LESION SEGMENTATION IN MAMMOGRAPHIC IMAGES USING THE SEGFORMER NETWORK ARCHITECTURE
DOI:
https://doi.org/10.24867/24BE33KljajicKeywords:
Segformer, segmentation, lesion, mammography imagesAbstract
Changes in breast tissue can indicate early stages of malignant diseases, in addition an early diagnosis is one of the key factors in increasing the success of the treatment. Therefore, it is necessary to find algorithms that will efficiently and precisely detect the presence of lesions. Due to their simplicity and efficiency, the application of transformers in image segmentation has gained a lot attention in recent years. In this paper, the Segformer network architecture was used for lesion segmentation in mammography images. The obtained results demonstrate significant potential for the application of this architecture in real-world settings.
References
[1] E. Xie, W. Wang et al., “SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers,” arXiv (Cornell University), Dec. 2021, doi: https://doi.org/10.48550/arxiv.2105.15203
[2] K. H. Zhang0_0, “An Overview of Segformer and Details Description,” GitHub, Apr. 15, 2023. https://github.com/ACSEkevin/An-Overview-of-Segformer-and-Details-Description (accessed Apr. 26, 2023).
[3] W. Wang et al., “Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions,” IEEE Xplore, Oct. 01, 2021. https://ieeexplore.ieee.org/document/9711179
[4] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, et al. “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv, 2020.
[5] I. C. Moreira, I. Amaral, I. Domingues et al. “INbreast: toward a full-field digital mammographic database,” Academic Radiology. 2012 Feb;19(2):236-48. doi: 10.1016/j.acra.2011.09.014. Epub 2011 Nov 10. PMID: 22078258.
[2] K. H. Zhang0_0, “An Overview of Segformer and Details Description,” GitHub, Apr. 15, 2023. https://github.com/ACSEkevin/An-Overview-of-Segformer-and-Details-Description (accessed Apr. 26, 2023).
[3] W. Wang et al., “Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions,” IEEE Xplore, Oct. 01, 2021. https://ieeexplore.ieee.org/document/9711179
[4] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, et al. “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv, 2020.
[5] I. C. Moreira, I. Amaral, I. Domingues et al. “INbreast: toward a full-field digital mammographic database,” Academic Radiology. 2012 Feb;19(2):236-48. doi: 10.1016/j.acra.2011.09.014. Epub 2011 Nov 10. PMID: 22078258.
Downloads
Published
2023-09-08
Issue
Section
Electrotechnical and Computer Engineering
