U-NTCA: nnUNet and nested transformer with channel attention for corneal cell segmentation

Dan Zhang; Jing Zhang; Saiqing Li; Zhixin Dong; Qinxiang Zheng; Jiong Zhang

doi:10.3389/fnins.2024.1363288

U-NTCA: nnUNet and nested transformer with channel attention for corneal cell segmentation

Front Neurosci. 2024 Mar 26:18:1363288. doi: 10.3389/fnins.2024.1363288. eCollection 2024.

Authors

Dan Zhang¹, Jing Zhang², Saiqing Li^{3

4}, Zhixin Dong^{3

4}, Qinxiang Zheng^{3

4

5}, Jiong Zhang^{2

5}

Affiliations

¹ School of Cyber Science and Engineering, Ningbo University of Technology, Ningbo, China.
² Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China.
³ National Clinical Research Center for Ocular Diseases, Wenzhou Medical University, Wenzhou, China.
⁴ The Eye Hospital and School of Ophthalmology and Optometry, Wenzhou Medical University, Wenzhou, China.
⁵ The Ningbo Eye Hospital of Wenzhou Medical University, Ningbo, China.

Abstract

Background: Automatic segmentation of corneal stromal cells can assist ophthalmologists to detect abnormal morphology in confocal microscopy images, thereby assessing the virus infection or conical mutation of corneas, and avoiding irreversible pathological damage. However, the corneal stromal cells often suffer from uneven illumination and disordered vascular occlusion, resulting in inaccurate segmentation.

Methods: In response to these challenges, this study proposes a novel approach: a nnUNet and nested Transformer-based network integrated with dual high-order channel attention, named U-NTCA. Unlike nnUNet, this architecture allows for the recursive transmission of crucial contextual features and direct interaction of features across layers to improve the accuracy of cell recognition in low-quality regions. The proposed methodology involves multiple steps. Firstly, three underlying features with the same channel number are sent into an attention channel named gⁿConv to facilitate higher-order interaction of local context. Secondly, we leverage different layers in U-Net to integrate Transformer nested with gⁿConv, and concatenate multiple Transformers to transmit multi-scale features in a bottom-up manner. We encode the downsampling features, corresponding upsampling features, and low-level feature information transmitted from lower layers to model potential correlations between features of varying sizes and resolutions. These multi-scale features play a pivotal role in refining the position information and morphological details of the current layer through recursive transmission.

Results: Experimental results on a clinical dataset including 136 images show that the proposed method achieves competitive performance with a Dice score of 82.72% and an AUC (Area Under Curve) of 90.92%, which are higher than the performance of nnUNet.

Conclusion: The experimental results indicate that our model provides a cost-effective and high-precision segmentation solution for corneal stromal cells, particularly in challenging image scenarios.

Keywords: cell segmentation; cornea; multi-scale; nested transformer; nnUNet.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work was supported in part by the Zhejiang Provincial Natural Science Foundation (LQ23F010002 and LZ23F010002), in part by the Ningbo Natural Science Foundation (2022J143), and the Scientific Research Program of Zhejiang Provincial Department of Education (Y202250360), in part by the Research Startup Fund of Ningbo University of Technology (2022KQ29).