White Blood Cell Detection and Segmentation Combined with the Channel Space Weighted Feature Pyramid Networks

Lei Geng, Mengmeng Yang, Zhitao Xiao, Fang Zhang, Yanbei Liu, Jun Wu, Wen WangJournal of Computer-Aided Design & Computer Graphics 2021 · DOI

Abstract

The accurate detection and segmentation of leukocytes is a challenging task in medical image processing. White blood cell images obtained under a microscope are easily affected by impurities, morphological variety, and overlapping phenomena, leading to inaccurate edge segmentation. To address these issues, this paper proposes a leukocyte detection method based on Mask R-CNN and an attention-mechanism-driven multi-scale feature fusion. The architecture integrates a Convolutional Block Attention Module (CBAM) into the Feature Pyramid Network (FPN), creating a Channel Spatial Feature Pyramid Network (CSFPN). This structure learns the weights of important channel features and the representation of critical feature regions. Additionally, a Skip-FPN module is incorporated to fuse low-level detailed information through short connections. Experimental results on the Kaggle open-source dataset demonstrate a mAP of 98.25% and a mIoU of 89.3%, showing significant performance improvements over baseline models.

Introduction

Automated white blood cell (WBC) analysis is a cornerstone of modern diagnostics for conditions like leukemia and anemia. However, clinical microscopy presents several challenges for computer vision algorithms:

  1. Impurities: Staining artifacts and debris in blood smears can be mistaken for cellular features.
  2. Morphological Variety: Subtle differences exist between WBC classes (e.g., neutrophils vs. eosinophils).
  3. Adhesion and Overlap: Clumped cells make it difficult to identify precise boundaries.
  4. Blurry Edges: Deep neural networks often lose fine-grained spatial detail, leading to imprecise segmentation.

Methodology: The C-Mask Architecture

The proposed C-Mask model enhances the standard Mask R-CNN framework with two primary architectural innovations: the Channel Spatial Feature Pyramid Network (CSFPN) and the Skip-FPN module.

Channel Spatial Feature Pyramid Network (CSFPN)

The CSFPN integrates the Convolutional Block Attention Module (CBAM) into the feature pyramid. This allows the network to focus on relevant cellular features while suppressing background noise and staining artifacts.

Architecture of the proposed Channel Spatial Feature Pyramid Network (CSFPN) integrating CBAM modules with a ResNet-50 backbone.

The CBAM component applies two distinct types of attention to the feature maps:

  • Channel Attention: Learns "what" features (e.g., specific textures or nuclear shapes) are most indicative of WBCs.
  • Spatial Attention: Learns "where" the most relevant information is located, helping the model ignore debris.
The Convolutional Block Attention Module (CBAM) featuring sequential channel and spatial attention mechanisms.

Skip-FPN

Standard FPNs pass information from bottom to top, which can cause high-resolution details to be "washed out" in deeper layers. The Skip-FPN introduces shortcut connections from early, high-resolution layers (specifically conv2) directly to the upper levels of the pyramid. This preserves the low-level edge information necessary to accurately separate cells that are touching or overlapping.

Experimental Results

The study utilized a subset of 4,000 images from the Kaggle WBC dataset, balanced across four leukocyte types: Eosinophils, Lymphocytes, Monocytes, and Neutrophils. The C-Mask model demonstrated superior performance compared to baseline architectures:

  • Detection Accuracy: Achieved a mAP of 98.25%, a 1.25% improvement over standard Mask R-CNN.
  • Segmentation Quality: Reached a mIoU of 89.30%.
  • Robustness: The False Positive Rate (FPR) dropped to 1.75% (compared to 3.00% for the baseline), proving the effectiveness of the attention mechanism in ignoring debris.

In comparative tests, C-Mask significantly outperformed U-Net (86.8% mAP) and FCN (72.1% mAP). Qualitative results showed that C-Mask was particularly effective at identifying the distinct multi-lobed nuclei of neutrophils and eosinophils, which are often difficult to segment precisely.

Conclusion

By combining attention mechanisms with multi-scale feature fusion, the C-Mask architecture effectively addresses the core difficulties of leukocyte image analysis. Future work will focus on expanding the dataset to include rarer cell types and bone marrow samples, as well as optimizing the model for real-time clinical use.

Summary updated

Abstract

<p indent=0mm>The accurate detection and segmentation of leukocytes is a challenging task in medical image processing. The white blood cell image obtained under microscope is easily affected by impurities. There are many kinds of white cells, different shapes and small differences among them, and also exiting overlapping and adhesion phenomena, which leads to the inaccuracy of cell edge segmentation. The above problems are always the difficulties of detection and segmentation of white cell image. To solve the above problems, a leukocyte detection method based on Mask R-CNN and attention mechanism multi-scale feature fusion is proposed. Based on the Mask R-CNN structure, proposed thesis integrates the attention mechanism module in the FPN (feature pyramid networks) module, and proposes the CSFPN (channel spatial feature pyramid networks) structure. This structure can learn the weight of important channel features and the representation of important feature regions in the feature maps. At the same time, Skip-FPN module is added to the network structure, which fuses more low-level detailed information of leukocytes through short connection, so as to detect and segment leukocytes more accurately. Experimental results show that this method has good detection and segmentation performance. Under the Kaggle open source data set, the mAP value of this method for white blood cell detection reaches 98.25%, which has an increase of 1.25% compared with the previous improvement. The accuracy mIoU value reached 89.3%, which has an increase of 0.002% compared to the before improvement.
BibTeX
@article{geng2021white,
  author = {Lei Geng and Mengmeng Yang and Zhitao Xiao and Fang Zhang and Yanbei Liu and Jun Wu and Wen Wang},
  title = {{White Blood Cell Detection and Segmentation Combined with the Channel Space Weighted Feature Pyramid Networks}},
  journal = {Journal of Computer-Aided Design \& Computer Graphics},
  year = {2021},
  doi = {10.3724/sp.j.1089.2021.18672},
}
Figure