FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation

Chaitanya Kaul; Suresh Kumar Manandhar; Nicholas Edwin Pears

FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation

Chaitanya Kaul, Suresh Kumar Manandhar, Nicholas Edwin Pears

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose a novel technique to incorporate attention within convolutional neural networks using feature maps generated by a separate convolutional autoencoder. Our attention architecture is well suited for incorporation with deep convolutional networks. We evaluate our model on benchmark segmentation datasets in skin cancer segmentation and lung lesion segmentation. Results show highly competitive performance when compared with U-Net and it’s residual variant.

Original language	English
Title of host publication	International Symposium on Biomedical Imaging (ISBI)
Place of Publication	Venice
Publication status	Published - Apr 2019

Keywords

Semantic segmentation, attention in CNNs, medical imaging, U-Net, residual connections

Access to Document

https://arxiv.org/pdf/1902.03091.pdf

Cite this

@inproceedings{9ae26959cafd4fb4938ef5467ca113f5,

title = "FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation",

abstract = "We propose a novel technique to incorporate attention within convolutional neural networks using feature maps generated by a separate convolutional autoencoder. Our attention architecture is well suited for incorporation with deep convolutional networks. We evaluate our model on benchmark segmentation datasets in skin cancer segmentation and lung lesion segmentation. Results show highly competitive performance when compared with U-Net and it{\textquoteright}s residual variant.",

keywords = "Semantic segmentation, attention in CNNs, medical imaging, U-Net, residual connections",

author = "Chaitanya Kaul and Manandhar, {Suresh Kumar} and Pears, {Nicholas Edwin}",

year = "2019",

month = apr,

language = "English",

booktitle = "International Symposium on Biomedical Imaging (ISBI)",

}

TY - GEN

T1 - FocusNet: An attention-based Fully Convolutional Network for Medical Image Segmentation

AU - Kaul, Chaitanya

AU - Manandhar, Suresh Kumar

AU - Pears, Nicholas Edwin

PY - 2019/4

Y1 - 2019/4

N2 - We propose a novel technique to incorporate attention within convolutional neural networks using feature maps generated by a separate convolutional autoencoder. Our attention architecture is well suited for incorporation with deep convolutional networks. We evaluate our model on benchmark segmentation datasets in skin cancer segmentation and lung lesion segmentation. Results show highly competitive performance when compared with U-Net and it’s residual variant.

AB - We propose a novel technique to incorporate attention within convolutional neural networks using feature maps generated by a separate convolutional autoencoder. Our attention architecture is well suited for incorporation with deep convolutional networks. We evaluate our model on benchmark segmentation datasets in skin cancer segmentation and lung lesion segmentation. Results show highly competitive performance when compared with U-Net and it’s residual variant.

KW - Semantic segmentation, attention in CNNs, medical imaging, U-Net, residual connections

M3 - Conference contribution

BT - International Symposium on Biomedical Imaging (ISBI)

CY - Venice

ER -