White Blood Cell Detection Based on FBDM-YOLOv8s

White blood cells, also known as immune cells, help the body resist infectious diseases and foreign pathogens as part of the immune system. This article proposes a white blood cell detection method based on an improved YOLOv8s to enhance the accurate detection of different categories of normal white...

Full description

Saved in:
Bibliographic Details
Main Authors: Borui Sun, Xiangsuo Fan, Jie Meng, Jinfeng Wang, Huajin Chen, Lei Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10934993/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736254480973824
author Borui Sun
Xiangsuo Fan
Jie Meng
Jinfeng Wang
Huajin Chen
Lei Liu
author_facet Borui Sun
Xiangsuo Fan
Jie Meng
Jinfeng Wang
Huajin Chen
Lei Liu
author_sort Borui Sun
collection DOAJ
description White blood cells, also known as immune cells, help the body resist infectious diseases and foreign pathogens as part of the immune system. This article proposes a white blood cell detection method based on an improved YOLOv8s to enhance the accurate detection of different categories of normal white blood cells. In the YOLOv8s network, this study replaces the main framework of YOLOv8 with the Fasternet module to reduce computational redundancy and memory access. Subsequently, a BiLevel Routing Attention mechanism is proposed to achieve precise localization of white blood cells. Additionally, to attain diversified feature extraction, this article introduces the DBBNCSPELAN4 module, which can perform diversified feature extraction in a multi-branch manner while lightweighting the model, reducing the number of parameters, and speeding up computation. Finally, the MultiSEAM module is integrated with Detect to address detection errors caused by occlusion and connected white blood cells. Experiments were conducted on a dataset of five types of normal cells provided by DML-LZWH (Liuzhou Workers&#x2019; Hospital Medical Laboratory). The FBDM-YOLOv8s significantly outperforms other advanced object detection algorithms in terms of performance, with a 2.1% increase in mAP compared to the baseline YOLOv8s.We will release the source code on <uri>https://github.com/SSRR-LLL/FBDM-YOLOv8.git</uri>.
format Article
id doaj-art-a88432bf93a74474beca21d6eb07d16a
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a88432bf93a74474beca21d6eb07d16a2025-08-20T03:07:20ZengIEEEIEEE Access2169-35362025-01-0113569185692910.1109/ACCESS.2025.355313910934993White Blood Cell Detection Based on FBDM-YOLOv8sBorui Sun0https://orcid.org/0009-0004-6788-7846Xiangsuo Fan1https://orcid.org/0000-0002-1685-4989Jie Meng2Jinfeng Wang3Huajin Chen4https://orcid.org/0000-0002-8783-3691Lei Liu5School of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaMedical Science Laboratory, Liuzhou Worker&#x2019;s Hospital, Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Electronic Engineering, Guangxi University of Science and Technology, Liuzhou, ChinaSichuan Provincial Corps Hospital, Chinese People&#x2019;s Armed Police Force, Leshan, Sichuan, ChinaWhite blood cells, also known as immune cells, help the body resist infectious diseases and foreign pathogens as part of the immune system. This article proposes a white blood cell detection method based on an improved YOLOv8s to enhance the accurate detection of different categories of normal white blood cells. In the YOLOv8s network, this study replaces the main framework of YOLOv8 with the Fasternet module to reduce computational redundancy and memory access. Subsequently, a BiLevel Routing Attention mechanism is proposed to achieve precise localization of white blood cells. Additionally, to attain diversified feature extraction, this article introduces the DBBNCSPELAN4 module, which can perform diversified feature extraction in a multi-branch manner while lightweighting the model, reducing the number of parameters, and speeding up computation. Finally, the MultiSEAM module is integrated with Detect to address detection errors caused by occlusion and connected white blood cells. Experiments were conducted on a dataset of five types of normal cells provided by DML-LZWH (Liuzhou Workers&#x2019; Hospital Medical Laboratory). The FBDM-YOLOv8s significantly outperforms other advanced object detection algorithms in terms of performance, with a 2.1% increase in mAP compared to the baseline YOLOv8s.We will release the source code on <uri>https://github.com/SSRR-LLL/FBDM-YOLOv8.git</uri>.https://ieeexplore.ieee.org/document/10934993/BiLevelRoutingAttentionDBBNCSPELAN4FBDM-YOLOv8sFasterNetleukocyte target detectionMultiSEAM
spellingShingle Borui Sun
Xiangsuo Fan
Jie Meng
Jinfeng Wang
Huajin Chen
Lei Liu
White Blood Cell Detection Based on FBDM-YOLOv8s
IEEE Access
BiLevelRoutingAttention
DBBNCSPELAN4
FBDM-YOLOv8s
FasterNet
leukocyte target detection
MultiSEAM
title White Blood Cell Detection Based on FBDM-YOLOv8s
title_full White Blood Cell Detection Based on FBDM-YOLOv8s
title_fullStr White Blood Cell Detection Based on FBDM-YOLOv8s
title_full_unstemmed White Blood Cell Detection Based on FBDM-YOLOv8s
title_short White Blood Cell Detection Based on FBDM-YOLOv8s
title_sort white blood cell detection based on fbdm yolov8s
topic BiLevelRoutingAttention
DBBNCSPELAN4
FBDM-YOLOv8s
FasterNet
leukocyte target detection
MultiSEAM
url https://ieeexplore.ieee.org/document/10934993/
work_keys_str_mv AT boruisun whitebloodcelldetectionbasedonfbdmyolov8s
AT xiangsuofan whitebloodcelldetectionbasedonfbdmyolov8s
AT jiemeng whitebloodcelldetectionbasedonfbdmyolov8s
AT jinfengwang whitebloodcelldetectionbasedonfbdmyolov8s
AT huajinchen whitebloodcelldetectionbasedonfbdmyolov8s
AT leiliu whitebloodcelldetectionbasedonfbdmyolov8s