DCCTNet: Kidney tumors segmentation based on dual-level combination of CNN and transformer

Hou, Bingzhen, Zhang, Guimei, Liu, Huiqun, Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126 and Chen, Ying 2024. DCCTNet: Kidney tumors segmentation based on dual-level combination of CNN and transformer. Presented at: IEEE International Conference on Image Processing (ICIP 2024), Abu Dhabi, United Arab Emirates, 27-30 October 2024. Proceedings of International Conference on Image Processing. IEEE, pp. 3112-3116. 10.1109/ICIP51287.2024.10647912

Preview

PDF - Accepted Post-Print Version Download (830kB) | Preview

Abstract

The hybrid model of CNN(Convolution Neural Networks) and Transformer is a popular method in segmenting kidney images, but most existing hybrid models directly fused local features from CNN with global features from Transformer, ignoring the issue of semantic gaps between distinct features. Furthermore, feature fusion is typically performed solely at the feature level, without considering alignment at the mask (prediction map) level. To address these limitations, we propose a novel segmentation method called Dual-level Combination of CNN and Transformers Network (DCCTNet). Specifically, we select similar features from both CNN and Transformer to reduce semantic gaps at the feature level. Additionally, we further utilize the global information of the Transformers by reducing the difference between the prediction maps in the coding stage at the mask level. We evaluate DCCTNet on the KiTS19 dataset, achieving 97.3% dice score for kidneys segmentation and 81.2% dice score for kidney tumors segmentation, respectively. https://github.com/hou-bz/DCCTNet.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	IEEE
ISBN:	9798350349405
ISSN:	1522-4880
Date of First Compliant Deposit:	7 October 2024
Date of Acceptance:	6 June 2024
Last Modified:	07 Oct 2024 10:30
URI:	https://orca.cardiff.ac.uk/id/eprint/172540

Actions (repository staff only)

Edit Item