A new level set model for cell image segmentation

In this paper we first determine three phases of cell images： background, cytoplasm and nucleolus according to the general physical characteristics of cell images, and then develop a variational model, based on these characteristics, to segment nucleolus and cytoplasm from their relatively complicated backgrounds. In the meantime, the preprocessing obtained information of cell images using the OTSU algorithm is used to initialize the level set function in the model, which can speed up the segmentation and present satisfactory results in cell image processing.

Color Cell Image Segmentation Based on Chan-Vese Model for Vector-Valued Images

In this paper, we propose a color cell image segmentation method based on the modified Chan-Vese model for vectorvalued images. In this method, both the cell nuclei and cytoplasm can be served simultaneously from the color cervical cell image. Color image could be regarded as vector-valued images because there are three channels, red, green and blue in color image. In the proposed color cell image segmentation method, to segment the cell nuclei and cytoplasm precisely in color cell image, we should use the coarse-fine segmentation which combined the auto dual-threshold method to separate the single cell connection region from the original image, and the modified C-V model for vectorvalued images which use two independent level set functions to separate the cell nuclei and cytoplasm from the cell body. From the result we can see that by using the proposed method we can get the nuclei and cytoplasm region more accurately than traditional model.

Automatic Leukaemia Segmentation Approach for Blood Cancer Classification Using Microscopic Images

Leukaemia is a type of blood cancer that is caused by undeveloped White Blood Cells(WBC),and it is also called a blast blood cell.In the marrow of human bones,leukaemia is developed and is responsible for blood cell generation with leukocytes and WBC,and if any cell gets blasted,then it may become a cause of death.Therefore,the diagnosis of leukaemia in its early stages helps greatly in the treatment along with saving human lives.Subsequently,in terms of detection,image segmentation techniques play a vital role,and they turn out to be the important image processing steps for the extraction of feature patterns from the Acute Lymphoblastic Leukaemia(ALL)type of blood cancer.Moreover,the image segmentation technique focuses on the division of cells by segmenting a microscopic image into background and cancer blood cell nucleus,which is well-known as the Region Of Interest(ROI).As a result,in this article,we attempt to build a segmentation technique capable of solving blood cell nucleus segmentation issues using four distinct scenarios,including K-means,FCM(Fuzzy Cmeans),K-means with FFA(Firefly Algorithm),and FCM with FFA.Also,we determine the most effective method of blood cell nucleus segmentation,which we subsequently use for the Leukaemia classification model.Finally,using the Convolution Neural Network(CNN)as a classifier,we developed a leukaemia cancer classification model from the microscopic images.The proposed system’s classification accuracy is tested using the CNN to test the model on the ALL-IDB dataset and equate it to the current state of the art.In terms of experimental analysis,we observed that the accuracy of the model is near to 99%,and it is far better than other existing models that are designed to segment and classify the types of leukaemia cancer in terms of ALL.

Generalized <i>α</i>-Entropy Based Medical Image Segmentation

In 1953, Rènyi introduced his pioneering work (known as α-entropies) to generalize the traditional notion of entropy. The functionalities of α-entropies share the major properties of Shannon’s entropy. Moreover, these entropies can be easily estimated using a kernel estimate. This makes their use by many researchers in computer vision community greatly appealing. In this paper, an efficient and fast entropic method for noisy cell image segmentation is presented. The method utilizes generalized α-entropy to measure the maximum structural information of image and to locate the optimal threshold desired by segmentation. To speed up the proposed method, computations are carried out on 1D histograms of image. Experimental results show that the proposed method is efficient and much more tolerant to noise than other state-of-the-art segmentation techniques.

Cell Segmentation and Tracking in Microfluidic Platform

In this research, we have concentrated on trajectory extraction based on image segmentation and data association in order to provide an economic and complete solution for rapid microfluidic cell migration experiments. We applied region scalable active contour model to segment the individual cells and then employed the ellipse fitting technique to process touching cells. Subsequently, we have also introduced a topology based technique to associate the cells between consecutive frames. This scheme achieves satisfactory segmentation and tracking results on the datasets acquired by our microfluidic platform.

Illumination-Free Clustering Using Improved Slime Mould Algorithm for Acute Lymphoblastic Leukemia Image Segmentation

Partitional clustering techniques such as K-Means(KM),Fuzzy C-Means(FCM),and Rough K-Means(RKM)are very simple and effective techniques for image segmentation.But,because their initial cluster centers are randomly determined,it is often seen that certain clusters converge to local optima.In addition to that,pathology image segmentation is also problematic due to uneven lighting,stain,and camera settings during the microscopic image capturing process.Therefore,this study proposes an Improved Slime Mould Algorithm(ISMA)based on opposition based learning and differential evolution’s mutation strategy to perform illumination-free White Blood Cell(WBC)segmentation.The ISMA helps to overcome the local optima trapping problem of the partitional clustering techniques to some extent.This paper also performs a depth analysis by considering only color components of many well-known color spaces for clustering to find the effect of illumination over color pathology image clustering.Numerical and visual results encourage the utilization of illumination-free or color component-based clustering approaches for image segmentation.ISMA-KM and“ab”color channels of CIELab color space provide best results with above-99%accuracy for only nucleus segmentation.Whereas,for entire WBC segmentation,ISMA-KM and the“CbCr”color component of YCbCr color space provide the best results with an accuracy of above 99%.Furthermore,ISMA-KM and ISMA-RKM have the lowest and highest execution times,respectively.On the other hand,ISMA provides competitive outcomes over CEC2019 benchmark test functions compared to recent well-established and efficient Nature-Inspired Optimization Algorithms(NIOAs).

Image segmentation of embryonic plant cell using pulse-coupled neural networks

Traditional image segmentation algorithms exhibit weak performance for plant cells which have complex structure. On the other hand, pulse-coupled neural network (PCNN) based on Eckhorn’s model of the cat visual cortex should be suitable to the segmentation of plant cell image. But the present theories cannot explain the relationship between the parameters of PCNN mathematical model and the effect of segmentation. Satisfactory results usually require time-consuming selection of experimental parameters. Mean-while, in a proper, selected parametric model, the number of iteration determines the segmented effect evaluated by visual judgment, which decreases the efficiency of image segmentation. To avoid these flaws, this note proposes a new PCNN algorithm for automatically segmenting plant embryonic cell image based on the maximum entropy principle. The algorithm produces a desirable result. In addition, a model with proper parameters can automatically determine the number of iteration, avoid visual judgment,

SOSNet:一种非对称编码器-解码器结构的非小细胞肺癌CT图像分割模型

非小细胞肺癌严重损害人类健康,早期非小细胞肺癌CT(Computed Tomography)图像中的肿瘤结节体积小,不易发现,极易造成漏诊和误诊.为了精确分割非小细胞肺癌CT图像中的小体积肿瘤结节,本文提出SOSNet(Small Object Segmentation Networks)自动分割模型,利用ResNet(Residual Network)基础层和空洞卷积构造非对称编码器-解码器结构作为分割主网络,利用轴向取反注意力模块ARA(Axial Reverse Attention)逐步擦除背景中对分割有影响的结构,再使用结构细化模块SR(Structure Refinement)对主网络输出的粗略特征图进行结构细化,从而实现非小细胞肺癌肿瘤结节分割.在非小细胞肺癌公开数据集的实验测试表明,本文提出的小目标自动分割模型SOSNet可以有效分割出非小细胞肺癌CT图像中的小体积肿瘤结节,其mDice(mean-Dice)、mIoU(mean Intersection over Union)、Sensitivity、F1、Specificity、平均绝对误差MAE(Mean Absolute Error)均优于当前最先进的小目标分割模型CaraNet(Context Axial Reverse Attention Network).

An energy conduction model for cell image segmentation

Cell image segmentation is an essential step in cytopathological analysis.Although their execution speed is fast,the results of cell image segmentation by conventional pixel-based,edge-based and continuity-based methods are often coarse.Fine structures in a cell image can be obtained with a method that quickly adjusts the threshold levels.However,the processing time of such a method is usually long and the final results may be sensitive to intensity differences and other factors.In this article,a new energy model is proposed that synthesizes a differential equation from the conventional and level set methods,and utilizes the nonuniformity property of cell images (e.g.cytoplasms are more uneven than the background).The feasibility and robustness of the proposed model was demonstrated by processing relatively complicated background images of both simulated and real cell images.

藻细胞显微成像中微流控自动进样分段控制方法

藻细胞显微图像快速自动获取具有重要的应用价值。针对微流控-显微成像技术中样品进样效率与细胞成像质量问题,研究了基于藻细胞通过荧光检测窗口持续时间的样品平均流速检测方法,并提出基于体积流量调节的微流控自动进样分段控制方法。结果表明,进样速度在10~30μL/min范围内,样品平均流速检测误差小于5%;分段控制实现了藻细胞显微图像的高质量自动获取,与显微镜检成像质量基本一致,且样品进样速度提升68%以上。研究结果为藻细胞显微图像高效自动获取提供了有效实用方法。

基于改进轻量化U-Net模型的光伏电池EL图像缺陷检测

基于实际工程检测现场神经网络结构庞大、参数量巨大、环境复杂,硬件设备性能差等原因导致缺陷的实时检测速率慢、精度低的问题,本研究结合MobileNet中的深度可分离卷积配合ECA注意力机制模块的轻量化思想,以及U-Net网络的特征提取模型提出了一种基于改进U-Net网络模型的光伏电池板缺陷检测方法。同时,根据光伏电池缺陷的特点,选择适合的激活函数以及对交叉熵损失函数进行了改进。实验结果表明,改进的U-Net算法较原算法不仅将参数量减少了36%,而且对裂纹、黑斑等缺陷的检测精度达到了97.05%,相对传统网络具有较好的光伏电池表面缺陷分割效果。

C1M2:a universal algorithm for 3D instance segmentation,annotation,and quantification of irregular cells

Cell instance segmentation is a fundamental task for many biological applications,especially for packed cells in three-dimensional(3D)microscope images that can fully display cellular morphology.Image processing algorithms based on neural networks and feature engineering have enabled great progress in two-dimensional(2D)instance segmentation.However,current methods cannot achieve high segmentation accuracy for irregular cells in 3D images.In this study,we introduce a universal,morphology-based 3D instance segmentation algorithm called Crop Once Merge Twice(C1M2),which can segment cells from a wide range of image types and does not require nucleus images.C1M2 can be extended to quantify the fluorescence intensity of fluorescent proteins and antibodies and automatically annotate their expression levels in individual cells.Our results suggest that C1M2 can serve as a tissue cytometry for 3D histopathological assays by quantifying fluorescence intensity with spatial localization and morphological information.

基于Swin-UNet血细胞分割方法研究

血细胞分割结果是医生诊断病情的一项重要依据。医学检测血细胞方法容易受外界干扰且效率低下,传统图像分割模型精确度低,对背景杂乱的血细胞图像分割效果差。为提高血细胞分割效率与准确性,提出一种基于Swin-UNet改进的血细胞分割算法,首先通过迁移学习引入Swin-UNet在ImageNet上预训练模型参数作为特征提取前端,提高模型的泛化能力;其次根据Swin-UNet算法改进下采样模块归一化函数,提高模型训练速度。实验结果表明,所提方法在精确率、召回率和F1指标上有较大提升,其值分别是97%、98%和97%,相较于传统的UNet分割方法提高3%。

A counting method for complex overlapping erythrocytes-based microscopic imaging

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%.

Automatic counting method for complex overlapping erythrocytes based on seed prediction in microscopic imaging

Blood cell counting is an important medical test to help medical staffs diagnose various symptoms and diseascs.An automatic segmentation of complex overlapping erythrocytes based on seed prediction in microscopic imaging is proposed.The four main innovations of this ressearch 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 clus-ters.(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%.

Automatic delineation of organs at risk in non-small cell lung cancer radiotherapy based on deep learning networks

Objective To introduce an end-to-end automatic segmentation method for organs at risk(OARs)in chest computed tomography(CT)images based on dense connection deep learning and to provide an accurate auto-segmentation model to reduce the workload on radiation oncologists.Methods CT images of 36 lung cancer cases were included in this study.Of these,27 cases were randomly selected as the training set,six cases as the validation set,and nine cases as the testing set.The left and right lungs,cord,and heart were auto-segmented,and the training time was set to approximately 5 h.The testing set was evaluated using geometric metrics including the Dice similarity coefficient(DSC),95%Hausdorff distance(HD95),and average surface distance(ASD).Thereafter,two sets of treatment plans were optimized based on manually contoured OARs and automatically contoured OARs,respectively.Dosimetric parameters including Dmax and Vx of the OARs were obtained and compared.Results The proposed model was superior to U-Net in terms of the DSC,HD95,and ASD,although there was no significant difference in the segmentation results yielded by both networks(P>0.05).Compared to manual segmentation,auto-segmentation significantly reduced the segmentation time by nearly 40.7%(P<0.05).Moreover,the differences in dose-volume parameters between the two sets of plans were not statistically significant(P>0.05).Conclusion The bilateral lung,cord,and heart could be accurately delineated using the DenseNet-based deep learning method.Thus,feature map reuse can be a novel approach to medical image auto-segmentation.

Automated segmentation and quantitative study of retinal pigment epithelium cells for photoacoustic microscopy imaging

We develop an improved region growing method to realize automatic retinal pigment epithelium （RPE） cell segmentation for photoacoustic microscopy （PAM） imaging. The minimum bounding rectangle of the segmented region is used in this method to dynamically update the growing threshold for optimal segmentation. Phantom images and PAM imaging results of normal porcine RPE are applied to demonstrate the effectiveness of the segmentation. The method realizes accurate segmentation of RPE cells and also provides the basis for quantitative analysis of cell features such as cell area and component content, which can have potential applications in studying RPE cell functions for PAM imaging.

Hybrid model enabling highly efficient follicular segmentation in thyroid cytopathological whole slide image

Background The prevalence of thyroid cancer is growing rapidly.Early and precise diagnosis is critical in thy-roid cancer caring.An automatic thyroid cancer diagnostic tool can be valuable to achieve early detection and diagnostic consistency.Only the follicular areas in the sample contain useful information to the thyroid cancer diagnosis based on fine needle aspiration(FNA).This study aimed to develop a highly efficient accurate method for follicular cell areas segmentation(FCAS)of thyroid cytopathological whole slide images(WSIs).Methods A total of 96 cell samples from July 2017 to July 2018 were collected in one hospital in Beijing,China.Forty-three WSIs were selected and manually labeled,including 17 cases of papillary thyroid carci-noma sample and 26 cases of benign sample.Six thousand and nine hundred cropped typical image patches(available on https://github.com/bupt-ai-cz/Hybrid-Model-Enabling-Highly-Efficient-Follicular-Segmentation)of 1024×1024 pixels from 13 large WSIs were used for patch-level model training and testing and all of the 13 large WSIs were papillary thyroid carcinoma samples.Thirty testing WSIs with an average size 36,217×29,400(from 10,240×10,240 to 81,920×61,440)were used to test the effectiveness of the hybrid model.Based on the traditional semantic segmentation model deeplabv3,we constructed a hybrid segmentation architecture by adding a classification branch into the segmentation scheme to improve efficiency.Accuracy was used to measure the performance of the classification model;pixel accuracy(pAcc),mean accuracy(mAcc),mean intersection over union(mIoU),and frequency weighted intersection over union(fwIoU)were used to measure the performance of the segmentation model,respectively.Results Using this method,up to 93%WSI segmentation time was reduced by skipping the colloidal areas and the blank background areas.The average processing time of 30 WSI was 49.49 s.On the patch dataset,this hybrid model might reach pAcc=98.65%,mAcc=85.60%,mIoU=79.61%,and fwIoU=97.54%.On the WSI dataset,this model might reach pAcc=99.30%,mAcc=68.94%,mIoU=58.21%,and fwIoU=99.50%.Conclusion The proposed hybrid method might significantly improve previous solutions and achieve the superior performance of efficiency and accuracy.

基于稠密块和注意力机制的肺部病理图像异常细胞分割

针对肺部细胞病理图像亮度不均衡、异常细胞轮廓精准分割难以实现的问题,提出一种以U-Net为基本框架,结合稠密块以及注意力机制的异常细胞分割模型。首先,利用具有编码器-解码器结构的U-Net对异常细胞进行分割;然后,在U-Net中引入稠密块,以提高特征之间的传播能力,提取更多异常细胞的特征信息;最后,利用注意力机制提高异常细胞区域的权重,降低亮度不均衡对模型的干扰。实验结果表明,该方法的IoU和Dice相似系数值分别为0.6928和0.8060,与其他模型相比,提出的方法能够分割出低对比度区域和形状多样的异常细胞。