红外与激光工程
2023, 52(8): 20230265
Author Affiliations
Abstract
1 Fudan University, Academy for Engineering and Technology, Shanghai, P. R. China
2 Tianjin Center for Medical Device Evaluation and Inspection, Tianjin, P. R. China
3 Shanghai University, School of Communication & Information Engineering, Shanghai, P. R. China
4 Fudan University, Center for Biomedical Engineering, Shanghai, P. R. China
5 Fudan University, State Key Laboratory of Medical Neurobiology, Institutes of Brain Science, Shanghai, P. R. China
Automatic cell counting provides an effective tool for medical research and diagnosis. Currently, cell counting can be completed by transmitted-light microscope, however, it requires expert knowledge and the counting accuracy which is unsatisfied for overlapped cells. Further, the image-translation-based detection method has been proposed and the potential has been shown to accomplish cell counting from transmitted-light microscope, automatically and effectively. In this work, a new deep-learning (DL)-based two-stage detection method (cGAN-YOLO) is designed to further enhance the performance of cell counting, which is achieved by combining a DL-based fluorescent image translation model and a DL-based cell detection model. The various results show that cGAN-YOLO can effectively detect and count some different types of cells from the acquired transmitted-light microscope images. Compared with the previously reported YOLO-based one-stage detection method, high recognition accuracy (RA) is achieved by the cGAN-YOLO method, with an improvement of 29.80%. Furthermore, we can also observe that cGAN-YOLO obtains an improvement of 12.11% in RA compared with the previously reported image-translation-based detection method. In a word, cGAN-YOLO makes it possible to implement cell counting directly from the experimental acquired transmitted-light microscopy images with high flexibility and performance, which extends the applicability in clinical research.
Automatic cell counting transmitted-light microscope deep-learning fluorescent image translation Journal of Innovative Optical Health Sciences
2023, 16(5): 2350004
1 湖南省畜牧兽医研究所, 湖南 长沙 410131
2 湖南农业大学动物科学技术学院, 湖南 长沙 410125
3 新晃贡溪夜郎贡鸡养殖专业合作社, 湖南 新晃 419200
精子密度仪在哺乳动物中已推广应用, 但在家禽中还研究很少。本文以黑凤鸡和攸县麻鸭精液为实验材料, 手持精子密度仪与血细胞计数板为检测工具, 对影响精子密度测定方法准确率因素进行分析, 建立鸡、鸭精子密度-吸光度函数并进行验证。结果表明: 用密度仪测定时的稀释液(简称“测试液”)为3%NaCl时, 精液稀释后应尽快检测吸光度; 样液在比色皿中的混匀方式对吸光度测定有很大影响; 精液用3%NaCl以及3种常用家禽精液稀释液进行10倍稀释后测定吸光度, B液吸光度显著高于与其它3组(P<0.05), 其它3组间差异不显著(P>0.05)。用测试液为3.0%NaCl, 鸡和鸭精子密度-吸光度呈三次函数关系, 回归方程分别是Y1=1.374X3-0.786X2+0.945X-0.002(R2=0.997)、Y2=1.283X3-0.899X2+0.994X-0.009(R2=0.996); 用0.9%NaCl代替3%NaCl作测试液简化精子密度测定方法可行, 鸡精子密度-吸光度回归方程为Y3=-0.264X3+1.23X2+0.468X+0.019 (R2=0.999)。鸡精液测试液为0.9%NaCl、3%NaCl时两种函数的吸光度最佳范围分别是0.035~0.692、0.069~0.624, 在此范围内计数板与方程两种方法得到的密度差异不显著(P>0.05), 以计数法为真实值, 两种方法平均相对误差分别为6.95%、3.11%。以3%NaCl为测试液, 鸭精液函数所测样品吸光度最佳范围小于鸡精液的, 以计数板法为真实值, 在吸光度0.054~0.123范围内的, 函数与计数板两种方法所得的精子密度的平均相对误差为4.61%。本文将促进家禽手持精子密度仪研发, 以及更好的使用哺乳动物精子密度仪。
鸡 鸭 精子密度 密度仪 细胞计数 roosters drakes sperm density density meter cell counting
Author Affiliations
Abstract
1 Med-X Research Institute and School of Biomedical Engineering, Shanghai Jiao Tong University, 1954 Huashan Road, Shanghai 200030, P. R. China
2 School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Shanghai 200240, P. R. China
In biomedical research fields, the in vivo flow cytometry (IVFC) is a widely used technology which is able to monitor target cells dynamically in living animals. Although the setup of IVFC system has been well established, baseline drift is still a challenge in the process of quantifying circulating cells. Previous methods, i.e., the dynamic peak picking method, counted cells by setting a static threshold without considering the baseline drift, leading to an inaccurate cell quantification. Here, we developed a method of cell counting for IVFC data with baseline drift by interpolation fitting, automatic segmentation and wavelet-based denoising. We demonstrated its performance for IVFC signals with three types of representative baseline drift. Compared with non-baseline-correction methods, this method showed a higher sensitivity and specificity, as well as a better result in the Pearson's correlation coe±cient and the mean-squared error (MSE).
In vivo flow cytometry cell counting baseline drift signal processing Journal of Innovative Optical Health Sciences
2017, 10(3): 1750008
Author Affiliations
Abstract
Department of Optical Electronics, Sichuan University Chengdu, Sichuan 610064, P. R. China
Blood cell counting is an important medical test to help medical staffs diagnose various symptoms and diseases. An automatic segmentation of complex overlapping erythrocytes based on seed prediction in microscopic imaging is proposed. The four main innovations of this research are as follows: (1) Regions of erythrocytes extracted rapidly and accurately based on the G component. (2) K-means algorithm is applied on edge detection of overlapping erythrocytes. (3) Traces of erythrocytes' biconcave shape are utilized to predict erythrocyte's position in overlapping clusters. (4) A new automatic counting method which aims at complex overlapping erythrocytes is presented. The experimental results show that the proposed method is efficient and accurate with very little running time. The average accuracy of the proposed method reaches 97.0%.
Image segmentation erythrocyte cell counting k-means seed prediction Journal of Innovative Optical Health Sciences
2016, 9(5): 1650016
Author Affiliations
Abstract
Department of Optical Electronics Sichuan University, Chengdu Sichuan 610064, P. R. China
Red blood cell (RBC) counting is a standard medical test that can help diagnose various conditions and diseases. Manual counting of blood cells is highly tedious and time consuming. However, new methods for counting blood cells are customary employing both electronic and computer-assisted techniques. Image segmentation is a classical task in most image processing applications which can be used to count blood cells in a microscopic image. In this research work, an approach for erythrocytes counting is proposed. We employed a classification before counting and a new segmentation idea was implemented on the complex overlapping clusters in a microscopic smear image. Experimental results show that the proposed method is of higher counting accuracy and it performs much better than most counting algorithms existed in the situation of three or more RBCs overlapping complexly into a group. The average total erythrocytes counting accuracy of the proposed method reaches 92.9%.
Cell counting image processing image segmentation overlap erythrocyte cell classi fication K-means Journal of Innovative Optical Health Sciences
2015, 8(6): 1550033
1 长春理工大学 生命科学技术学院, 长春 130022
2 吉林农业大学 工程技术学院, 长春 130118
针对细胞工厂监控系统长工作距和大倾斜角的观测需求, 设计了一种结构简单、成像清晰的光学显微成像系统.由于获得的细胞图像光照和色彩不均、样本浑浊、细胞重叠、边界粘连较多、细胞间距不明显, 采用单尺度Retinex算法进行图像预处理, 并结合Otsu阈值分割法与K均值聚类法进行细胞图像分割处理, 最后应用改进的快速连通区域标记以及高准确度细胞计数方法进行细胞个数统计.仿真实验和实际测试结果表明: 该系统成像分辨率和清晰度均达到工程需求, 能够较清晰地辨识出培养皿中细胞的形态和分布情况.细胞显微图像处理方法取得了良好的图像增强效果, 弱化了由光照不均和样本浑浊造成的人眼视觉无法清晰分辨细胞的现象, 消除了由于图像分割不到位造成统计误差, 细胞计数准确度达到95%以上.该方法适合多种类型细胞监测与计数处理, 可满足细胞工厂实时准确监控的要求.
细胞工厂 光电监测 显微成像 细胞图像增强 细胞图像分割 细胞计数 计数准确度 Cell factories Optical monitoring Microscopic imaging Cell image enhancement Cell image segmentation Cell counting Counting accuracy
1 西南大学 工程技术学院,重庆 400715
2 重庆大学 新型微纳器件与系统技术国家重点学科实验室,重庆 400030
构建了用于微流控细胞分析芯片的发光二极管(LED)诱导透射式荧光检测微系统,以克服现有荧光检测系统体积大、能耗高,以及激发光光路、检测区域和荧光收集光路间光学耦合效率低等问题。该系统的激发光光路和荧光收集光路互成135°,LED发出的激发光经透镜聚焦和激发光滤色片滤光后,经直径为200 μm的小孔光阑限束,然后投射到微流控芯片通道末端的检测区域;产生的荧光及杂散光经加工后置于微流控芯片底部的发射光高通干涉滤色薄膜后,被光电倍增管收集。以HepG2肝癌细胞为测试样本对该荧光检测微系统的有效性进行了评测,结果显示:当LED工作电流为200 mA,PMT控制电压为3.5 V时,可产生与背景噪声明显区分的峰值信号;用250 s观测时间得到了8个平均峰高为0.7 V的峰值信号,与荧光显微镜观察结果一致,实现了细胞的在线计数检测功能。提出的系统为新型微全细胞分析提供了一种新的技术途径。
荧光检测 发光二极管(LED) 透射式光路 微流控芯片 细胞计数检测 fluorescence detection Light Emitting Diode(LED) transmitted optical path microfluidic chip cell counting detection