Unstained Blood Smear Analysis: A Review of Rule‐Based, Machine Learning, and Deep Learning Techniques

Анализ неокрашенных мазков крови: обзор методов на основе правил, машинного обучения и глубокого обучения
Thomas Wilhelm Bocklitz, Husnu Baris Baydargil
2025-06-30

blood cell classificationblood cell segmentationdeep learninglabel-free imagingunstained blood smear analysis
ABSTRACT Blood cells are central to oxygen transport, immune defense, and hemostasis. Their number and morphology act as sensitive biomarkers, making accurate segmentation and classification essential for hematological diagnostics. Biophotonic techniques now provide label‐free imaging of unstained smears by exploiting intrinsic phase and scattering contrast, yet such images exhibit low optical signal and subtle morphological variation that exacerbate segmentation errors. Label‐free modalities nevertheless preserve contrast where dyes fail, motivating renewed interest in unstained workflows. This review analyzes rule‐based, machine‐learning, and deep‐learning approaches for segmenting and classifying label‐free blood cells, highlighting performance gains, persistent challenges, and future directions for clinical adoption.
1
Accurate blood-cell segmentation and classification are essential because cell counts and morphology provide sensitive biomarkers for hematological diagnostics.
2
Biophotonic imaging enables label-free analysis of unstained blood smears using intrinsic phase and scattering contrast.
3
Label-free modalities can preserve diagnostically relevant contrast where staining fails, but persistent challenges remain for clinical adoption.
4
The review compares rule-based, machine-learning, and deep-learning methods for segmenting and classifying label-free blood cells.
5
Unstained images often have low optical signal and subtle morphological variation, which increase segmentation errors.

label-free images of unstained blood smears and their blood cells

segmentation and classification of blood cells based on intrinsic phase and scattering contrast, including performance, challenges, and clinical adoption

Publication Details
Publication Date
2025-06-30
Journal
Publisher
ISSN
Cited by
7
Access Type
Author Information
Authors
Thomas Wilhelm Bocklitz
Husnu Baris Baydargil
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%