Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2024 Aug;37(4):1529-1547.
doi: 10.1007/s10278-024-00981-7. Epub 2024 Mar 4.

From CNN to Transformer: A Review of Medical Image Segmentation Models

Wenjian Yao  1 , Jiajun Bai  1 , Wei Liao  2 , Yuheng Chen  1 , Mengjuan Liu  3 , Yao Xie  4   5
Affiliations
Review

From CNN to Transformer: A Review of Medical Image Segmentation Models

Wenjian Yao et al. J Imaging Inform Med. 2024 Aug.

Abstract

Medical image segmentation is an important step in medical image analysis, especially as a crucial prerequisite for efficient disease diagnosis and treatment. The use of deep learning for image segmentation has become a prevalent trend. The widely adopted approach currently is U-Net and its variants. Moreover, with the remarkable success of pre-trained models in natural language processing tasks, transformer-based models like TransUNet have achieved desirable performance on multiple medical image segmentation datasets. Recently, the Segment Anything Model (SAM) and its variants have also been attempted for medical image segmentation. In this paper, we conduct a survey of the most representative seven medical image segmentation models in recent years. We theoretically analyze the characteristics of these models and quantitatively evaluate their performance on Tuberculosis Chest X-rays, Ovarian Tumors, and Liver Segmentation datasets. Finally, we discuss the main challenges and future trends in medical image segmentation. Our work can assist researchers in the related field to quickly establish medical segmentation models tailored to specific regions.

Keywords: CNN; Deep learning; Medical image segmentation; Transformer; U-Net.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Structure of FCN-8 s [20]
Fig. 2
Fig. 2
Structure of U-Net [6]
Fig. 3
Fig. 3
Structure of UNet++ [17]
Fig. 4
Fig. 4
Structure of TransUNet [9]
Fig. 5
Fig. 5
Structure of Swin-Unet [10]
Fig. 6
Fig. 6
Examples of Tuberculosis Chest X-rays (Shenzhen)dataset
Fig. 7
Fig. 7
Examples of Clinical Liver CT dataset
Fig. 8
Fig. 8
Examples of Ovarian Tumors dataset
Fig. 9
Fig. 9
Tuberculosis Chest X-rays (Shenzhen)dataset segmentation results
Fig. 10
Fig. 10
Tuberculosis Chest X-rays (Shenzhen)dataset segmentation coloring results
Fig. 11
Fig. 11
Ovarian Tumors dataset segmentation results
Fig. 12
Fig. 12
Clinical Liver dataset segmentation results
Fig. 13
Fig. 13
Ovarian Tumors dataset segmentation coloring results
Fig. 14
Fig. 14
Clinical Liver dataset segmentation coloring results
See this image and copyright information in PMC

References

    1. Cheng, J.Z., Ni, D., Chou, Y.H., Qin, J., Tiu, C.M., Chang, Y.C., Huang, C.S., Shen, D., Chen, C.M.: Computer-aided diagnosis with deep learning architecture: Applications to breast lesions in US images and pulmonary nodules in CT scans. Scientific Reports 6, 24454 (2016) - PMC - PubMed
    1. Golan, R., Jacob, C., Denzinger, J.: Lung nodule detection in ct images using deep convolutional neural networks. In: International Joint Conference on Neural Networks (2016)
    1. Christ, P.F., Ettlinger, F., Grün, F., Elshaera, M.E.A., Lipkova, J., Schlecht, S., Ahmaddy, F., Tatavarty, S., Bickel, M., Bilic, P.: Automatic liver and tumor segmentation of CT and MRI volumes using cascaded fully convolutional neural networks (2017)
    1. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics 9(1), 62–66 (1979)
    1. Magnier, Baptiste: Edge detection: a review of dissimilarity evaluations and a proposed normalized measure. Multimedia Tools & Applications (2017)

LinkOut - more resources