Related Experiment Video
Updated: Jul 15, 2026
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
Published on: November 19, 2018
Self-explaining artificial intelligence for the classification of B cell non-Hodgkin lymphoma: A diagnostic decision
Michael C Thrun1,2, Jörg Hoffmann3, Stefan W Krause4
1Mathematics and Computer Science, Philipps University Marburg, Marburg, Germany.
Insights
FlowXAI, an AI system, aids B cell non-Hodgkin lymphoma (B-NHL) diagnosis using flow cytometry data. It offers trustworthy, data-efficient, and transparent classification, even with limited data.
Area of Science:
- Computational biology
- Medical diagnostics
- Artificial intelligence in healthcare
Background:
- Multiparameter flow cytometry is crucial for B cell non-Hodgkin lymphoma (B-NHL) diagnosis.
- Interpretation challenges include high-dimensional data, variable sample quality, and evolving classifications.
- Current AI methods often need large datasets and lack diagnostic transparency.
Purpose of the Study:
- To develop FlowXAI, a self-explaining AI system for B-NHL classification.
- To enhance diagnostic trustworthiness and reduce AI training data requirements.
- To provide transparent and data-efficient support for B-NHL immunophenotyping.
Main Methods:
- Developed FlowXAI, integrating unsupervised structural analysis (Tile Mining) with a multi-level diagnostic framework.
- Used Tile Mining for pre-diagnostic sample-quality assessment and training data filtering.
- Evaluated FlowXAI via cross-validation on 19,493 samples and an external benchmark dataset.
Main Results:
- FlowXAI achieved performance comparable to deep learning models with significantly less training data.
- Confident predictions from FlowXAI surpassed the neural network baseline performance.
- Unsupervised analysis showed clear separation for some lymphoma entities but not others, depending on antibody panels.
Conclusions:
- FlowXAI offers accurate, data-efficient, and transparent B-NHL immunophenotyping support from flow cytometry data.
- The system provides a clinically meaningful framework for diagnostic support and training, especially for rare subtypes or limited expertise.
- Prospective validation within integrated workflows is recommended for FlowXAI as a decision-support tool.
Background:
Multiparameter flow cytometry is a cornerstone of B cell non-Hodgkin lymphoma (B-NHL) diagnostics, but interpretation requires substantial expertise and is complicated by high-dimensional data, variable sample quality, limited data for rare entities, and evolving clinical classification systems. Current artificial intelligence approaches often require large training datasets and provide limited insight into the rationale behind individual diagnostic decisions.
Methods And Findings:
We developed FlowXAI, a self-explaining artificial intelligence system designed to support B-NHL classification while explicitly reporting case-level diagnostic trustworthiness. FlowXAI combines unsupervised structural analysis with a clinically motivated, multi-level diagnostic framework reflecting routine diagnostic priorities. An unsupervised Tile Mining (TM) procedure performs pre-diagnostic sample-quality assessment by identifying structurally atypical samples. TM is applied to filter training data, enabling substantial reduction of training requirements while preserving unbiased evaluation on independent test samples. FlowXAI was evaluated using repeated cross-validation on 19,493 peripheral blood samples and further assessed on an independent external benchmark dataset generated at a separate diagnostic center using a different antibody panel. Across diagnostic levels, FlowXAI achieved performance comparable to a deep learning-based system despite requiring approximately two orders of magnitude fewer training samples. When predictions were classified as confident by the system's internal self-assessment, diagnostic performance exceeded that of the neural network baseline. Unsupervised structural analysis demonstrated clear separation between normal controls and selected lymphoma entities such as chronic lymphocytic leukemia-like lymphomas and hairy cell leukemia, while other entities were not clearly separable using the antibody panels studied.
Conclusions:
FlowXAI provides accurate, data-efficient, and transparent support for B-NHL immunophenotyping from nonstandardized flow cytometry data. By combining interpretable decision logic with explicit self-assessment, FlowXAI offers a clinically meaningful framework for diagnostic support and training, particularly in settings with limited expert availability or rare lymphoma subtypes. The main limitation is the retrospective evaluation using specific antibody panels, and FlowXAI requires prospective validation as a decision-support tool within integrated diagnostic workflows.
