Interpretable morphology mapping of peripheral blood leukocytes using annotation-efficient artificial intelligence
Journal:
bioRxiv
Published Date:
May 26, 2026
Abstract
Background Peripheral blood smears (PBS) review is labor-intensive, subjective, and challenging for rare or morphologically heterogeneous cell types in hematologic malignancies. Artificial intelligence (AI) offers a scalable alternative, but broader clinical translation is constrained by annotation burden and limited interpretability. Methods We developed an interpretable, annotation-efficient AI framework that learns leukocyte morphology through a two-stage process: label-free representation learning to construct a morphological embedding space, followed by supervised fine-tuning for cell type and morphological attribute classification. The model was trained and evaluated on 5,952 PBS images from cancer patients at MD Anderson Cancer Center, including blast cells, and 17,092 images from public sources. Active learning strategies were assessed to improve label efficiency, and interpretability was examined using saliency and embedding visualization. An interactive web application, HemoSight, was developed to support clinical review. Findings The framework achieved a macro-F1 score of 0.96 for 9-way leukocyte classification on the internal test split and 0.83 on the held-out patient cohort. Active learning substantially reduced annotation requirements, reaching peak performance with only 13.3% of available labels and significantly improving learning efficiency across 8 of 9 cell types. The model generalized to classifying 11 leukocyte morphological attributes with a mean F1; score of 85.8% and revealed structured morphological landscapes. Saliency maps, embedding visualizations, and the HemoSight application enabled transparent morphological inspection of model predictions, supporting confidence in model behavior and feasibility for clinical integration. Interpretation Our framework enables scalable, annotation-efficient, and interpretable modeling of leukocyte morphology, supporting the integration of AI-assisted PBS review for hematopathology workflows.
