期刊
IEEE ACCESS
卷 10, 期 -, 页码 48747-48760出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3171916
关键词
Image segmentation; Computer architecture; Feature extraction; Morphology; Blood; Support vector machines; Computational efficiency; Deep learning; computer-assisted diagnosis; leukemia diagnosis; WBC count; WBC segmentation
资金
- Basic Science Research Program through the National Research Foundation of Korea (NRF) - Ministry of Science and Information Communication Technology (MSICT) [NRF-2017R1E1A1A01077717]
- Korea Institute for Advanced Study (KIAS) [CG076601]
- NRF - MSICT through the Development Research Program [NRF2022R1G1A101022611]
- National Research Foundation of Korea [CG076601] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
In this study, a multi-scale information fusion network (MIF-Net) is proposed for white blood cell (WBC) segmentation, which effectively aids in the diagnosis and prognosis of leukemia. The network utilizes internal and external spatial information fusion mechanisms to preserve boundary information and improve segmentation performance. The proposed architecture achieves state-of-the-art segmentation performance on publicly available datasets while maintaining superior computational efficiency.
Leukemia is one of the most terminal types of blood cancer, and many people suffer from it every year. White blood cells (WBCs) have a significant association with leukemia diagnosis. Research studies reported that leukemia brings changes in WBC count and morphology. WBC accurate segmentation enables to detect morphology and WBC count which consequently helps in the diagnosis and prognosis of leukemia. Manual WBC assessment methods are tedious, subjective, and less accurate. To overcome these problems, we propose a multi-scale information fusion network (MIF-Net) for WBC segmentation. MIF-Net is a shallow architecture with internal and external spatial information fusion mechanisms. In WBC images, the cytoplasm is with low contrast compared to the background, whereas nuclei shape can be complex with an indistinctive boundary for some cases, therefore accurate segmentation becomes challenging. Spatial features in the initial layers of the network include fine boundary information and MIF-Net splits and propagates this boundary information on multi-scale for external information fusion. Multi-scale information fusion in our network helps in preserving boundary information and contributes to segmentation performance improvement. MIF-Net also uses internal information fusion after intervals for feature empowerment in different stages of the network. We evaluated our network for four publicly available datasets and achieved state-of-the-art segmentation performance. In addition, the proposed architecture exhibits superior computational efficiency by using only 2.67 million trainable parameters.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据