https://scholars.lib.ntu.edu.tw/handle/123456789/581533
標題: | Automatic detection and characterization of quantitative phase images of thalassemic red blood cells using a mask region-based convolutional neural network | 作者: | Lin Y.-H Liao K.Y.-K KUNG-BIN SUNG |
關鍵字: | Blood; Cells; Convolution; Decision making; Deep learning; Image segmentation; Learning systems; Microscopic examination; Automatic Detection; Biochemical characteristics; Canonical correlation analysis; Clinical decision making; Digital holographic microscopy; Learning techniques; Morphological features; Quantitative phase imaging; Convolutional neural networks | 公開日期: | 2020 | 卷: | 25 | 期: | 11 | 來源出版物: | Journal of Biomedical Optics | 摘要: | 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. ? The Authors. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096153439&doi=10.1117%2f1.JBO.25.11.116502&partnerID=40&md5=d2c83077cae59adb10c8d0f615b9483d https://scholars.lib.ntu.edu.tw/handle/123456789/581533 |
ISSN: | 10833668 | DOI: | 10.1117/1.JBO.25.11.116502 |
顯示於: | 生醫電子與資訊學研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。