CN111815591A - Pulmonary nodule detection method based on CT image - Google Patents
Pulmonary nodule detection method based on CT image Download PDFInfo
- Publication number
- CN111815591A CN111815591A CN202010609059.6A CN202010609059A CN111815591A CN 111815591 A CN111815591 A CN 111815591A CN 202010609059 A CN202010609059 A CN 202010609059A CN 111815591 A CN111815591 A CN 111815591A
- Authority
- CN
- China
- Prior art keywords
- image
- corrosion
- lung nodule
- structural elements
- original
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 230000002685 pulmonary effect Effects 0.000 title claims abstract description 19
- 206010056342 Pulmonary mass Diseases 0.000 claims abstract description 95
- 230000007797 corrosion Effects 0.000 claims abstract description 48
- 238000005260 corrosion Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000013145 classification model Methods 0.000 claims abstract description 21
- 238000005070 sampling Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 4
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 3
- 229910003460 diamond Inorganic materials 0.000 claims 2
- 239000010432 diamond Substances 0.000 claims 2
- 238000002591 computed tomography Methods 0.000 description 49
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 5
- 201000005202 lung cancer Diseases 0.000 description 5
- 208000020816 lung neoplasm Diseases 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000005530 etching Methods 0.000 description 3
- 210000004072 lung Anatomy 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000003211 malignant effect Effects 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
- G06T2207/30064—Lung nodule
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a pulmonary nodule detection method based on a CT image, and belongs to the technical field of medical image processing. The detection method comprises the following steps: acquiring an original CT image, and binarizing the original CT image; carrying out continuous n-time corrosion on the binarized image by using the structural elements, and carrying out convolution processing on the image subjected to corrosion each time; carrying out exclusive OR operation on the images subjected to corrosion and convolution twice, and finding out the pixels which disappear in the corrosion process; intercepting a lung nodule suspected region picture with a set size by taking the position of a disappeared pixel point as a center on an original CT image; and inputting the lung nodule suspected region picture into a trained classification model for classification, and completing the detection of the lung nodule. According to the method, the suspected lung nodule area is found out before the lung nodule area is positioned, so that the accuracy of positioning the lung nodule area is improved, and the suspected lung nodule area is subjected to binaryzation, multiple corrosion and convolution operations only on an original CT image, so that the whole process is simple.
Description
Technical Field
The invention relates to a pulmonary nodule detection method based on a CT image, and belongs to the technical field of medical image processing.
Background
The lung cancer is one of the most common malignant tumors in China, the five-year survival rate of the lung cancer in China is only 16.1%, and early diagnosis of the lung cancer is an important means for improving the survival rate of patients. However, early lung cancer features, lung nodules, are not obvious and need to be effectively differentially diagnosed and treated. The diagnosis process is to quickly determine whether the lung nodule is benign or malignant, and the treatment process is to remove the malignant nodule as early as possible, so that the diagnosis and treatment of the lung nodule can not only avoid unnecessary over-treatment, but also is the key to preventing and treating lung cancer.
At present, the diagnosis process of the pulmonary nodules is carried out by matching CT images with clinical experience, but the diagnosis efficiency is not high due to limited medical resources, so that the method proposes that the neural network is used for detecting the pulmonary nodules on the CT images, and doctors assist, so that the human resources can be better saved, and the detection efficiency is improved.
In general, the process of performing lung nodule identification includes: firstly, segmenting a CT image through a neural network to obtain a lung nodule region; and then, identifying the lung nodule region through another neural network, and grading the lung nodules to further finish the detection of the lung nodules.
However, in the above detection process, the accuracy of the neural network algorithm used for determining the lung nodule region is low.
Disclosure of Invention
The application aims to provide a lung nodule detection method based on a CT image, which is used for solving the problem of inaccurate detection in the prior art.
In order to achieve the above object, the present application provides a first technical solution of a pulmonary nodule detection method based on CT images, including the following steps:
1) acquiring an original CT image, and binarizing the original CT image;
2) carrying out continuous n-time corrosion on the binarized image by using the structural elements, and carrying out convolution processing on the image subjected to corrosion each time;
3) carrying out exclusive OR operation on the images subjected to corrosion and convolution twice, and finding out the pixels which disappear in the corrosion process;
4) intercepting a lung nodule suspected region picture with a set size by taking the position of a disappeared pixel point as a center on an original CT image;
5) and inputting the lung nodule suspected region picture into a trained classification model for classification, and completing the detection of the lung nodule.
The first technical scheme of the lung nodule detection method based on the CT image has the beneficial effects that: after an original CT image is obtained, firstly, binarization processing is carried out, the binarization processing is the basis of subsequent mathematical form processing, the mathematical form processing is corrosion processing, and continuous n times of corrosion processing is carried out, the most marginal pixel point of the image is eliminated by corrosion each time, for a nodule area, the pixel point eliminated for the last time is the lung nodule central point, so that the pixel point which disappears in the corrosion process can be found out by carrying out XOR operation on the images subjected to adjacent two times of corrosion and convolution, the position of the pixel point which disappears is determined, the position of a suspected lung nodule area on the original CT image is further determined according to the corrosion times and the number of layers of the pixel point which corrodes each time, and finally, the suspected lung nodule area is intercepted and classified in a classification model, whether the area is the lung nodule area is determined, and the detection of the lung nodule is completed. According to the method, the suspected lung nodule area is found out before the lung nodule area is positioned, so that the accuracy of the positioning detection of the lung nodule area is improved, and the determination of the suspected lung nodule area is only to carry out binaryzation, multiple corrosion and convolution operations on an original CT image, so that the whole process is simple.
Further, in order to obtain a classification model, the training method of the classification model comprises: and manually segmenting the marked CT image to obtain a data set, and training the data set.
Further, in order to complete the etching operation, the structural element in step 2) is a cross-shaped structural element of 3 x 3, a diamond-shaped structural element, a spherical structural element, or a disc-shaped structural element.
In addition, the present application also provides a second technical solution of a pulmonary nodule detection method based on CT images, comprising the following steps:
1) acquiring an original CT image, and binarizing the original CT image;
2) carrying out continuous n-time corrosion on the binarized image by using the structural elements, and carrying out convolution processing on the image subjected to corrosion each time;
3) carrying out exclusive OR operation on the images subjected to corrosion and convolution twice, and finding out the pixels which disappear in the corrosion process;
4) intercepting a lung nodule suspected region picture with a set size by taking the position of a disappeared pixel point as a center on an original CT image;
5) performing down-sampling processing on the lung nodule suspected region picture to obtain an image pyramid;
6) and (5) inputting the image pyramid in the step 5) into a trained classification model for classification, and performing fusion judgment, thereby completing the detection of the pulmonary nodules.
The second lung nodule detection method based on the CT image has the beneficial effects that: after obtaining an original CT image, firstly carrying out binarization processing, wherein the binarization processing is the basis of subsequent mathematical morphology processing, namely corrosion processing, and carrying out continuous n times of corrosion processing, wherein the most marginal pixel point of the image is eliminated each time through corrosion, and for a nodule area, the pixel point eliminated for the last time is necessarily the lung nodule central point, so that the pixel point which disappears in the corrosion process can be found out by carrying out XOR operation on the images subjected to adjacent two times of corrosion and convolution, the position of the disappeared pixel point is determined, the position of a suspected lung nodule area on the original CT image is further determined through the corrosion times and the number of layers of the pixel points subjected to each time of corrosion, finally, the suspected lung nodule area is intercepted, and is subjected to down-sampling processing to obtain a suspected image pyramid, and then the lung nodule area is classified in a classification model to determine whether the area is the lung nodule area or not, detection of lung nodules is completed. Before the lung nodule region is positioned, the suspected lung nodule region is firstly found out, and the suspected lung nodule region is subjected to down-sampling treatment, so that the multi-scale information of the suspected lung nodule region is obtained, the positioning detection accuracy is improved, the suspected lung nodule region is determined only by carrying out binaryzation, multiple corrosion and convolution operations on an original CT image, and the whole process is simple.
Further, in order to improve the detection accuracy of the lung nodule, the method for fusion judgment in step 6) includes: and inputting the image pyramid into a trained classification model to obtain the classification probability of each layer of image in the image pyramid, and fusing the obtained classification probabilities by using a DS evidence theory method to complete the detection of the lung nodule.
Further, in order to obtain a classification model, the training method of the classification model comprises: and manually segmenting the marked CT image, performing down-sampling processing on the segmented image to obtain an image pyramid data set, and training the image pyramid data set.
Further, in order to complete the etching operation, the structural element in step 2) is a cross-shaped structural element of 3 x 3, a diamond-shaped structural element, a spherical structural element, or a disc-shaped structural element.
Drawings
FIG. 1 is a schematic block diagram of an embodiment 1 of a CT image-based lung nodule detection method according to the present invention;
FIG. 2 is a schematic diagram of a suspected area detection algorithm of the present invention;
FIG. 3 is a schematic diagram of a CNN model training process;
fig. 4 is a schematic block diagram of an embodiment 2 of the method for detecting lung nodules based on CT images.
Detailed Description
Lung nodule detection method embodiment 1 based on CT image:
the lung nodule detection method based on the CT image has the main conception that based on the problem of large detection calculation amount of the existing suspected region, the method carries out binarization processing on an original CT image, continuously corrodes the binarized image for multiple times by using structural elements, carries out convolution operation on the corroded image after each corrosion operation to obtain multiple corroded and convolved images, carries out XOR operation on the adjacent corroded and convolved images to obtain pixel points which disappear in the corrosion process, and intercepts a picture with a set size on the original CT image by taking the positions of the disappeared pixel points as the center, wherein the picture is the suspected region picture of the lung nodule, the overall process is simple, and the identification efficiency of the suspected region is improved.
Specifically, as shown in fig. 1, the lung nodule detection method based on CT image includes the following steps:
1) original CT images of the lungs are acquired.
2) And (3) finding out a lung nodule suspected region picture (image) of the original CT image in the step 1) by a suspected region detection algorithm.
The suspected area detection algorithm is shown in fig. 2:
a. carrying out binarization operation on an original CT image;
binarization is to set the gray value of a pixel point on an image to be 0 or 255, i.e. to make the whole image show obvious black and white effect.
b. Continuously carrying out n times of corrosion operations (n is generally 3-10 times) on the binarized image by using structural elements, wherein the edge of 1 pixel can be eliminated by corrosion each time, and carrying out convolution operation after each time of corrosion operation to obtain a plurality of corroded and convoluted pictures (feature maps);
in the step b, the structural element is a cross-shaped structural element with the number 3 x 3, and the corrosion is a process of eliminating boundary points and enabling boundaries to shrink inwards, and can be used for eliminating small and meaningless targets. The specific process of corrosion is as follows: scanning each pixel in the binary image by using 3-by-3 cross-shaped structural elements, and performing AND operation on the cross-shaped structural elements and the binary image covered by the cross-shaped structural elements, wherein if the cross-shaped structural elements and the binary image are both 1, the pixel is 1; otherwise, the binary image is 0, and finally the binary image is reduced by one circle; and the purpose of the convolution operation is to extract image features and search for isolated pixel blocks;
c. performing exclusive or operation (exclusive or operation is to remove the same part in the two pictures and reserve different parts) on the pictures subjected to the two adjacent corrosion and convolution (for example, the picture subjected to the n-1 corrosion and convolution and the picture subjected to the n-1 corrosion and convolution), finding out a pixel point which disappears in the corrosion process, and intercepting a suspected Region (ROI) with a set size by taking the pixel point as a center;
for example, by using a 3 × 3 cross-shaped structural element, 1 layer of pixel points at the edge are etched each time, and the position of the suspected lung nodule region determined by the nth step is determined, and on the original CT image, a rectangular region with the pixel size (i.e., the set size) of (n × 1) × (n × 1) is cut out with the pixel point of the last etching as the center.
3) Inputting the picture of the suspected lung nodule area obtained in the step 2) into a trained classification model (CNN model), completing the classification of the picture, determining whether the suspected lung nodule area is the lung nodule area, and further realizing the detection of the suspected lung nodule area.
The training method of the classification model is shown in fig. 3:
a. acquiring a plurality of CT images, and labeling the CT images into a lung nodule region (namely a true nodule) and a non-lung nodule region (namely a false nodule);
b. and manually segmenting the labeled lung nodule region and the labeled non-lung nodule region to obtain a series of images of the lung nodule region and images of the non-lung nodule region, forming a training set after segmentation, and performing model training.
In the above embodiment, the structural element is a cross-shaped structural element of 3 × 3, and as another embodiment, the structural element may also be a diamond-shaped structural element, a spherical structural element, a disc-shaped structural element, and other shapes with other sizes, which is not limited in the present invention.
When the method is used for determining the suspected lung nodule area, binaryzation, multiple corrosion and convolution operations are only performed on the original CT image, the whole process is simple, the calculation resources are reduced, the consumption of the calculation resources is reduced, and the detection efficiency is improved.
Lung nodule detection method embodiment 2 based on CT image:
the lung nodule detection method based on the CT image in this embodiment is different from the lung nodule detection method based on the CT image in embodiment 1 in that, in this embodiment, a downsampling process is performed on a lung nodule suspected region picture when the picture is obtained, so as to obtain an image pyramid of the picture, meanwhile, the corresponding classification model is an image pyramid training model, the image pyramid of the lung nodule suspected region is input into the image pyramid training model, so as to complete classification detection, and the image pyramid can obtain multi-scale features of the image, so that the detection accuracy is further improved.
Specifically, as shown in fig. 4, the lung nodule detection method based on the CT image includes the following steps:
1) original CT images of the lungs are acquired.
2) And finding out a lung nodule suspected region picture of the original CT image in the step 1) by a suspected region detection algorithm.
The specific implementation process of step 2) is already described in embodiment 1 of the method for detecting lung nodules based on CT images, and is not described herein again.
3) And (3) performing down-sampling on the lung nodule suspected area picture obtained in the step (2) to obtain an image pyramid of the suspected area.
The image pyramid is a combination of a series of images with different sizes of the same picture, wherein the size of the image at the bottom is the largest, the size of the image at the top is the smallest, and the image pyramid looks like a pyramid when viewed from the top down in space. And (4) performing down-sampling on the image with the largest bottom size through filtering operation, such as Gaussian filtering, and processing to obtain an image pyramid.
4) Inputting the image pyramid of the suspected region into a trained classification model to obtain the classification probability of each layer of image in the image pyramid, fusing the obtained classification probabilities through a Dempster synthesis rule in a DS evidence theory method to obtain a final recognition probability, and determining whether the suspected region of the pulmonary nodule is the region of the pulmonary nodule to finish the detection of the pulmonary nodule.
The synthesis rule is as follows:
wherein A is1Taking the value of the layer 1 image; a. the2Taking the value of the layer 2 image; a. thenTaking the value of the nth layer image; the value can be a pulmonary nodule or a non-pulmonary nodule; m is1(A1) Is A of layer 1 image1A classification probability; m is2(A2) Is A of layer 2 image2A classification probability; m isn(An) Is A of the nth layer imagenA classification probability; n is the number of image pyramid layers;
the final recognition probability is obtained, and A is the lung nodule, and the final lung nodule recognition probability is obtained; when a is a non-lung nodule, the probability is identified for the final non-lung nodule.
The classification model is a CNN model of an image pyramid, and the training method comprises the following steps:
a. acquiring a plurality of 2D (two-dimensional) CT (computed tomography) images of the lung, labeling the CT images into a lung nodule region and a non-lung nodule region, and then manually segmenting the labeled lung nodule region and the non-lung nodule region to obtain a series of images of the lung nodule region and images of the non-lung nodule region;
b. each image in a series of images of lung nodule areas and images of non-lung nodule areas is subjected to down sampling to obtain a corresponding image pyramid, and multi-scale information of the images is obtained;
c. and (5) taking all the marked image pyramids as a training set to train a classification model.
The invention fully utilizes the multi-scale information of the CT image and improves the detection precision on the basis of improving the detection efficiency.
Claims (7)
1. A pulmonary nodule detection method based on CT images is characterized by comprising the following steps:
1) acquiring an original CT image, and binarizing the original CT image;
2) carrying out continuous n-time corrosion on the binarized image by using the structural elements, and carrying out convolution processing on the image subjected to corrosion each time;
3) carrying out exclusive OR operation on the images subjected to corrosion and convolution twice, and finding out the pixels which disappear in the corrosion process;
4) intercepting a lung nodule suspected region picture with a set size by taking the position of a disappeared pixel point as a center on an original CT image;
5) and inputting the lung nodule suspected region picture into a trained classification model for classification, and completing the detection of the lung nodule.
2. The CT-image-based pulmonary nodule detection method according to claim 1, wherein the training method of the classification model is as follows: and manually segmenting the marked CT image to obtain a data set, and training the data set.
3. The method for detecting lung nodules based on CT image according to claim 1 or 2, wherein the structural elements in step 2) are 3 x 3 cross structural elements, diamond structural elements, spherical structural elements, or disc structural elements.
4. A pulmonary nodule detection method based on CT images is characterized by comprising the following steps:
1) acquiring an original CT image, and binarizing the original CT image;
2) carrying out continuous n-time corrosion on the binarized image by using the structural elements, and carrying out convolution processing on the image subjected to corrosion each time;
3) carrying out exclusive OR operation on the images subjected to corrosion and convolution twice, and finding out the pixels which disappear in the corrosion process;
4) intercepting a lung nodule suspected region picture with a set size by taking the position of a disappeared pixel point as a center on an original CT image;
5) performing down-sampling processing on the lung nodule suspected region picture to obtain an image pyramid;
6) and (5) inputting the image pyramid in the step 5) into a trained classification model for classification, and performing fusion judgment, thereby completing the detection of the pulmonary nodules.
5. The CT-image-based pulmonary nodule detection method according to claim 4, wherein the fusion judgment in the step 6) comprises: and inputting the image pyramid into a trained classification model to obtain the classification probability of each layer of image in the image pyramid, and fusing the obtained classification probabilities by using a DS evidence theory method to complete the detection of the lung nodule.
6. The CT-image-based lung nodule detection method according to claim 4 or 5, wherein the training method of the classification model is as follows: and manually segmenting the marked CT image, performing down-sampling processing on the segmented image to obtain an image pyramid data set, and training the image pyramid data set.
7. The method for detecting lung nodules based on CT image according to claim 4 or 5, wherein the structural elements in step 2) are 3 x 3 cross structural elements, diamond structural elements, spherical structural elements, or disc structural elements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010609059.6A CN111815591B (en) | 2020-06-29 | 2020-06-29 | Lung nodule detection method based on CT image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010609059.6A CN111815591B (en) | 2020-06-29 | 2020-06-29 | Lung nodule detection method based on CT image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111815591A true CN111815591A (en) | 2020-10-23 |
| CN111815591B CN111815591B (en) | 2024-02-27 |
Family
ID=72856584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010609059.6A Active CN111815591B (en) | 2020-06-29 | 2020-06-29 | Lung nodule detection method based on CT image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815591B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177955A (en) * | 2021-05-10 | 2021-07-27 | 电子科技大学成都学院 | Lung cancer image lesion area dividing method based on improved image segmentation algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016665A (en) * | 2017-02-16 | 2017-08-04 | 浙江大学 | A kind of CT pulmonary nodule detection methods based on depth convolutional neural networks |
| CN108198179A (en) * | 2018-01-03 | 2018-06-22 | 华南理工大学 | A kind of CT medical image pulmonary nodule detection methods for generating confrontation network improvement |
| WO2019238104A1 (en) * | 2018-06-16 | 2019-12-19 | 深圳市前海安测信息技术有限公司 | Computer apparatus and method for implementing classification detection of pulmonary nodule images |
-
2020
- 2020-06-29 CN CN202010609059.6A patent/CN111815591B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016665A (en) * | 2017-02-16 | 2017-08-04 | 浙江大学 | A kind of CT pulmonary nodule detection methods based on depth convolutional neural networks |
| CN108198179A (en) * | 2018-01-03 | 2018-06-22 | 华南理工大学 | A kind of CT medical image pulmonary nodule detection methods for generating confrontation network improvement |
| WO2019238104A1 (en) * | 2018-06-16 | 2019-12-19 | 深圳市前海安测信息技术有限公司 | Computer apparatus and method for implementing classification detection of pulmonary nodule images |
Non-Patent Citations (2)
| Title |
|---|
| 郑光远;刘峡壁;韩光辉;: "医学影像计算机辅助检测与诊断系统综述", 软件学报, no. 05 * |
| 魏颖;徐心和;贾同;赵大哲;: "基于多尺度形态学滤波的CT图像疑似肺结节提取", 东北大学学报(自然科学版), no. 03 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113177955A (en) * | 2021-05-10 | 2021-07-27 | 电子科技大学成都学院 | Lung cancer image lesion area dividing method based on improved image segmentation algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111815591B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zebari et al. | Improved threshold based and trainable fully automated segmentation for breast cancer boundary and pectoral muscle in mammogram images | |
| Han et al. | A deep learning framework for supporting the classification of breast lesions in ultrasound images | |
| US10580137B2 (en) | Systems and methods for detecting an indication of malignancy in a sequence of anatomical images | |
| Al-Najdawi et al. | Mammogram image visual enhancement, mass segmentation and classification | |
| CN109685060B (en) | Image processing method and device | |
| CN109635846B (en) | Multi-type medical image judging method and system | |
| WO2022063198A1 (en) | Lung image processing method, apparatus and device | |
| Patil et al. | Cancer cells detection using digital image processing methods | |
| CN111369530B (en) | CT image pulmonary nodule rapid screening method based on deep learning | |
| Akram et al. | Intensity-based statistical features for classification of lungs CT scan nodules using artificial intelligence techniques | |
| Bandyopadhyay | Pre-processing of mammogram images | |
| CN110415208A (en) | A kind of adaptive targets detection method and its device, equipment, storage medium | |
| CN111415352B (en) | Cancer metastasis panoramic pathological section analysis method based on deep cascade network | |
| CN111539980B (en) | Multi-target tracking method based on visible light | |
| Sarwar et al. | Segmentation of cervical cells for automated screening of cervical cancer: a review | |
| Unni et al. | Tumour detection in double threshold segmented mammograms using optimized GLCM features fed SVM | |
| CN112700461A (en) | System for pulmonary nodule detection and characterization class identification | |
| Khordehchi et al. | Automatic lung nodule detection based on statistical region merging and support vector machines | |
| Fu et al. | Automatic detection of lung nodules using 3D deep convolutional neural networks | |
| CN111815591B (en) | Lung nodule detection method based on CT image | |
| CN116718599B (en) | Apparent crack length measurement method based on three-dimensional point cloud data | |
| US20020048402A1 (en) | Segmentation of digital images | |
| Rajkumar et al. | Automated mammogram segmentation using seed point identification and modified region growing algorithm | |
| CN117115117A (en) | Pathological image recognition method based on small sample, electronic equipment and storage medium | |
| Genc et al. | Automated abnormality classification of chest radiographs using MobileNetV2 |
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 |