Microscopic examination of peripheral blood plays an important role in the field of diagnosis and control of major diseases. Peripheral leukocyte recognition by manual requires medical technicians to observe blood smears through light microscopy, using their experience and expertise to discriminate and analyze different cells, which is time-consuming, labor-intensive and subjective. The traditional systems based on feature engineering often need to ensure successful segmentation and then manually extract certain quantitative and qualitative features for recognition but still remaining a limitation of poor robustness. The classification pipeline based on convolutional neural network is of automatic feature extraction and free of segmentation but hard to deal with multiple object recognition. In this paper, we take leukocyte recognition as object detection task and apply two remarkable object detection approaches, Single Shot Multibox Detector and An Incremental Improvement Version of You Only Look Once . To improve recognition performance, some key factors involving these object detection approaches are explored and the detection models are generated using the train set of 14,700 annotated images. Finally, we evaluate these detection models on test sets consisting of 1,120 annotated images and 7,868 labeled single object images corresponding to 11 categories of peripheral leukocytes, respectively. A best mean average precision of 93.10% and mean accuracy of 90.09% are achieved while the inference time is 53 ms per image on a NVIDIA GTX1080Ti GPU.
Cell image segmentation plays a central role in numerous biology studies and clinical applications. As a result, the development of cell image segmentation algorithms with high robustness and accuracy is attracting more and more attention. In this study, an automated cell image segmentation algorithm is developed to get improved cell image segmentation with respect to cell boundary detection and segmentation of the clustered cells for all cells in the field of view in negative phase contrast images. A new method which combines the thresholding method and edge based active contour method was proposed to optimize cell boundary detection. In order to segment clustered cells, the geographic peaks of cell light intensity were utilized to detect numbers and locations of the clustered cells. In this paper, the working principles of the algorithms are described. The influence of parameters in cell boundary detection and the selection of the threshold value on the final segmentation results are investigated. At last, the proposed algorithm is applied to the negative phase contrast images from different experiments. The performance of the proposed method is evaluated. Results show that the proposed method can achieve optimized cell boundary detection and highly accurate segmentation for clustered cells.
Purpose The paper aims to develop a cownose ray-inspired robotic fish which can be propelled by oscillating and chordwise twisting pectoral fins. Design/methodology/approach The bionic pectoral fin which can simultaneously realize the combination of oscillating motion and chordwise twisting motion is designed based on analyzing the movement of cownose ray’s pectoral fins. The structural design and control system construction of the robotic fish are presented. Finally, a series of swimming experiments are carried out to verify the effectiveness of the design for the bionic pectoral fin. Findings The experimental results show that the deformation of the bionic pectoral fin can be well close to that of the cownose ray’s. The bionic pectoral fin can produce effective angle of attack, and the thrust generated can propel robotic fish effectively. Furthermore, the tests of swimming performance in the water tank show that the robotic fish can achieve a maximum forward speed of 0.43 m/s (0.94 times of body length per second) and an excellent turning maneuverability with a small radius. Originality/value The oscillating and pitching motion can be obtained simultaneously by the active control of chordwise twisting motion of the bionic pectoral fin, which can better imitate the movement of cownose ray’s pectoral fin. The designed bionic pectoral fin can provide an experimental platform for further study of the effect of the spanwise and chordwise flexibility on propulsion performance.
Interfacial nanobubbles (NBs) and nanodroplets (NDs) have been attracting increasing attention due to their potential for numerous applications. As a result, the automated segmentation and morphological characterization of NBs and NDs in atomic force microscope (AFM) images is highly awaited. The current segmentation methods suffer from the uneven background in AFM images due to thermal drift and hysteresis of AFM scanners. In this study, a two-step approach was proposed to segment NBs and NDs in AFM images in an automated manner. The spherical Hough transform (SHT) and a boundary optimization operation were combined to achieve robust segmentation. The SHT was first used to preliminarily detect NBs and NDs. After that, the so-called contour expansion operation was applied to achieve optimized boundaries. The principle and the detailed procedure of the proposed method were presented, followed by the demonstration of the automated segmentation and morphological characterization. The result shows that the proposed method gives an improved segmentation result compared with the thresholding and circle Hough transform method. Moreover, the proposed method shows strong robustness of segmentation in AFM images with an uneven background.
As a Chinese medicine complex prescription, Qiming Granule may alleviate retinal hypoxia and ischemia by increasing retinal blood flow and improving the blood circulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.