English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In standard hospital blood tests, the traditional process requires doctors tomanually isolate leukocytes from microscopic images of patients' blood usingmicroscopes. These isolated leukocytes are then categorized via automaticleukocyte classifiers to determine the proportion and volume of different typesof leukocytes present in the blood samples, aiding disease diagnosis. Thismethodology is not only time-consuming and labor-intensive, but it also has ahigh propensity for errors due to factors such as image quality andenvironmental conditions, which could potentially lead to incorrect subsequentclassifications and misdiagnosis. To address these issues, this paper proposesan innovative method of leukocyte detection: the Multi-level Feature Fusion andDeformable Self-attention DETR (MFDS-DETR). To tackle the issue of leukocytescale disparity, we designed the High-level Screening-feature Fusion Pyramid(HS-FPN), enabling multi-level fusion. This model uses high-level features asweights to filter low-level feature information via a channel attention moduleand then merges the screened information with the high-level features, thusenhancing the model's feature expression capability. Further, we address theissue of leukocyte feature scarcity by incorporating a multi-scale deformableself-attention module in the encoder and using the self-attention andcross-deformable attention mechanisms in the decoder, which aids in theextraction of the global features of the leukocyte feature maps. Theeffectiveness, superiority, and generalizability of the proposed MFDS-DETRmethod are confirmed through comparisons with other cutting-edge leukocytedetection models using the private WBCDD, public LISC and BCCD datasets. Oursource code and private WBCCD dataset are available athttps://github.com/JustlfC03/MFDS-DETR.

Accurate Leukocyte Detection Based on Deformable-DETR and Multi-Level Feature Fusion for Aiding Diagnosis of Blood Diseases