Cervical cell nuclei segmentation based on GC-UNet

Enguang Zhang; Rixin Xie; Yuxin Bian; Jiayan Wang; Pengyi Tao; Heng Zhang; Shenlu Jiang

doi:10.1016/j.heliyon.2023.e17647

Cervical cell nuclei segmentation based on GC-UNet

Heliyon. 2023 Jun 28;9(7):e17647. doi: 10.1016/j.heliyon.2023.e17647. eCollection 2023 Jul.

Authors

Enguang Zhang^{1

2}, Rixin Xie¹, Yuxin Bian¹, Jiayan Wang¹, Pengyi Tao¹, Heng Zhang³, Shenlu Jiang¹

Affiliations

¹ School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China.
² Zhuhai College of Science and Technology, Zhuhai, China.
³ Faculty of Education, The University of Hong Kong, Pokfulam Road, Hong Kong, China.

Abstract

Cervical cancer diagnosis hinges significantly on precise nuclei segmentation at early stages, which however, remains largely elusive due to challenges such as overlapping cells and blurred nuclei boundaries. This paper presents a novel deep neural network (DNN), the Global Context UNet (GC-UNet), designed to adeptly handle intricate environments and deliver accurate cell segmentation. At the core of GC-UNet is DenseNet, which serves as the backbone, encoding cell images and capitalizing on pre-existing knowledge. A unique context-aware pooling module, equipped with a gating model, is integrated for effective encoding of ImageNet pre-trained features, ensuring essential features at different levels are retained. Further, a decoder grounded in a global context attention block is employed to foster global feature interaction and refine the predicted masks.

Keywords: Cell nuclei segmentation; Semantic segmentation.