CASPIANET++: A Multidimensional Channel-Spatial Asymmetric Attention Network with Noisy Student Curriculum Learning Paradigm for Brain Tumor Segmentation

07/08/2021
by   Andrea Liew, et al.
0

Convolutional neural networks (CNNs) have been used quite successfully for semantic segmentation of brain tumors. However, current CNNs and attention mechanisms are stochastic in nature and neglect the morphological indicators used by radiologists to manually annotate regions of interest. In this paper, we introduce a channel and spatial wise asymmetric attention (CASPIAN) by leveraging the inherent structure of tumors to detect regions of saliency. To demonstrate the efficacy of our proposed layer, we integrate this into a well-established convolutional neural network (CNN) architecture to achieve higher Dice scores, with less GPU resources. Also, we investigate the inclusion of auxiliary multiscale and multiplanar attention branches to increase the spatial context crucial in semantic segmentation tasks. The resulting architecture is the new CASPIANET++, which achieves Dice Scores of 91.19 tumor, 87.6 by the scarcity of brain tumor data, we investigate the Noisy Student method for segmentation tasks. Our new Noisy Student Curriculum Learning paradigm, which infuses noise incrementally to increase the complexity of the training images exposed to the network, further boosts the enhancing tumor region to 81.53 Noisy Student Curriculum Learning method works well without any additional training or finetuning.

READ FULL TEXT

page 13

page 14

research
09/09/2017

Sequential 3D U-Nets for Biologically-Informed Brain Tumor Segmentation

Deep learning has quickly become the weapon of choice for brain lesion s...
research
10/06/2017

A Multiscale Patch Based Convolutional Network for Brain Tumor Segmentation

This article presents a multiscale patch based convolutional neural netw...
research
09/17/2018

Multi Modal Convolutional Neural Networks forBrain Tumor Segmentation

In this work, we propose a multi-modal Convolutional Neural Network (CNN...
research
05/22/2022

Residual Channel Attention Network for Brain Glioma Segmentation

A glioma is a malignant brain tumor that seriously affects cognitive fun...
research
06/06/2018

Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI

Convolutional neural networks (CNNs) have been successfully used for bra...
research
07/07/2021

AGD-Autoencoder: Attention Gated Deep Convolutional Autoencoder for Brain Tumor Segmentation

Brain tumor segmentation is a challenging problem in medical image analy...

Please sign up or login with your details

Forgot password? Click here to reset