Low dimensional representation of multi-patient flow cytometry datasets using optimal transport for minimal residual disease detection in leukemia

2024-07-24

AI Summary

Minimal residual disease (MRD) detection in acute myeloid leukemia (AML) suffers from low sensitivity, while high-dimensional flow cytometry (FCM) data pose challenges for interpretability and visualization. Method: We propose a novel analytical framework grounded in optimal transport (OT), integrating Wasserstein principal component analysis (WPCA) with mean measure quantification—marking the first application of this combination to enable interpretable, low-dimensional representation and visualization of multi-patient, high-dimensional FCM data. Contribution/Results: Compared to kernel mean embedding and FlowSom, our framework significantly enhances MRD-level discriminability and yields more diagnostically informative 2D projections. Validation on public benchmarks and clinical FCM data from Bordeaux University Hospital demonstrates accurate patient clustering by MRD status, clear 2D separation between remission and relapse groups, and MRD detection sensitivity surpassing the conventional morphological limit of 5%. This establishes a new paradigm for individualized AML prognostic assessment.

Technology Category

• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Web data visualization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Representing and quantifying Minimal Residual Disease (MRD) in Acute Myeloid Leukemia (AML), a type of cancer that affects the blood and bone marrow, is essential in the prognosis and follow-up of AML patients. As traditional cytological analysis cannot detect leukemia cells below 5%, the analysis of flow cytometry dataset is expected to provide more reliable results. In this paper, we explore statistical learning methods based on optimal transport (OT) to achieve a relevant low-dimensional representation of multi-patient flow cytometry measurements (FCM) datasets considered as high-dimensional probability distributions. Using the framework of OT, we justify the use of the K-means algorithm for dimensionality reduction of multiple large-scale point clouds through mean measure quantization by merging all the data into a single point cloud. After this quantization step, the visualization of the intra and inter-patients FCM variability is carried out by embedding low-dimensional quantized probability measures into a linear space using either Wasserstein Principal Component Analysis (PCA) through linearized OT or log-ratio PCA of compositional data. Using a publicly available FCM dataset and a FCM dataset from Bordeaux University Hospital, we demonstrate the benefits of our approach over the popular kernel mean embedding technique for statistical learning from multiple high-dimensional probability distributions. We also highlight the usefulness of our methodology for low-dimensional projection and clustering patient measurements according to their level of MRD in AML from FCM. In particular, our OT-based approach allows a relevant and informative two-dimensional representation of the results of the FlowSom algorithm, a state-of-the-art method for the detection of MRD in AML using multi-patient FCM.

Problem

• Detect Minimal Residual Disease in leukemia.
• Analyze multi-patient flow cytometry datasets.
• Apply optimal transport for dimensionality reduction.

Innovation

• Optimal transport for data representation
• K-means for dimensionality reduction
• Wasserstein PCA for visualization