Real-time deep learning phase imaging flow cytometer reveals blood cell aggregate biomarkers for haematology diagnostics

2025-08-11

AI Summary

Rare cellular aggregates in hematology are challenging to identify label-free; conventional flow cytometry cannot detect them, and quantitative phase imaging flow cytometry remains clinically impractical due to data bottlenecks. Method: This work proposes RT-HAD, an end-to-end framework integrating physics-constrained off-axis digital holographic reconstruction with graph representation learning to process high-speed holographic image streams exceeding 30 GB online. Contribution/Results: RT-HAD enables the first real-time extraction of latent biological biomarkers from aggregates and their automatic clustering identification. Full processing completes in under 1.5 minutes, achieving a platelet aggregate detection error rate of only 8.9%—within clinically acceptable limits. The system overcomes key technical barriers in label-free, high-throughput, real-time functional blood diagnostics, delivering a deployable deep learning–enabled phase-imaging flow cytometry platform for point-of-care hematology analysis.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

While analysing rare blood cell aggregates remains challenging in automated haematology, they could markedly advance label-free functional diagnostics. Conventional flow cytometers efficiently perform cell counting with leukocyte differentials but fail to identify aggregates with flagged results, requiring manual reviews. Quantitative phase imaging flow cytometry captures detailed aggregate morphologies, but clinical use is hampered by massive data storage and offline processing. Incorporating hidden biomarkers into routine haematology panels would significantly improve diagnostics without flagged results. We present RT-HAD, an end-to-end deep learning-based image and data processing framework for off-axis digital holographic microscopy (DHM), which combines physics-consistent holographic reconstruction and detection, representing each blood cell in a graph to recognize aggregates. RT-HAD processes >30 GB of image data on-the-fly with turnaround time of <1.5 min and error rate of 8.9% in platelet aggregate detection, which matches acceptable laboratory error rates of haematology biomarkers and solves the big data challenge for point-of-care diagnostics.

Problem

• Detect blood cell aggregates for haematology diagnostics
• Overcome data storage and processing limitations in phase imaging
• Enable real-time analysis of large image datasets

Innovation

• Deep learning-based real-time holographic reconstruction
• Graph representation for blood cell aggregates
• On-the-fly processing of large image data