Development and Validation of an Unsupervised Feature Learning System for Leukocyte Characterization and Classification: A Multi-Hospital Study
Title | Development and Validation of an Unsupervised Feature Learning System for Leukocyte Characterization and Classification: A Multi-Hospital Study |
Publication Type | Journal Article |
Year of Publication | 2021 |
Authors | Yan H, Mao X, Yang X, Xia Y, Wang C, Wang J, Xia R, Xu X, Wang Z, Li Z, Zhao X, Li Y, Liu G, He L, Wang Z, Wang Z, Li Z, Cai W, Shen H, Chang H |
Volume | 129 |
Issue | 6 |
Pagination | 1837 - 1856 |
Date Published | 2021/06/01 |
ISBN Number | 1573-1405 |
Abstract | The characterization and classification of white blood cells (WBC) are critical for the diagnosis of anemia, leukemia, and many other hematologic diseases. We developed WBC-Profiler, an unsupervised feature learning system for quantitative analysis of leukocytes. We demonstrate, through independent validation, that WBC-Profiler enables automatic extraction of complex and robust signatures from microscopic images without human-intervention and, thereafter, effective construction of interpretable leukocyte profiles, which decouples large scale complex leukocyte characterization from limitations in both human-based feature engineering/optimization and the end-to-end solutions provided by many modern deep neural networks. Further evaluation in a real-world clinical setting confirms that, compared with 23 clinicians from 8 hospitals (class-average-sensitivity, 0.798; class-average-specificity, 0.963; cell-average-timecost: 3.158 s), WBC-Profiler performs with significantly improved accuracy and speed (class-average-sensitivity, 0.890; class-average-specificity, 0.980; cell-average-timecost: 0.375 s). Our findings suggest that WBC-Profiler has the potential clinical implications. |
URL | https://doi.org/10.1007/s11263-021-01449-9 |
Short Title | International Journal of Computer Vision |