Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Parallel matters : Efficient polyp segmentation with parallel structured feature augmentation modules

Guo, Qingqing ; Fang, Xianyong ; Wang, Kaibing ; Shi, Yuqing ; Wang, Linbo ; Zhang, Enming LU and Liu, Zhengyi (2023) In IET Image Processing 17(8). p.2503-2515
Abstract

The large variations of polyp sizes and shapes and the close resemblances of polyps to their surroundings call for features with long-range information in rich scales and strong discrimination. This article proposes two parallel structured modules for building those features. One is the Transformer Inception module (TI) which applies Transformers with different reception fields in parallel to input features and thus enriches them with more long-range information in more scales. The other is the Local-Detail Augmentation module (LDA) which applies the spatial and channel attentions in parallel to each block and thus locally augments the features from two complementary dimensions for more object details. Integrating TI and LDA, a new... (More)

The large variations of polyp sizes and shapes and the close resemblances of polyps to their surroundings call for features with long-range information in rich scales and strong discrimination. This article proposes two parallel structured modules for building those features. One is the Transformer Inception module (TI) which applies Transformers with different reception fields in parallel to input features and thus enriches them with more long-range information in more scales. The other is the Local-Detail Augmentation module (LDA) which applies the spatial and channel attentions in parallel to each block and thus locally augments the features from two complementary dimensions for more object details. Integrating TI and LDA, a new Transformer encoder based framework, Parallel-Enhanced Network (PENet), is proposed, where LDA is specifically adopted twice in a coarse-to-fine way for accurate prediction. PENet is efficient in segmenting polyps with different sizes and shapes without the interference from the background tissues. Experimental comparisons with state-of-the-arts methods show its merits.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
biomedical imaging, computer vision, image segmentation
in
IET Image Processing
volume
17
issue
8
pages
13 pages
publisher
John Wiley & Sons Inc.
external identifiers
  • scopus:85153480316
ISSN
1751-9659
DOI
10.1049/ipr2.12813
language
English
LU publication?
yes
id
50b46a7c-3478-471d-8efe-6573ea0109b2
date added to LUP
2023-07-14 13:53:31
date last changed
2023-11-08 07:39:53
@article{50b46a7c-3478-471d-8efe-6573ea0109b2,
  abstract     = {{<p>The large variations of polyp sizes and shapes and the close resemblances of polyps to their surroundings call for features with long-range information in rich scales and strong discrimination. This article proposes two parallel structured modules for building those features. One is the Transformer Inception module (TI) which applies Transformers with different reception fields in parallel to input features and thus enriches them with more long-range information in more scales. The other is the Local-Detail Augmentation module (LDA) which applies the spatial and channel attentions in parallel to each block and thus locally augments the features from two complementary dimensions for more object details. Integrating TI and LDA, a new Transformer encoder based framework, Parallel-Enhanced Network (PENet), is proposed, where LDA is specifically adopted twice in a coarse-to-fine way for accurate prediction. PENet is efficient in segmenting polyps with different sizes and shapes without the interference from the background tissues. Experimental comparisons with state-of-the-arts methods show its merits.</p>}},
  author       = {{Guo, Qingqing and Fang, Xianyong and Wang, Kaibing and Shi, Yuqing and Wang, Linbo and Zhang, Enming and Liu, Zhengyi}},
  issn         = {{1751-9659}},
  keywords     = {{biomedical imaging; computer vision; image segmentation}},
  language     = {{eng}},
  number       = {{8}},
  pages        = {{2503--2515}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{IET Image Processing}},
  title        = {{Parallel matters : Efficient polyp segmentation with parallel structured feature augmentation modules}},
  url          = {{http://dx.doi.org/10.1049/ipr2.12813}},
  doi          = {{10.1049/ipr2.12813}},
  volume       = {{17}},
  year         = {{2023}},
}