ABSTRACT
The use of artificial intelligence algorithm to determine whether the lesion has cerebral aneurysm, especially small aneurysms, is still not completely solved. In this paper, the Faster R-CNN network was used as the localization network, and the model was trained by adjusting the network parameters, and the appropriate feature extraction network and classification network were selected to finally solve the localization problem of small aneurysms. Compared with most 3D methods, this method had the characteristics of shorter training cycle and faster image recognition. The experimental results show that the algorithm has a high accuracy in discriminating whether the lesion has cerebral aneurysm, but the false positive phenomenon may occur in the identification of single image localization. Finally, the paper discusses the experimental results and puts forward some conjecture ideas to solve the problem.
- Shvets, A. A., Iglovikov, V. I., Rakhlin, A. & Kalinin, A. A. (2018). Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks. Presented at 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). Orlando.Google ScholarCross Ref
- Huang, G, Liu, Z, Laurens, V & Weinberger, K Q. (2017). Densely Connected Convolutional Networks. Presented at 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Hawaii.Google ScholarCross Ref
- He, K, Zhang, X, Ren, S & Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Ccmputer Vision and Pattern Recognition (CVPR). Las Vegas.Google Scholar
- Long, J, Shelhamer, E & Darrell, T. (2015). Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(4), 640-651.Google Scholar
- Li, Mengxin, Li, Meiling, Pei, Wenlong & Xu, Rui. (2021). Cerebral Vascular Image Segmentation Method Based on CNN and Local Information. Computer simulation. 38(05), 344-347+352. (in Chinese).Google Scholar
- Liu, Chen, Xiao, Zhiyong and Du, Nianmao. (2019). Application of Improved Convolutional Neural Network in Medical Image Segmentation. Computer science and exploration. 13(09), 1593-1603. (in Chinese).Google Scholar
- Çiçek, Özgün, Abdulkadir, Ahmed, Lienkamp, Soeren S., Brox, Thomas & Ronneberger, Olaf. (2016). 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. CoRR. Volume abs/1606.06650.Google Scholar
- Ning, Jiaxu, Zhao, Haitong, Lan, Lei, Sun, Peng & Feng Yunfei. (2019). A Computer-Aided Detection System for the Detection of Lung Nodules Based on 3D-ResNet. Applied Sciences. 9(24), 5544. https://doi.org/10.3390/app9245544.Google ScholarCross Ref
- Zhan, Tianming, Xiao, Liang , Zhang, Jun & Wei, Zhihui. (2013). A 4D Brain Image Segmentation Model Based on Space-time Continuum Constraint. Acta Electronica Sinica. 8, 1592-1597. (in Chinese).Google Scholar
- Ren, Shaoqing, He, Kaiming, Girshick, Ross & Sun, Jian. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE transactions on pattern analysis and machine intelligence. 39(6), 1137-1149.Google ScholarDigital Library
- Kaiming He,Xiangyu Zhang,Shaoqing Ren & Jian Sun 0001. (2015). Deep Residual Learning for Image Recognition. CoRR. Volume abs/1512.03385.Google Scholar
- Zuiderveld, Karel. (1994). Contrast limited adaptive histogram equalization. Graphics gems IV. Academic Press Professional, Inc.Google Scholar
Recommendations
Fovea Localization in Fundus Photographs by Faster R-CNN with Physiological Prior
Ophthalmic Medical Image AnalysisAbstractA macular fovea is a physiological structure of the human retina, which is an essential optical center. The distance between the lesion area and the foveal center determines the severity degree of visual impacts. Therefore, accurate fovea ...
Hemodynamic analysis of cerebral aneurysm and stenosed carotid bifurcation using computational fluid dynamics technique
LSMS'07: Proceedings of the 2007 international conference on Life System Modeling and SimulationCerebrovascular diseases are one of the three major mortalities in Japan, such as the rupture of cerebral aneurysm and cerebral infarction caused by carotid stenosis. The growth mechanism of the cerebral aneurysm and carotid stenosis has not been ...
Cerebral aneurysm image segmentation based on multi-modal convolutional neural network
Highlights- Cerebral aneurysm and adjacent vessels can be segmented by convolutional neural network efficiently.
AbstractBackground and Objective: Accurate segmentation of cerebral aneurysms in computed tomography angiography (CTA) can provide an essential reference for diagnosis and treatment. This study aimed to evaluate a more helpful image ...
Comments