Paper Info
Title
Exploiting Uncertainty Of Deep Neural Networks For Improving Segmentation Accuracy In Mri Images
Abstract
Deep neural networks have shown great achievements in solving complex problems. However, there are fundamental challenges which limit their real world applications. Lack of a measurable criterion for estimating uncertainty of the network predictions is one of these challenges. However, we can compute the variance of the network output by applying spatial transformations, distortions or noise injection to network inputs and interpret these variances as uncertainty of the network predictions. In other words, as long as the deformations do not conceptually alter target of interest, we expect the network to produce the same result. Hence, any outputs changes can be a sign of uncertainty in the network predictions. In order to estimate the prediction uncertainty of deep convolutional neural networks we use simple random transformations. By exploiting the network uncertainty, we improve the overall performance of the system. For a real use case, we apply the proposed method to segment left ventricle in MRI cardiac images. Experimental results demonstrate state-of- the-art performance and highlight the potential capabilities of simple ideas in conjunction with deep neural networks.
Year
DOI
Venue
2019
10.1109/icassp.2019.8682530
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
adaptive thresholding, conditional random fields, deep convolutional networks, segmentation
Simple random sample,Pattern recognition,Computer science,Convolutional neural network,Measure (mathematics),Medical imaging,Segmentation,Image segmentation,Artificial intelligence,Artificial neural network,Deep neural networks
Conference
ISSN
Citations 
PageRank 
1520-6149
1
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Alireza Norouzi1122.85
Ali Emami288.05
Kayvan Najarian326259.53
Nader Karimi414532.75
Shadrokh Samavi523338.99
S. M. R. Soroushmehr67121.08