Elsevier

Pattern Recognition

Volume 132, December 2022, 108963
Pattern Recognition

GFNet: Automatic segmentation of COVID-19 lung infection regions using CT images based on boundary features

https://doi.org/10.1016/j.patcog.2022.108963Get rights and content

Highlights

  • A novel deep learning network framework, GFNet, was proposed for the segmentation of infected region of COVID-19 in two-dimensional CT images of lungs. By aggregating the high-layer features using the aggregation module, the aggregated features can capture context information and generate a global location map as an initial boot region for subsequent steps. In order to further dig the boundary information of the target, we use the reverse attention module step by step from the high-layer to the low-layer, then further extract the hidden details of each layer, and finally fuse the features of each layer, so that the network can fully extract the details that are difficult to be noticed by the previous model.

  • We design a Edge-guidance map that contains the boundary features of each layer to further extract the boundary information when the features of each layer are extracted. The experiment proves that this design is very effective.

  • We applied the GFNet framework to VGG16 and used our method on two different datasets. One data set was “seen” to verify learning ability, and the other was “not seen” to verify generalization ability. Experimental results show that GFNet has better learning ability and generalization ability than existing models.

  • We conducted experiments with each model on training datasets of different sizes. Our model can achieve good performance when the training set is relatively small. In real world case decision making, our GFNet is fully capable of such tasks if it is put into application under time constraints or with few training samples. Our GFNet can also be sufficiently trained to achieve maximum performance if there is sufficient time or a large training sample.

Abstract

In early 2020, the global spread of the COVID-19 has presented the world with a serious health crisis. Due to the large number of infected patients, automatic segmentation of lung infections using computed tomography (CT) images has great potential to enhance traditional medical strategies. However, the segmentation of infected regions in CT slices still faces many challenges. Specially, the most core problem is the high variability of infection characteristics and the low contrast between the infected and the normal regions. This problem leads to fuzzy regions in lung CT segmentation. To address this problem, we have designed a novel global feature network(GFNet) for COVID-19 lung infections: VGG16 as backbone, we design a Edge-guidance module(Eg) that fuses the features of each layer. First, features are extracted by reverse attention module and Eg is combined with it. This series of steps enables each layer to fully extract boundary details that are difficult to be noticed by previous models, thus solving the fuzzy problem of infected regions. The multi-layer output features are fused into the final output to finally achieve automatic and accurate segmentation of infected areas. We compared the traditional medical segmentation networks, UNet, UNet++, the latest model Inf-Net, and methods of few shot learning field. Experiments show that our model is superior to the above models in Dice, Sensitivity, Specificity and other evaluation metrics, and our segmentation results are clear and accurate from the visual effect, which proves the effectiveness of GFNet. In addition, we verify the generalization ability of GFNet on another “never seen” dataset, and the results prove that our model still has better generalization ability than the above model. Our code has been shared at https://github.com/zengzhenhuan/GFNet.

Keywords

Image segmentation
COVID-19
Edge-guidance
Convolutional neural network
CT image

Data availability

Cited by (0)

Chaodong Fan received his master...s degree and doctor’s degree from Hunan University in 2011 and 2014 respectively. Mainly engaged in intelligent computing, pattern recognition and intelligent systems, smart grid related fields. Some new intelligent optimization algorithms and image processing technologies, such as molecular dynamics optimization algorithm, spatial section projection histogram and postprocessing strategy based on threshold,are proposed. His research interests include artificial intelligence, image processing and model recognition.

Zhenhuan Zeng was born in 1995 in Changsha, Hunan Province, China. He is studying in Xiangtan University for his master...s degree. His main research interests are evolutionary algorithms, and computer vision.

Leyi Xiao was born in 1986 in Changde, Hunan, China. She graduated from Hunan University with a doctorate in engineering in 2020. Her research interest include image processing and model recognition, which relate to both the field of computer vision and pattern recognition.

Qu Xilong was born in January 1978, graduated from Southwest Jiaotong University with a doctor’s degree in 2006. His research interests include manufacturing informatization, distributed system integration technology, information security technology.

This work is supported by Hunan Provincial Natural Science Foundation of China (No. 2020JJ4587), Guangdong Basic and Applied Basic Research Foundation (No. 2019A1515110423), Degree & Postgraduate Education Reform Project of Hunan Province (No. 2019JGYB115), Scientific Research Project of Hunan Provincial Department of Education (No. 21C0922), Open Fund Project of Fujian Provincial Key Laboratory of Data Intensive Computing (No. BD202004), Open Research Fund of AnHui Key Laboratory of Detection Technology and Energy Saving Devices (No. JCKJ2021B05), Open Fund Project of Vehicle Measurement, Control and Safety Key Laboratory of Sichuan Province (No. QCCK2021-006).

View Abstract