Journal Article Research Support, Non-U.S. Gov't Ppublish 24 citations
PubMed: 33188571 DOI: 10.1117/1.JBO.25.11.116502
Automatic detection and characterization of quantitative phase images of thalassemic red blood cells using a mask region-based convolutional neural network.
J Biomed Opt 25(11)
Authors: Yang-Hsien Lin, Ken Y-K Liao, Kung-Bin Sung
Affiliations
- National Taiwan University, Graduate Institute of Biomedical Electronics and Bioinformatics, Taipei, Taiwan.
- Feng Chia University, College of Information and Electrical Engineering, Taichung, Taiwan.
- National Taiwan University, Department of Electrical Engineering, Taipei, Taiwan.
- National Taiwan University, Molecular Imaging Center, Taipei, Taiwan.
Abstract
SIGNIFICANCE
Label-free quantitative phase imaging is a promising technique for the automatic detection of abnormal red blood cells (RBCs) in real time. Although deep-learning techniques can accurately detect abnormal RBCs from quantitative phase images efficiently, their applications in diagnostic testing are limited by the lack of transparency. More interpretable results such as morphological and biochemical characteristics of individual RBCs are highly desirable.
AIM
An end-to-end deep-learning model was developed to efficiently discriminate thalassemic RBCs (tRBCs) from healthy RBCs (hRBCs) in quantitative phase images and segment RBCs for single-cell characterization.
APPROACH
Two-dimensional quantitative phase images of hRBCs and tRBCs were acquired using digital holographic microscopy. A mask region-based convolutional neural network (Mask R-CNN) model was trained to discriminate tRBCs and segment individual RBCs. Characterization of tRBCs was achieved utilizing SHapley Additive exPlanation analysis and canonical correlation analysis on automatically segmented RBC phase images.
RESULTS
The implemented model achieved 97.8% accuracy in detecting tRBCs. Phase-shift statistics showed the highest influence on the correct classification of tRBCs. Associations between the phase-shift features and three-dimensional morphological features were revealed.
CONCLUSIONS
The implemented Mask R-CNN model accurately identified tRBCs and segmented RBCs to provide single-RBC characterization, which has the potential to aid clinical decision-making.
MeSH
Cells, Erythrocytes, Blood, Masks, Biomedical Engineering, Thalassemia, Blood Cells, Learning, Biomedical Technology, Quantitative Phase Imaging
Cited by
- Self-supervised pretraining for transferable quantitative phase image cell segmentation. Biomed Opt Express, 2021
- Advancing Laboratory Medicine Practice With Machine Learning: Swift yet Exact. Ann Lab Med, 2024
- Automatic Image Segmentation of Monocytes and Index Computation Using Deep Learning. Proceedings (IEEE Int Conf Bioinformatics Biomed), 2022
- [Chinese expert consensus on the technical and clinical practice specifications of artificial intelligence assisted morphology examination of blood cells (2024)]. Zhonghua Xue Ye Xue Za Zhi, 2024