AUTHOR=Luo Yang , Wang Yingwei , Zhao Yongda , Guan Wei , Shi Hanfeng , Fu Chong , Jiang Hongyang 

TITLE=A lightweight network based on dual-stream feature fusion and dual-domain attention for white blood cells segmentation

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1223353

DOI=10.3389/fonc.2023.1223353

ISSN=2234-943X

ABSTRACT=Accurate white blood cells segmentation from cytopathological images is crucial for evaluating leukemia. In this paper, a novel instance segmentation network called YOLACT-CIS for cytopathological images is presented. The proposed method improves the feature representation capability of the network while reducing parameters and computational redundancy by utilizing the feature reuse of Ghost module to reconstruct a lightweight backbone network. Additionally, a dual-stream feature fusion network (DFFN) based on the feature pyramid network is designed to enhance detailed information acquisition. Furthermore, a dual-domain attention module (DDAM) is developed to extract global features from both frequency and spatial domains simultaneously, resulting in better cell segmentation performance. Experimental results on ALL-IDB and BCCD datasets demonstrate that our method outperforms existing instance segmentation networks such as Mask R-CNN, PointRend, MS R-CNN, SOLOv2, and YOLACT with an average precision (AP) of 87.41%, while significantly reducing parameters and computational cost.