Share Email Print

Proceedings Paper

Multi-resolution CNN for brain vessel segmentation from cerebrovascular images of intracranial aneurysm: a comparison of U-Net and DeepMedic
Author(s): Tatsat R. Patel; Nikhil Paliwal; Prakhar Jaiswal; Muhammad Waqas; Maxim Mokin; Adnan H. Siddiqui; Hui Meng; Rahul Rai; Vincent Tutino
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Background: Vascular segmentation of cerebral vascular imaging is tedious and manual, hindering translation of imagebased computational tools for neurovascular disease (such as intracranial aneurysm) management. Current cerebrovascular segmentation techniques use classic model-based algorithms, but such algorithms are incapable of distinguishing vasculature from artifacts. Deep Learning, specifically the widely accepted U-Net architecture, could be an effective alternative to conventional approaches for cerebrovascular segmentation, but has been shown to perform poorly in segmentation of smaller yet critical vessels. Methods: In this study, we present a methodology using a specialized convolutional neural network (CNN) architecture— DeepMedic—which uses multi-resolution inputs to enhance the field of view of the architecture, thereby enhancing the accuracy of segmentation of smaller vessels. To show the capability of this architecture, we collected and segmented a total of 100 digital subtraction angiography (DSA) images of cerebral vessels for training, internal validation, and testing (n=80, n=10, and n=10, respectively). Results: The DeepMedic architecture yielded high performance with a Connectivity-Area-Length (CAL) of 0.84±0.07 and a dice similarity coefficient (DSC) of 0.94±0.02 in the independent testing cohort. This was better than U-Net optimized for the patch-size and %-overlap in predictions, which performed with a CAL of 0.79±0.06 and a DSC of 0.92±0.02. Notably, our work demonstrated that DeepMedic (CAL: 0.45±0.12) outperformed U-Net (CAL: 0.59±0.11) for segmentation of smaller vessels. Conclusions: Our work showed DeepMedic performs better than the current state-of-the-art method for cerebrovascular segmentation. We hope this study begins to bring a high fidelity deep-learning based approach closer to clinical translation.

Paper Details

Date Published: 16 March 2020
PDF: 9 pages
Proc. SPIE 11314, Medical Imaging 2020: Computer-Aided Diagnosis, 113142W (16 March 2020); doi: 10.1117/12.2549761
Show Author Affiliations
Tatsat R. Patel, Univ. at Buffalo (United States)
Nikhil Paliwal, Univ. at Buffalo (United States)
Prakhar Jaiswal, Univ. at Buffalo (United States)
Muhammad Waqas, Univ. at Buffalo (United States)
Maxim Mokin, Univ. of Florida (United States)
Adnan H. Siddiqui, Canon Stroke and Vascular Research Ctr. (United States)
Univ. at Buffalo (United States)
Univ. of Florida (United States)
Hui Meng, Univ. at Buffalo (United States)
Canon Stroke and Vascular Research Ctr. (United States)
Rahul Rai, Univ. at Buffalo (United States)
Vincent Tutino, Canon Stroke and Vascular Research Ctr. (United States)
Univ. at Buffalo (United States)

Published in SPIE Proceedings Vol. 11314:
Medical Imaging 2020: Computer-Aided Diagnosis
Horst K. Hahn; Maciej A. Mazurowski, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?