logo
ResearchBunny Logo
Automated detection of intracranial aneurysms using skeleton-based 3D patches, semantic segmentation, and auxiliary classification for overcoming data imbalance in brain TOF-MRA

Medicine and Health

Automated detection of intracranial aneurysms using skeleton-based 3D patches, semantic segmentation, and auxiliary classification for overcoming data imbalance in brain TOF-MRA

S. Ham, J. Seo, et al.

This groundbreaking study introduces a CNN model that demonstrates impressive accuracy in detecting intracranial aneurysms through 3D TOF-MRA imaging. Conducted by a team of esteemed researchers, this innovative approach not only highlights the model's capabilities but also suggests significant potential for clinical use.

00:00
00:00
~3 min • Beginner • English
Abstract
Accurate and reliable detection of intracranial aneurysms is vital for subsequent treatment to prevent bleeding. However, the detection of intracranial aneurysms can be time-consuming and even challenging, and there is great variability among experts, especially in the case of small aneurysms. This study aimed to detect intracranial aneurysms accurately using a convolutional neural network (CNN) with 3D time-of-flight magnetic resonance angiography (TOF-MRA). A total of 154 3D TOF-MRA datasets with intracranial aneurysms were acquired, and the gold standards were manually drawn by neuroradiologists. We also obtained 113 subjects from a public dataset for external validation. These angiograms were pre-processed using skull-stripping, signal intensity normalization, and N4 bias correction. The 3D patches along the vessel skeleton from MRA were extracted. Values of the ratio between the aneurysmal and the normal patches ranged from 1:1 to 1:5. The semantic segmentation on intracranial aneurysms was trained using a 3D U-Net with an auxiliary classifier to overcome the imbalance in patches. The proposed method achieved an accuracy of 0.910 in internal validation and external validation accuracy of 0.883 with a 2:1 ratio of normal to aneurysmal patches. This multi-task learning method showed that the aneurysm segmentation performance was sufficient to be helpful in an actual clinical setting.
Publisher
Scientific Reports
Published On
Jul 11, 2023
Authors
Sungwon Ham, Jiyeon Seo, Jihye Yun, Yun Jung Bae, Tackeun Kim, Leonard Sunwoo, Sooyoung Yoo, Seung Chai, Jeong-Whun Kim, Namkug Kim
Tags
convolutional neural network
intracranial aneurysms
3D TOF-MRA
semantic segmentation
data imbalance
clinical application
machine learning
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny