automated results against manual segmentation using Dice coefficient, Hausdorff distance, Precision, and Root Mean Square (RMS) distance.
- Statistical validation was employed to assess the reproducibility and accuracy of each method.
Main Results:
- Automatic Brain Structure Segmentation (ABSS) demonstrated superior accuracy compared to LocalInfo, FreeSurfer, and Hammer.
- ABSS achieved higher Dice coefficients (4-17% increase) and Precision (5-12% increase) compared to the other methods.
- ABSS significantly reduced Hausdorff distance (23-87% decrease) and RMS distance (19-65% decrease), indicating better boundary adherence and shape similarity to manual segmentation.
Conclusions:
- Automatic Brain Structure Segmentation (ABSS) is the most accurate and reproducible automated method for hippocampus segmentation in mTLE patients.
- ABSS offers a reliable and efficient alternative to manual segmentation, suitable for large-scale neuroimaging studies.
- This finding has significant implications for improving the diagnostic and prognostic evaluation of mTLE.
