Paper Info
Title
Carisi: Convolutional Autoencoder-Based Inter-Slice Interpolation Of Brain Tumor Volumetric Images
Abstract
The paper is motivated by the fact that brain cancer is one of the deadliest cancers and its detection in early stages is of paramount importance. In this regard, tumor 3D shape reconstruction from magnetic resonance (MR) or computed tomography (CT) scans provides critical information, which can not be interpreted from 2D images. However, CT and MR images have low resolution in z direction compared to their resolution in x and y directions, therefore, 3D reconstructed shapes are of low quality. In this paper, we propose to use convolutional auto-encoders (CAEs) to address this drawback, and develop a convolutional autoencoder-based inter-slice interpolation (CARISI) framework. Although deep nets have been used very recently for brain tumor segmentation, to the best of our knowledge, this is the first attempt to use CAEs for 3D reconstruction of brain tumor. The proposed CARISI framework consists of several encoding and decoding components, which can handle rapid changes in tumor shape without the need for supervision of an expert. Our experiments based on a real data-set consisting of 3064 segmented brain tumor images indicate that the proposed CARISI framework outperforms its counterpart and has the potential to significantly improve the overall quality of the reconstructed shapes.
Year
Venue
Keywords
2018
2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Brain tumor, volumetric images, 3D reconstruction, Interpolation, Convolutional auto-encoder
Field
DocType
ISSN
Iterative reconstruction,Computer vision,Autoencoder,Pattern recognition,Convolution,Computer science,Interpolation,Brain tumor,Artificial intelligence,Decoding methods,3D reconstruction,Encoding (memory)
Conference
1522-4880
Citations 
PageRank 
References 
1
0.34
0
Authors
4
Name
Order
Citations
PageRank
Parnian Afshar1487.42
Atefeh Shahroudnejad240.85
Arash Mohammadi322946.79
Kostas N. Plataniotis4347.69