MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation

Accurate polyp image segmentation is of great significance, because it can help in the detection of polyps. Convolutional neural network (CNN) is a common automatic segmentation method, but its main disadvantage is the long training time. Transformer is another method that can be adapted to the auto...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen Peng, Zhiqin Qian, Kunyu Wang, Lanzhu Zhang, Qi Luo, Zhuming Bi, Wenjun Zhang
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7473
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060213223161856
author Chen Peng
Zhiqin Qian
Kunyu Wang
Lanzhu Zhang
Qi Luo
Zhuming Bi
Wenjun Zhang
author_facet Chen Peng
Zhiqin Qian
Kunyu Wang
Lanzhu Zhang
Qi Luo
Zhuming Bi
Wenjun Zhang
author_sort Chen Peng
collection DOAJ
description Accurate polyp image segmentation is of great significance, because it can help in the detection of polyps. Convolutional neural network (CNN) is a common automatic segmentation method, but its main disadvantage is the long training time. Transformer is another method that can be adapted to the automatic segmentation method by employing a self-attention mechanism, which essentially assigns different importance weights to each piece of information, thus achieving high computational efficiency during segmentation. However, a potential drawback with Transformer is the risk of information loss. The study reported in this paper employed the well-known hybridization principle to propose a method to combine CNN and Transformer to retain the strengths of both. Specifically, this study applied this method to the early detection of colonic polyps and to implement a model called MugenNet for colonic polyp image segmentation. We conducted a comprehensive experiment to compare MugenNet with other CNN models on five publicly available datasets. An ablation experiment on MugenNet was conducted as well. The experimental results showed that MugenNet can achieve a mean Dice of 0.714 on the ETIS dataset, which is the optimal performance on this dataset compared to other models, with an inference speed of 56 FPS. The overall outcome of this study is a method to optimally combine two methods of machine learning which are complementary to each other.
format Article
id doaj-art-5823d87f16d742a6a8982d5b3b3e7f08
institution DOAJ
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-5823d87f16d742a6a8982d5b3b3e7f082025-08-20T02:50:40ZengMDPI AGSensors1424-82202024-11-012423747310.3390/s24237473MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image SegmentationChen Peng0Zhiqin Qian1Kunyu Wang2Lanzhu Zhang3Qi Luo4Zhuming Bi5Wenjun Zhang6School of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, ChinaSchool of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, ChinaSchool of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, ChinaSchool of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, ChinaSchool of Mechanical and Power Engineering, East China University of Science and Technology, Shanghai 200237, ChinaDepartment of Engineering, Purdue University, West Lafayette, IN 47907, USADepartment of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK S7N 5A9, CanadaAccurate polyp image segmentation is of great significance, because it can help in the detection of polyps. Convolutional neural network (CNN) is a common automatic segmentation method, but its main disadvantage is the long training time. Transformer is another method that can be adapted to the automatic segmentation method by employing a self-attention mechanism, which essentially assigns different importance weights to each piece of information, thus achieving high computational efficiency during segmentation. However, a potential drawback with Transformer is the risk of information loss. The study reported in this paper employed the well-known hybridization principle to propose a method to combine CNN and Transformer to retain the strengths of both. Specifically, this study applied this method to the early detection of colonic polyps and to implement a model called MugenNet for colonic polyp image segmentation. We conducted a comprehensive experiment to compare MugenNet with other CNN models on five publicly available datasets. An ablation experiment on MugenNet was conducted as well. The experimental results showed that MugenNet can achieve a mean Dice of 0.714 on the ETIS dataset, which is the optimal performance on this dataset compared to other models, with an inference speed of 56 FPS. The overall outcome of this study is a method to optimally combine two methods of machine learning which are complementary to each other.https://www.mdpi.com/1424-8220/24/23/7473transformerconvolutional neural networkpolyp detectionimage segmentation
spellingShingle Chen Peng
Zhiqin Qian
Kunyu Wang
Lanzhu Zhang
Qi Luo
Zhuming Bi
Wenjun Zhang
MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation
Sensors
transformer
convolutional neural network
polyp detection
image segmentation
title MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation
title_full MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation
title_fullStr MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation
title_full_unstemmed MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation
title_short MugenNet: A Novel Combined Convolution Neural Network and Transformer Network with Application in Colonic Polyp Image Segmentation
title_sort mugennet a novel combined convolution neural network and transformer network with application in colonic polyp image segmentation
topic transformer
convolutional neural network
polyp detection
image segmentation
url https://www.mdpi.com/1424-8220/24/23/7473
work_keys_str_mv AT chenpeng mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation
AT zhiqinqian mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation
AT kunyuwang mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation
AT lanzhuzhang mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation
AT qiluo mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation
AT zhumingbi mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation
AT wenjunzhang mugennetanovelcombinedconvolutionneuralnetworkandtransformernetworkwithapplicationincolonicpolypimagesegmentation