Related Experiment Video
Updated: Sep 26, 2025
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
OTO-Net: An Automated MRA Image Segmentation Network for Intracranial Aneurysms
Jianming Ye1, Xiaomei Xu2, Liuyi Li2
1First Affiliated Hospital, Gannan Medical University, Ganzhou, China.
Insights
A new One-Two-One Fully Convolutional Network (OTO-Net) accurately segments intracranial aneurysms in MRA images, improving detection and reducing variability in clinical assessments.
Area of Science:
- Neurosurgery
- Radiology
- Medical Imaging
Background:
- Intracranial aneurysms are cerebral blood vessel dilations posing significant mortality and morbidity risks due to potential brain bleeding.
- Accurate detection and segmentation of intracranial aneurysms from Magnetic Resonance Angiography (MRA) are critical for patient management.
- Current manual segmentation methods suffer from interobserver variability, impacting aneurysm assessment and growth tracking.
Purpose of the Study:
- To develop and evaluate a novel automated segmentation method for intracranial aneurysms in MRA images.
- To address the limitations of existing automated methods in handling the diverse appearance of intracranial aneurysms.
- To improve the accuracy and reliability of intracranial aneurysm segmentation in clinical practice.
Main Methods:
- A novel One-Two-One Fully Convolutional Network (OTO-Net) was proposed for automated intracranial aneurysm segmentation.
- The OTO-Net architecture integrates downsampling, upsampling, and skip connections for comprehensive feature extraction.
- Loss ensemble was employed as the objective function to enhance network training efficiency.
Main Results:
- The OTO-Net achieved high automated segmentation accuracy, reaching 98.37% on a public dataset and 97.86% on a private dataset.
- Excellent performance was demonstrated by average surface distances of 1.081 and 0.753, and Dice similarity coefficients of 0.9721 and 0.9813.
- Low Hausdorff distances (0.578 and 0.642) further indicate the model's precision in segmenting intracranial aneurysms.
Conclusions:
- The proposed OTO-Net demonstrates superior performance in automated intracranial aneurysm segmentation from MRA images.
- This novel deep learning approach offers a reliable and accurate alternative to manual segmentation, reducing interobserver variability.
- OTO-Net has the potential to significantly aid clinicians in the accurate detection and assessment of intracranial aneurysms.
Abstract:
Intracranial aneurysms are local dilations of the cerebral blood vessels; people with intracranial aneurysms have a high risk to cause bleeding in the brain, which is related to high mortality and morbidity rates. Accurate detection and segmentation of intracranial aneurysms from Magnetic Resonance Angiography (MRA) images are essential in the clinical routine. Manual annotations used to assess the intracranial aneurysms on MRA images are substantial interobserver variability for both aneurysm detection and assessment of aneurysm size and growth. Many prior automated segmentation works have focused their efforts on tackling the problem, but there is still room for performance improvement due to the significant variability of lesions in the location, size, structure, and morphological appearance. To address these challenges, we propose a novel One-Two-One Fully Convolutional Networks (OTO-Net) for intracranial aneurysms automated segmentation in MRA images. The OTO-Net uses full convolution to achieve intracranial aneurysms automated segmentation through the combination of downsampling, upsampling, and skip connection. In addition, loss ensemble is used as the objective function to steadily improve the backpropagation efficiency of the network structure during the training process. We evaluated the proposed OTO-Net on one public benchmark dataset and one private dataset. Our proposed model can achieve the automated segmentation accuracy with 98.37% and 97.86%, average surface distances with 1.081 and 0.753, dice similarity coefficients with 0.9721 and 0.9813, and Hausdorff distance with 0.578 and 0.642 on these two datasets, respectively.
