CN112200801B - Automatic detection method for cell nucleus of digital pathological image - Google Patents

Automatic detection method for cell nucleus of digital pathological image Download PDF

Info

Publication number
CN112200801B
CN112200801B CN202011190195.2A CN202011190195A CN112200801B CN 112200801 B CN112200801 B CN 112200801B CN 202011190195 A CN202011190195 A CN 202011190195A CN 112200801 B CN112200801 B CN 112200801B
Authority
CN
China
Prior art keywords
image
cell nucleus
fragment
images
data set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011190195.2A
Other languages
Chinese (zh)
Other versions
CN112200801A (en
Inventor
叶丰
步宏
付波
李艳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
West China Hospital of Sichuan University
Original Assignee
West China Hospital of Sichuan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by West China Hospital of Sichuan University filed Critical West China Hospital of Sichuan University
Priority to CN202011190195.2A priority Critical patent/CN112200801B/en
Publication of CN112200801A publication Critical patent/CN112200801A/en
Application granted granted Critical
Publication of CN112200801B publication Critical patent/CN112200801B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20081Training; Learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20084Artificial neural networks [ANN]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30024Cell structures in vitro; Tissue sections in vitro

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

本发明公开了一种数字病理图像的细胞核自动检测方法,其包括获取数字病理图像的碎片图像,并对其进行标准化处理;将标准化处理后的碎片图像输入已训练的细胞核检测模型中进行检测,得到细胞核集合SN1;将碎片图像中检测到的细胞核采用背景色覆盖,并采用图像梯度能量函数计算每张碎片图像的能量值;判断每张碎片图像的能量值是否大于预设阈值,若是,进入下一步,否则舍弃相应的碎片图像;将所有的能量值大于预设阈值的碎片图像输入已训练的细胞核检测模型中进行检测,得到细胞核集合SN2;合并细胞核集合SN1和细胞核集合SN2,得到最终的细胞核集合SN

Figure 202011190195

The invention discloses an automatic detection method for cell nucleus of digital pathological images, which comprises acquiring fragment images of digital pathological images and standardizing them; inputting the normalized fragment images into a trained cell nucleus detection model for detection, Obtain the cell nucleus set S N1 ; cover the detected cell nucleus in the fragment image with the background color, and use the image gradient energy function to calculate the energy value of each fragment image; judge whether the energy value of each fragment image is greater than the preset threshold, if so, Go to the next step, otherwise discard the corresponding fragment images; input all the fragment images with energy values greater than the preset threshold into the trained cell nucleus detection model for detection to obtain the cell nucleus set S N2 ; merge the cell nucleus set S N1 and the cell nucleus set S N2 , to obtain the final set of nuclei S N .

Figure 202011190195

Description

数字病理图像的细胞核自动检测方法A method for automatic detection of cell nuclei in digital pathological images

技术领域technical field

本发明涉及图像中的细胞核检测技术,具体涉及数字病理图像的细胞核自动检测方法。The invention relates to a cell nucleus detection technology in an image, in particular to a cell nucleus automatic detection method of a digital pathological image.

背景技术Background technique

癌的发生发展是癌细胞与肿瘤微环境相互作用的结果,肿瘤间质中细胞种类、数量或形态的改变,具有重要医学指导意义。例如,乳腺癌中的淋巴细胞浸润者一般预后较好,而肿瘤相关纤维细胞的出现,则提示预后不良。在常规病理工作中,一般定性描述肿瘤间质中细胞成分和细胞外基质的变化。而基于数字病理图像分析,可自动分割间质中的不同成分,并进行定量或定性研究。The occurrence and development of cancer is the result of the interaction between cancer cells and the tumor microenvironment. The changes in the type, number or shape of cells in the tumor stroma have important medical guiding significance. For example, lymphocytic infiltrates in breast cancer generally have a better prognosis, while the presence of tumor-associated fibroblasts suggests a poor prognosis. In routine pathological work, changes in cellular components and extracellular matrix in the tumor stroma are generally described qualitatively. Based on digital pathological image analysis, different components in the interstitium can be automatically segmented and quantitative or qualitative studies can be performed.

在定量研究上,利用核形态量化测定,研究者发现细胞核在低核面积与高核面积患者之间的预后存在显著性差异。为提取乳腺癌上皮细胞和基质(6642个特征)中丰富的定量特征集,斯坦福大学的研究者开发了C-Path系统(Computational Pathologist),用于测量包括图像对象的标准形态描述符和更高级别的上下文、关系和全局图像特征。In quantitative studies, using quantitative nuclear morphometry, the researchers found that there was a significant difference in the prognosis of nuclei between patients with low nuclear area and high nuclear area. To extract a rich set of quantitative features in breast cancer epithelium and stroma (6642 features), researchers at Stanford University developed the C-Path system (Computational Pathologist) to measure standard morphological descriptors including image objects and higher Levels of contextual, relational, and global image features.

病理WSI图像的细胞核检测是整个图像定量分析的基础,为各种医学研究所需的定量分析、生物指标判定提供可靠的支持。虽然基于数字病理的细胞核检测方法提出很多,但其仍然是一项非常有挑战性的工作。其主要原因在于:The detection of nuclei in pathological WSI images is the basis for the quantitative analysis of the entire image, and provides reliable support for the quantitative analysis and determination of biological indicators required for various medical research. Although many methods for nuclear detection based on digital pathology have been proposed, it is still a very challenging task. The main reasons are:

(1)WSI图像间的差异性细微、细胞重叠、颜色分布不均匀;(1) The difference between WSI images is subtle, the cells overlap, and the color distribution is uneven;

(2)缺乏大型公开的、已标记的数据集,给算法研究带来一定困难;(2) The lack of large-scale public and labeled data sets brings certain difficulties to algorithm research;

(3)有别于其他肿瘤,乳腺大小、致密度、形状等个体差异大,导致的数字成像复杂。(3) Different from other tumors, the size, density, and shape of the breast have great individual differences, resulting in complicated digital imaging.

(4)细胞核手工标记工作非常繁重,难以形成大的标记数据库。(4) The manual labeling of nuclei is very heavy, and it is difficult to form a large labeling database.

实现基于传统的机器学习检测细胞核,需要手动调整大量的参数,准确率难以提高,且难以适应各类复杂设备和染色差异;基于深度学习方法的模型又往往需要大量标记训练样本,并且需要仔细调节模型参数和训练神经网络模型,这会耗费大量时间。To realize the detection of cell nuclei based on traditional machine learning, a large number of parameters need to be manually adjusted, the accuracy is difficult to improve, and it is difficult to adapt to various complex equipment and staining differences; models based on deep learning methods often require a large number of labeled training samples, and need to be carefully adjusted Model parameters and training neural network models, which can take a lot of time.

发明内容SUMMARY OF THE INVENTION

针对现有技术中的上述不足,本发明提供了一种检测精度高的数字病理图像的细胞核自动检测方法。Aiming at the above deficiencies in the prior art, the present invention provides an automatic detection method for cell nuclei of digital pathological images with high detection accuracy.

为了达到上述发明目的,本发明采用的技术方案为:In order to achieve the above-mentioned purpose of the invention, the technical scheme adopted in the present invention is:

提供一种数字病理图像的细胞核自动检测方法,其包括:Provided is a method for automatic detection of cell nuclei in digital pathological images, comprising:

S1、获取数字病理图像的碎片图像,并对其进行标准化处理;S1. Acquiring fragment images of digital pathological images and standardizing them;

S2、将标准化处理后的碎片图像输入已训练的细胞核检测模型中进行检测,得到细胞核集合SN1S2, input the fragmented images after the standardized processing into the trained cell nucleus detection model for detection, and obtain the cell nucleus set S N1 ;

S3、将碎片图像中检测到的细胞核采用背景色覆盖,并采用图像梯度能量函数计算每张碎片图像的能量值;S3. Cover the cell nucleus detected in the fragment image with the background color, and use the image gradient energy function to calculate the energy value of each fragment image;

S4、判断每张碎片图像的能量值是否大于预设阈值,若是,进入步骤S5,否则舍弃相应的碎片图像;S4, determine whether the energy value of each fragment image is greater than the preset threshold, if so, go to step S5, otherwise discard the corresponding fragment image;

S5、将所有的能量值大于预设阈值的碎片图像输入已训练的细胞核检测模型中进行检测,得到细胞核集合SN2S5, input all the fragmented images whose energy values are greater than the preset threshold into the trained cell nucleus detection model for detection, and obtain the cell nucleus set S N2 ;

S6、合并细胞核集合SN1和细胞核集合SN2,得到最终的细胞核集合SNS6. Merge the cell nucleus set S N1 and the cell nucleus set S N2 to obtain the final cell nucleus set S N .

进一步地,所述细胞核检测模型的训练方法包括:Further, the training method of the cell nucleus detection model includes:

下载MSCOCO数据集D1,并采用MSCOCO数据集对目标检测算法进行训练,得到目标检测模型M1Download the MSCOCO data set D 1 , and use the MSCOCO data set to train the target detection algorithm to obtain the target detection model M 1 ;

下载2018DSB数据集D2,并采用2018DSB数据集对模型参数仅保留特征提取层的目标检测模型M1进行训练,得到目标检测模型M2Download the 2018DSB data set D 2 , and use the 2018 DSB data set to train the target detection model M 1 whose model parameters only retain the feature extraction layer to obtain the target detection model M 2 ;

下载开放的数字病理图像的细胞核标注数据集D3,并对数据集D3中的每张碎片图像进行标准化处理,之后随机对标准化处理后的碎片图像中三通道的像素值按预设比例进行反色;Download the open digital pathological image nucleus labeling dataset D 3 , and normalize each fragment image in the dataset D 3 , and then randomly perform pixel values of three channels in the normalized fragment image according to a preset ratio. reverse color;

将反色处理后得到的数据集与数据集D3合并后对模型参数仅保留特征提取层的目标检测模型M3进行训练,得到细胞核检测模型。After merging the data set obtained after the inverse color processing with the data set D 3 , the target detection model M 3 whose model parameters are retained only in the feature extraction layer is trained to obtain a cell nucleus detection model.

本发明的有益效果为:在对细胞核进行检测时,本方案对每个碎片图像执行两次检测,即第一次直接在碎片图像上执行检测,第二次在原始图像的RGB三通道上,分别将检测到的细胞核设置为背景色;然后重新执行细胞核检测;最后,合并两次细胞核检测作为最终的检测结果;通过该种检测方式可以大幅降低图像中细胞核漏检的情况。The beneficial effects of the present invention are: when detecting cell nuclei, the scheme performs two detections on each fragment image, that is, the first time is directly on the fragment image, and the second time is on the RGB three channels of the original image, Set the detected nuclei as the background color respectively; then perform the nuclei detection again; finally, combine the two nuclei detections as the final detection result; this detection method can greatly reduce the missed detection of nuclei in the image.

另外,本方案在对细胞核检测模型进行训练时,充分利用开放数据集提供大量标注信息,通过迁移学习可省去大量的标注工作;此外,可以减少设备、环境和其他客观因素对病理图像的影响,极大提升细胞核检测的精度和鲁棒性。In addition, when training the cell nucleus detection model, this scheme makes full use of open data sets to provide a large amount of labeling information, and a lot of labeling work can be saved through transfer learning; in addition, the influence of equipment, environment and other objective factors on pathological images can be reduced , which greatly improves the accuracy and robustness of nuclear detection.

附图说明Description of drawings

图1为数字病理图像的细胞核自动检测方法的流程图。Figure 1 is a flow chart of a method for automatic detection of cell nuclei in digital pathological images.

具体实施方式Detailed ways

下面对本发明的具体实施方式进行描述,以便于本技术领域的技术人员理解本发明,但应该清楚,本发明不限于具体实施方式的范围,对本技术领域的普通技术人员来讲,只要各种变化在所附的权利要求限定和确定的本发明的精神和范围内,这些变化是显而易见的,一切利用本发明构思的发明创造均在保护之列。The specific embodiments of the present invention are described below to facilitate those skilled in the art to understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes Such changes are obvious within the spirit and scope of the present invention as defined and determined by the appended claims, and all inventions and creations utilizing the inventive concept are within the scope of protection.

参考图1,图1示出了数字病理图像的细胞核自动检测方法的流程图;如图1所示,该方法S包括步骤S1至步骤S6。Referring to FIG. 1 , FIG. 1 shows a flowchart of a method for automatic detection of cell nuclei in digital pathological images; as shown in FIG. 1 , the method S includes steps S1 to S6 .

在步骤S1中,获取数字病理图像的碎片图像,并对其进行标准化处理;其中标准化处理所采用的方法为Vahadane方法。In step S1, a fragmented image of the digital pathological image is acquired and subjected to standardization processing; wherein the method adopted for the standardization processing is the Vahadane method.

在步骤S2中,将标准化处理后的碎片图像输入已训练的细胞核检测模型中进行检测,得到细胞核集合SN1In step S2, the standardized fragmented images are input into the trained cell nucleus detection model for detection, and the cell nucleus set S N1 is obtained;

在本发明的一个实施例中,细胞核检测模型的训练方法包括:In one embodiment of the present invention, the training method of the cell nucleus detection model includes:

A1、下载MSCOCO数据集D1,并采用MSCOCO数据集对目标检测算法进行训练,得到目标检测模型M1;本方案优选目标检测算法为Mask-RCNN算法。A1. Download the MSCOCO data set D 1 , and use the MSCOCO data set to train the target detection algorithm to obtain a target detection model M 1 ; the preferred target detection algorithm in this scheme is the Mask-RCNN algorithm.

A2、下载2018DSB数据集D2,并采用2018DSB数据集对模型参数仅保留特征提取层的目标检测模型M1进行训练,得到目标检测模型M2A2. Download the 2018DSB data set D 2 , and use the 2018 DSB data set to train the target detection model M 1 whose model parameters only retain the feature extraction layer to obtain the target detection model M 2 ;

A3、下载开放的数字病理图像的细胞核标注数据集D3,并对数据集D3中的每张碎片图像进行标准化处理,之后随机对标准化处理后的碎片图像中三通道的像素值按预设比例进行反色;A3. Download the open digital pathological image cell nucleus labeling dataset D 3 , and standardize each fragment image in the dataset D 3 , and then randomly select the pixel values of the three channels in the standardized fragment image according to the preset value. Invert the scale;

其中反色处理为采用255减原像素值更新三通道的原像素值。The inverse color processing is to use 255 minus the original pixel value to update the original pixel value of the three channels.

A4、将反色处理后得到的数据集与数据集D3合并后对模型参数仅保留特征提取层的目标检测模型M3进行训练,得到细胞核检测模型。A4. After merging the data set obtained after the inverse color processing with the data set D3 , train the target detection model M3 whose model parameters only retain the feature extraction layer to obtain a cell nucleus detection model.

本方案采用上述方式对训练得到细胞核检测模型,充分利用开放数据集提供的大量标注信息,通过迁移学习可以省去大量的标注工作。通过少量的数字病理图像进行数据集扩增后,再对目标检测模型进行训练,可以大幅提高细胞核的检测精度。This scheme uses the above method to train the nucleus detection model, makes full use of the large amount of annotation information provided by the open data set, and saves a lot of annotation work through transfer learning. After augmenting the dataset with a small number of digital pathological images, and then training the target detection model, the detection accuracy of cell nuclei can be greatly improved.

实施时,本方案优选细胞核检测模型的训练方法还包括以下步骤:During implementation, the preferred training method of the cell nucleus detection model in this scheme further includes the following steps:

B1、获取用户存储的多张数字病理图像,并读取数字病理图像最底层的超高清图像,之后采用重叠或非重叠方式提取超高清图像的碎片图像构成碎片集合。B1. Acquire multiple digital pathological images stored by the user, and read the ultra-high-definition images at the bottom of the digital pathological images, and then extract the fragmented images of the ultra-high-definition images in an overlapping or non-overlapping manner to form a fragment collection.

实施时,本方案可以采用OpenSlide病理图像读取软件,读取最底层图像;提取碎片时,根据图像像素位置坐标,直接读取碎片图像Ti;可重叠读取,则Ti的起始坐标随机,非重叠读取,则Ti的按步长n读取。When implementing, this scheme can use OpenSlide pathological image reading software to read the bottom image; when extracting fragments, according to the image pixel position coordinates, directly read the fragment image T i ; can be overlapped and read, then the starting coordinates of T i Random, non-overlapping reads, then Ti reads in steps of n .

B2、采用图像梯度能量函数计算每张碎片图像的能量值,挑选能量值大于设定阈值的碎片图像构成图像集ST1B2, using the image gradient energy function to calculate the energy value of each fragment image, and selecting fragment images whose energy value is greater than the set threshold to form an image set ST 1 ;

B3、对图像集ST1中的每张碎片图像进行标准化处理,之后随机对标准化处理后的碎片图像中三通道的像素值按预设比例进行反色,得到新的数据集ST2B3, standardize each fragment image in the image set ST 1 , and then randomly invert the pixel values of the three channels in the normalized fragment image according to a preset ratio to obtain a new data set ST 2 ;

B4、将图像集ST1和数据集ST2合并后对模型参数仅保留特征提取层的细胞核检测模型进行训练,得到最终的细胞核检测模型。B4. After merging the image set ST 1 and the data set ST 2 , train the cell nucleus detection model whose model parameters only retain the feature extraction layer to obtain the final cell nucleus detection model.

本方案在进行模型训练时,通过引入少量实践中的标注数据,可大大提高检测的精确度,减少设备、环境和其他客观因素对病理图像的影响,极大提升细胞核检测的精度和鲁棒性。During model training, this scheme can greatly improve the accuracy of detection by introducing a small amount of labeled data in practice, reduce the impact of equipment, environment and other objective factors on pathological images, and greatly improve the accuracy and robustness of nuclear detection. .

在步骤S3中,将碎片图像中检测到的细胞核采用背景色覆盖,所述背景色覆盖为将碎片图像中检测到的细胞核位置所对应的像素值全部修改为255;In step S3, the cell nucleus detected in the fragment image is covered with a background color, and the background color covering is to modify all the pixel values corresponding to the position of the cell nucleus detected in the fragment image to 255;

之后,采用图像梯度能量函数计算每张碎片图像的能量值:After that, the energy value of each fragment image is calculated using the image gradient energy function:

Figure BDA0002752559670000061
Figure BDA0002752559670000061

其中,Ti为数据集中的第i张碎片图像;g(Ti)为Ti的能量值;x为图像x方向像素值;y为图像y方向像素值。Among them, T i is the ith fragment image in the dataset; g(T i ) is the energy value of T i ; x is the pixel value in the x direction of the image; y is the pixel value in the y direction of the image.

在步骤S4中,判断每张碎片图像的能量值是否大于预设阈值,若是,进入步骤S5,否则舍弃相应的碎片图像;In step S4, it is judged whether the energy value of each fragment image is greater than the preset threshold, if so, go to step S5, otherwise the corresponding fragment image is discarded;

在步骤S5中,将所有的能量值大于预设阈值的碎片图像输入已训练的细胞核检测模型中进行检测,得到细胞核集合SN2In step S5, input all fragment images with energy values greater than a preset threshold into the trained cell nucleus detection model for detection, to obtain a cell nucleus set S N2 ;

在步骤S6中,合并细胞核集合SN1和细胞核集合SN2,得到最终的细胞核集合SNIn step S6, the set of nuclei S N1 and the set of nuclei SN2 are combined to obtain the final set of nuclei SN .

综上所述,采用本方案进行细胞核的检测,可以降低细胞核的漏检,同时还可以大幅提升细胞核检测的精度和鲁棒性。To sum up, the detection of nuclei using this scheme can reduce the missed detection of nuclei, and at the same time can greatly improve the accuracy and robustness of nuclei detection.

Claims (7)

1. The automatic detection method of the cell nucleus of the digital pathological image is characterized by comprising the following steps:
s1, acquiring a fragment image of the digital pathological image, and carrying out standardization processing on the fragment image;
s2, inputting the normalized fragment images into a trained cell nucleus detection model for detection to obtain a cell nucleus set SN1
S3, covering the cell nucleuses detected in the fragment images with background colors, and calculating the energy value of each fragment image by using an image gradient energy function;
s4, judging whether the energy value of each fragment image is larger than a preset threshold value, if so, entering a step S5, and otherwise, discarding the corresponding fragment image;
s5, inputting all fragment images with energy values larger than a preset threshold value into a trained cell nucleus detection model for detection to obtain a cell nucleus set SN2
S6 merging cell nucleus set SN1And cell nucleus set SN2Obtaining the final cell nucleus set SN
2. The method for automatically detecting the cell nucleus of the digital pathological image according to claim 1, wherein the training method of the cell nucleus detection model comprises:
downloading MSCOCO data set D1Training a target detection algorithm by adopting an MSCOCO data set to obtain a target detection model M1
Downloading 2018DSB data set D2And adopting 2018DSB data set to only reserve the target detection model M of the feature extraction layer for the model parameters1Training to obtain a target detection model M2
Downloading open nuclear annotation data set D of digital pathology images3And to the data set D3Normalizing each fragment image, and then randomly reversing the pixel values of three channels in the normalized fragment images according to a preset proportion;
the data set obtained after the reverse color processing and the data set D are processed3Target detection model M only retaining feature extraction layer for model parameters after combination3And training to obtain a cell nucleus detection model.
3. The method for automatically detecting the cell nucleus of the digital pathological image according to claim 2, further comprising:
acquiring a plurality of digital pathological images stored by a user, reading the ultra-high-definition image at the bottommost layer of the digital pathological images, and extracting fragment images of the ultra-high-definition image in an overlapping or non-overlapping mode to form a fragment set;
calculating the energy value of each fragment image by adopting an image gradient energy function, and selecting the fragment images with the energy values larger than a set threshold value to form an image set ST1
For image set ST1Normalizing each fragment image, and then randomly reversing the pixel values of three channels in the normalized fragment images according to a preset proportion to obtain a new data set ST2
Set of images ST1And a data set ST2And training the cell nucleus detection model with model parameters only reserved in the feature extraction layer after combination to obtain the final cell nucleus detection model.
4. The method for automatically detecting the cell nucleus of the digital pathological image according to claim 3, wherein the energy function is calculated by the formula:
Figure FDA0002752559660000021
wherein, TiThe ith fragment image in the data set; g (T)i) Is TiThe energy value of (a); x is the pixel value in the x direction of the image; y is the image y-direction pixel value.
5. The method for automatically detecting the cell nucleus of the digital pathological image according to claim 2, wherein the normalization process is performed by a Vahadane method; the reverse color processing is to adopt 255 to reduce the original pixel value to update the original pixel value of three channels.
6. The method as claimed in claim 1, wherein the background color is overlaid to modify all pixel values corresponding to the detected cell nucleus positions in the fragment image to 255.
7. The method for automatically detecting the cell nucleus of a digital pathological image according to any one of claims 2-5, wherein the target detection algorithm is Mask-RCNN algorithm.
CN202011190195.2A 2020-10-30 2020-10-30 Automatic detection method for cell nucleus of digital pathological image Active CN112200801B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011190195.2A CN112200801B (en) 2020-10-30 2020-10-30 Automatic detection method for cell nucleus of digital pathological image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011190195.2A CN112200801B (en) 2020-10-30 2020-10-30 Automatic detection method for cell nucleus of digital pathological image

Publications (2)

Publication Number Publication Date
CN112200801A CN112200801A (en) 2021-01-08
CN112200801B true CN112200801B (en) 2022-06-17

Family

ID=74011149

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011190195.2A Active CN112200801B (en) 2020-10-30 2020-10-30 Automatic detection method for cell nucleus of digital pathological image

Country Status (1)

Country Link
CN (1) CN112200801B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008146278A (en) * 2006-12-08 2008-06-26 National Institute Of Advanced Industrial & Technology Cell contour extraction apparatus, cell contour extraction method and program
CN107169977A (en) * 2017-04-24 2017-09-15 华南理工大学 Adaptive threshold color image edge detection method based on FPGA and Kirsch
CN108364288A (en) * 2018-03-01 2018-08-03 北京航空航天大学 Dividing method and device for breast cancer pathological image
CN110288582A (en) * 2019-06-26 2019-09-27 电子科技大学 An Accurate Segmentation Method of Cell Nuclei
CN111275727A (en) * 2020-01-19 2020-06-12 北方工业大学 Cell segmentation method, cell segmentation apparatus, and computer-readable storage medium

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5354842B2 (en) * 2006-05-26 2013-11-27 キヤノン株式会社 Image processing method and image processing apparatus
US10360434B2 (en) * 2016-07-25 2019-07-23 Case Western Reserve University Multi-pass adaptive voting for nuclei detection in histopathological images

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008146278A (en) * 2006-12-08 2008-06-26 National Institute Of Advanced Industrial & Technology Cell contour extraction apparatus, cell contour extraction method and program
CN107169977A (en) * 2017-04-24 2017-09-15 华南理工大学 Adaptive threshold color image edge detection method based on FPGA and Kirsch
CN108364288A (en) * 2018-03-01 2018-08-03 北京航空航天大学 Dividing method and device for breast cancer pathological image
CN110288582A (en) * 2019-06-26 2019-09-27 电子科技大学 An Accurate Segmentation Method of Cell Nuclei
CN111275727A (en) * 2020-01-19 2020-06-12 北方工业大学 Cell segmentation method, cell segmentation apparatus, and computer-readable storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于卷积神经网络的细胞核图像检测与分类研究;李想;《中国知网硕士学位论文全文数据库电子期刊》;20200615;正文第21-48页 *

Also Published As

Publication number Publication date
CN112200801A (en) 2021-01-08

Similar Documents

Publication Publication Date Title
WO2022063199A1 (en) Pulmonary nodule automatic detection method, apparatus and computer system
CN111462042B (en) Cancer prognosis analysis method and system
CN111986150B (en) The method comprises the following steps of: digital number pathological image Interactive annotation refining method
CN110472676A (en) Stomach morning cancerous tissue image classification system based on deep neural network
CN110866893A (en) Pathological image-based TMB classification method, system and TMB analysis device
Chang et al. Nuclear segmentation in H&E sections via multi-reference graph cut (MRGC)
CN108564026A (en) Network establishing method and system for Thyroid Neoplasms smear image classification
Rong et al. A deep learning approach for histology-based nucleus segmentation and tumor microenvironment characterization
CN113160175B (en) Tumor lymphatic vessel infiltration detection method based on cascade network
CN110555835A (en) brain slice image region division method and device
CN108009567B (en) An Automatic Discrimination Method of Fecal Traits Combining Image Color and HOG and SVM
CN112990214A (en) Medical image feature recognition prediction model
Xu et al. Using transfer learning on whole slide images to predict tumor mutational burden in bladder cancer patients
CN107358611A (en) A kind of automatic division method of panoramic scanning pathological image transport zone
CN113674292A (en) A Semi-Supervised Myeloma Cell Instance Segmentation Method Based on Partial Instance Annotation
CN116883341A (en) Liver tumor CT image automatic segmentation method based on deep learning
CN113011257A (en) Breast cancer immunohistochemical artificial intelligence interpretation method
CN108921172A (en) Image processing apparatus and method based on support vector machines
Ayana et al. Vision Transformers for Breast Cancer Human Epidermal Growth Factor Receptor 2 Expression Staging without Immunohistochemical Staining
CN112508860B (en) Artificial intelligence interpretation method and system for positive check of immunohistochemical image
CN112200801B (en) Automatic detection method for cell nucleus of digital pathological image
CN112669288B (en) Cell target expression prediction method, system and device based on digital pathological image
CN117670895B (en) Cell segmentation method for immunohistochemical pathological images based on section restaining technology
CN113435469A (en) Kidney tumor enhanced CT image automatic identification system based on deep learning and training method thereof
CN118247224A (en) A breast cancer pathology image analysis method based on deep learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant