Analyzing Images of Blood Cells with Quantum Machine Learning Methods: Equilibrium Propagation and Variational Quantum Circuits to Detect Acute Myeloid Leukemia

TL;DR

This study demonstrates that quantum machine learning methods can effectively classify blood cell images for leukemia detection, achieving performance close to classical models even with limited data and quantum constraints.

Contribution

It introduces the application of Equilibrium Propagation and Variational Quantum Circuits for medical image classification, showing their competitive performance under resource constraints.

Findings

Quantum methods achieve 12-15% lower accuracy than classical CNNs.

VQC maintains 83% accuracy with only 50 samples per class.

EP reaches 86.4% accuracy, close to CNN performance.

Abstract

This paper presents a feasibility study demonstrating that quantum machine learning (QML) algorithms achieve competitive performance on real-world medical imaging despite operating under severe constraints. We evaluate Equilibrium Propagation (EP), an energy-based learning method that does not use backpropagation (incompatible with quantum systems due to state-collapsing measurements) and Variational Quantum Circuits (VQCs) for automated detection of Acute Myeloid Leukemia (AML) from blood cell microscopy images using binary classification (2 classes: AML vs. Healthy). Key Result: Using limited subsets (50-250 samples per class) of the AML-Cytomorphology dataset (18,365 expert-annotated images), quantum methods achieve performance only 12-15% below classical CNNs despite reduced image resolution (64x64 pixels), engineered features (20D), and classical simulation via Qiskit. EP reaches 86.4% accuracy (only 12% below CNN) without backpropagation, while the 4-qubit VQC attains 83.0% accuracy with consistent data efficiency: VQC maintains stable 83% performance with only 50 samples per class, whereas CNN requires 250 samples (5x more data) to reach 98%. These results establish reproducible baselines for QML in healthcare, validating NISQ-era feasibility.