CN112950612A - Brain tumor image segmentation method based on convolutional neural network - Google Patents
Brain tumor image segmentation method based on convolutional neural network Download PDFInfo
- Publication number
- CN112950612A CN112950612A CN202110290515.XA CN202110290515A CN112950612A CN 112950612 A CN112950612 A CN 112950612A CN 202110290515 A CN202110290515 A CN 202110290515A CN 112950612 A CN112950612 A CN 112950612A
- Authority
- CN
- China
- Prior art keywords
- layer
- neural network
- brain
- convolutional neural
- convolution
- 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.)
- Pending
Links
- 208000003174 Brain Neoplasms Diseases 0.000 title claims abstract description 25
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000003709 image segmentation Methods 0.000 title claims abstract description 14
- 210000004556 brain Anatomy 0.000 claims abstract description 33
- 238000005070 sampling Methods 0.000 claims abstract description 22
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 230000004913 activation Effects 0.000 claims abstract description 6
- 238000012805 post-processing Methods 0.000 claims abstract description 6
- 238000010586 diagram Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims description 13
- JXSJBGJIGXNWCI-UHFFFAOYSA-N diethyl 2-[(dimethoxyphosphorothioyl)thio]succinate Chemical compound CCOC(=O)CC(SP(=S)(OC)OC)C(=O)OCC JXSJBGJIGXNWCI-UHFFFAOYSA-N 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 3
- 230000003902 lesion Effects 0.000 description 2
- 230000003211 malignant effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 208000028389 Nerve injury Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 210000005013 brain tissue Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 208000032839 leukemia Diseases 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008764 nerve damage Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- 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
- G06T2207/30016—Brain
-
- 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
- G06T2207/30096—Tumor; Lesion
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)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a brain tumor image segmentation method based on a convolutional neural network, which comprises the steps of firstly obtaining a 3D brain image, cutting a slice boundary of the 3D brain image, and identifying and deleting tumor-free slices to obtain a training set and a test set; and then training a convolutional neural network model by using the training set obtained by processing, wherein the convolutional neural network model is based on a Unet network and comprises a layer, a down-sampling stage, an up-sampling stage and an activation layer, wherein the layer comprises a parallel deep convolutional path and a standard convolutional path, finally processing the test set by using the trained convolutional neural network model, and inputting the obtained characteristic diagram into a post-processing module for detection to obtain a brain tumor image segmentation result. On the premise of ensuring the precision of brain tumor segmentation, the invention reduces the calculation amount of a convolutional neural network system by means of pretreatment, network structure optimization and the like.
Description
Technical Field
The invention belongs to the field of medical image processing, and particularly relates to a brain tumor image segmentation method based on a convolutional neural network.
Background
Brain tumors pose a serious problem to human health, especially in malignant lesions that children are susceptible to, next to leukemia. For brain tumors, whether benign or malignant in form, the intracranial pressure is elevated, and brain tissue is compressed, which leads to central nerve damage and endangers patient life.
The localization and quantitative calculation (such as calculating the volume and diameter of the tumor) of the brain tumor lesion tissue are very important for the diagnosis, treatment plan formulation, efficacy monitoring and the like of the brain tumor, so the brain tumor automatic segmentation technology has very important significance for the auxiliary treatment of the brain tumor.
In the prior art, the magnetic resonance brain tumor segmentation method is mainly applied to model and method construction in the fields of image processing, computer graphics, traditional artificial intelligence and the like, and mainly comprises a threshold-based method, a region-based method and the like. Then, although the existing brain tumor segmentation method guarantees the accuracy of brain tumor segmentation, it needs more computing resources.
Disclosure of Invention
In order to solve the above problems in the prior art, the invention provides a brain tumor image segmentation method based on a convolutional neural network, which greatly reduces the calculation amount of a convolutional neural network system on the premise of ensuring that the brain tumor image segmentation of a brain image keeps certain precision. The technical scheme of the invention is as follows:
a method for brain tumor image segmentation based on a convolutional neural network, the method comprising:
s1, acquiring a 3D brain image, and preprocessing the 3D brain image to obtain a training set and a test set; the preprocessing operation comprises the steps of cutting slice boundaries of acquired 3D brain image slices of four modalities of FLAIR, T1, T1c and T2 and identifying and deleting tumor-free slices;
s2, training the convolutional neural network model by using the training set obtained by preprocessing;
the convolutional neural network model is based on a Unet network and comprises a layer, a down-sampling stage, an up-sampling stage and an activation layer:
the normalization layer normalizes the preprocessed 3D brain image slices in four modes, and inputs the normalized brain image slices into a down-sampling stage;
the down-sampling stage comprises 4 convolutional layers, wherein the layers 1 and 2 comprise parallel deep convolution paths and standard convolution paths; layer 3 performs a convolution operation on the combination of the two paths; the 4 th layer performs convolution on the result of the 3 rd layer and then performs up-sampling, and the two adjacent down-sampling layers perform maximum pooling operation;
the up-sampling stage comprises 3 deconvolution layers, wherein the input of the 2 nd deconvolution layer comprises the output of the 1 st deconvolution layer and the output weighted concatenation of the deep convolution path and the standard convolution path in the 2 nd convolution layer in the down-sampling stage; the input of the 3 rd deconvolution layer comprises the weighted splicing of the output of the 2 nd deconvolution layer and the outputs of the deep convolution path and the standard convolution path in the 1 st convolution layer in the downsampling stage;
the activation layer activates the output of the up-sampling stage by using a softmax function;
s3, inputting the test set data obtained by preprocessing into a trained convolutional neural network model, and inputting the obtained characteristic diagram into a post-processing module for detection to obtain a brain tumor image segmentation result after detection; the post-processing module includes determining false positive slices based on the number of consecutive tumor slices in the feature map.
Further, the 3D brain image slices of the four modalities, namely FLAIR, T1, T1c and T2, are the same in size after preprocessing operation.
The invention has the beneficial effects that: on the premise of ensuring that the brain tumor image segmentation of the brain image keeps certain precision, the calculation amount of a convolutional neural network system is greatly reduced by means of pretreatment, network structure optimization and the like.
Drawings
FIG. 1 is a flow chart of a method for segmenting a brain tumor image according to the present invention;
FIG. 2 is a diagram of a convolutional neural network model architecture of the present invention.
Detailed Description
The technical scheme of the invention is further described by combining the drawings and the embodiment:
the embodiment provides a brain tumor image segmentation method based on a convolutional neural network, as shown in fig. 1, including:
step 1, acquiring 3D brain images, each patient in this embodiment including 3D brain images of four modalities, FLAIR, T1, T1c and T2, each 3D image having a size of 240 × 240 × 155.
After the 3D brain image is acquired, boundary clipping in preprocessing operation, i.e. detection and removal of redundant edges, is performed first: in each slice of the 3D brain image, because each side is provided with a very wide boundary, and the brain area only occupies a small part of the space, all slices are cut by detecting the distance between the upper vertex, the lower vertex, the left vertex and the right vertex of the brain area in the brain image slice and according to the minimum four boundary distances in all the detected slices, the maximum cutting is realized under the condition of ensuring the integrity of the brain area, and the size of the slice after removing redundant edges is 168 multiplied by 200 pixels;
then, the detection and removal of the tumor-free section in the pretreatment operation are carried out, and the method specifically comprises 3 detection means:
(1) in each 3D image slice sequence, the slices at the two ends of the sequence rarely have tumor areas, and the tumor-free slices are determined by background pixels;
(2) the healthy brain has the characteristic of bilateral symmetry, which is reflected as vertical symmetry in a brain image, and the tumor-free section is determined by detecting the high vertical symmetry of pixel data in a brain region;
(3) because the brain image slices with incomplete display are acquired with a certain probability in the acquisition process, because the slices are positioned in the region where the tumor is difficult to find and the data is incomplete, the data of the slices are removed, and the slices have the characteristic that the upper half part and the lower half part of the brain contour are obviously asymmetrical, so the slices are identified by calculating the symmetry of the contour.
In this embodiment, Structural Similarity (SSIM) is used to evaluate the asymmetry of the images, 13 to 43 tumor-free slices are detected in each modality according to the 3-clock method, and the identified brain image slices are deleted, so that the reduction of the data volume by more than 50% can be realized by detecting and deleting redundant edges and tumor-free slices in the preprocessing; and dividing the valid data into a training set and a testing set.
Step 2, training a convolutional neural network model by using the obtained training set; as shown in fig. 2, the convolutional neural network model is based on the Unet network, and includes a layer classification, a downsampling stage, an upsampling stage, and an activation layer:
determining that the 3D brain images of the four modes including FLAIR, T1, T1c and T2 are different region emphasis points, performing channel dimension normalization on preprocessed 3D brain image slices of the four modes by a normalization layer, and inputting image slices with the resolution of 168 x 200 into a down-sampling stage;
the downsampling stage comprises 4 convolutional layers, wherein the 1 st and 2 nd layers comprise parallel deep convolutional paths and standard convolutional paths, wherein the deep convolutional paths comprise four 3 x 3 kernels, and each of the four kernels is applied to each 2D slice to generate a 2D feature map of a specific feature, the 3 rd layer performs a convolution operation on the combination of the two paths, the first 3 convolutional layers perform feature extraction, the 4 th layer detects a tumor region, and the two adjacent downsampling layers perform a maximum pooling operation; .
Reducing the size of the feature map to the size of an input slice through an upsampling stage, wherein the upsampling stage comprises 3 deconvolution layers (convolution layers 5, 6 and 7), a deep convolution path and a standard convolution path in the downsampling stage are spliced to the deconvolution layers through trainable coefficient weighting, so that feature data of a tumor region is enhanced, and the input of a specific 2 nd deconvolution layer comprises the output of a 1 st deconvolution layer and the output of the deep convolution path and the standard convolution path in a 2 nd convolution layer in the downsampling stage; the input of the 3 rd deconvolution layer comprises the output of the 2 nd deconvolution layer and the output weighted concatenation of the deep convolution path and the standard convolution path in the 1 st convolution layer in the downsampling stage.
Finally, activating the output of the up-sampling stage by using a softmax function; in this embodiment, the batch size of the model training is selected to be 100, the training is completed after 50 periods, the loss function is selected to be the cross entropy, the optimizer is selected to be Adam (adaptive moment estimation), and the initial learning rate is selected to be 0.1.
And 3, inputting the test set data obtained by preprocessing into a trained convolutional neural network model, inputting the obtained characteristic diagram into a post-processing module for detection, setting a tumor area to exist in at least 6 continuous slices as the thickness of the detectable tumor is at least 1/20 of the diameter of the brain, setting the tumor area to exist in less than 6 continuous slices, regarding the tumor area as a non-tumor pixel, regarding the slice with the non-tumor pixel as a false positive slice, and outputting the brain tumor image segmentation result of finally removing the false positive slice.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the above teachings, and that all such modifications and variations are intended to be within the scope of the invention as defined in the appended claims.
Claims (2)
1. A brain tumor image segmentation method based on a convolutional neural network is characterized by comprising the following steps:
s1, acquiring a 3D brain image, and preprocessing the 3D brain image to obtain a training set and a test set; the preprocessing operation comprises the steps of cutting slice boundaries of acquired 3D brain image slices of four modalities of FLAIR, T1, T1c and T2 and identifying and deleting tumor-free slices;
s2, training the convolutional neural network model by using the training set obtained by preprocessing;
the convolutional neural network model is based on a Unet network and comprises a layer, a down-sampling stage, an up-sampling stage and an activation layer:
the normalization layer is used for carrying out channel dimension normalization on the preprocessed 3D brain image slices in four modes and inputting the normalized brain image slices into a down-sampling stage;
the down-sampling stage comprises 4 convolutional layers, wherein the layers 1 and 2 comprise parallel deep convolution paths and standard convolution paths; layer 3 performs a convolution operation on the combination of the two paths; the 4 th layer performs convolution on the result of the 3 rd layer and then performs up-sampling, and the two adjacent down-sampling layers perform maximum pooling operation;
the up-sampling stage comprises 3 deconvolution layers, wherein the input of the 2 nd deconvolution layer comprises the output of the 1 st deconvolution layer and the output weighted concatenation of the deep convolution path and the standard convolution path in the 2 nd convolution layer in the down-sampling stage; the input of the 3 rd deconvolution layer comprises the weighted splicing of the output of the 2 nd deconvolution layer and the outputs of the deep convolution path and the standard convolution path in the 1 st convolution layer in the downsampling stage;
the activation layer activates the output of the up-sampling stage by using a softmax function;
s3, inputting the test set data obtained by preprocessing into a trained convolutional neural network model, and inputting the obtained characteristic diagram into a post-processing module for detection to obtain a brain tumor image segmentation result after detection; the post-processing module includes determining false positive slices based on the number of consecutive tumor slices in the feature map.
2. The method according to claim 1, wherein the 3D brain image slices of the four modalities FLAIR, T1, T1c and T2 are the same size after the preprocessing operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110290515.XA CN112950612A (en) | 2021-03-18 | 2021-03-18 | Brain tumor image segmentation method based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110290515.XA CN112950612A (en) | 2021-03-18 | 2021-03-18 | Brain tumor image segmentation method based on convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112950612A true CN112950612A (en) | 2021-06-11 |
Family
ID=76226568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110290515.XA Pending CN112950612A (en) | 2021-03-18 | 2021-03-18 | Brain tumor image segmentation method based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950612A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114972249A (en) * | 2022-05-24 | 2022-08-30 | 广州市华奕电子科技有限公司 | Liver tumor segmentation method based on lightweight convolutional neural network |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018082084A1 (en) * | 2016-11-07 | 2018-05-11 | 中国科学院自动化研究所 | Brain tumor automatic segmentation method by means of fusion of full convolutional neural network and conditional random field |
| US20190122074A1 (en) * | 2017-10-19 | 2019-04-25 | General Electric Company | Deep learning architecture for automated image feature extraction |
| CN109872328A (en) * | 2019-01-25 | 2019-06-11 | 腾讯科技（深圳）有限公司 | A kind of brain image dividing method, device and storage medium |
| CN110120048A (en) * | 2019-04-12 | 2019-08-13 | 天津大学 | In conjunction with the three-dimensional brain tumor image partition method for improving U-Net and CMF |
| CN110120033A (en) * | 2019-04-12 | 2019-08-13 | 天津大学 | Based on improved U-Net neural network three-dimensional brain tumor image partition method |
| CN110264476A (en) * | 2019-06-19 | 2019-09-20 | 东北大学 | A kind of multiple dimensioned serial convolution deep learning microscopic image segmentation |
| CN110570431A (en) * | 2019-09-18 | 2019-12-13 | 东北大学 | Medical image segmentation method based on improved convolutional neural network |
| CN110738660A (en) * | 2019-09-09 | 2020-01-31 | 五邑大学 | Spine CT image segmentation method and device based on improved U-net |
| CN111192245A (en) * | 2019-12-26 | 2020-05-22 | 河南工业大学 | Brain tumor segmentation network and method based on U-Net network |
| US20200311914A1 (en) * | 2017-04-25 | 2020-10-01 | The Board Of Trustees Of Leland Stanford University | Dose reduction for medical imaging using deep convolutional neural networks |
| CN112085162A (en) * | 2020-08-12 | 2020-12-15 | 北京师范大学 | Magnetic resonance brain tissue segmentation method and device based on neural network, computing equipment and storage medium |
| CN112164082A (en) * | 2020-10-09 | 2021-01-01 | 深圳市铱硙医疗科技有限公司 | Method for segmenting multi-modal MR brain image based on 3D convolutional neural network |
-
2021
- 2021-03-18 CN CN202110290515.XA patent/CN112950612A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018082084A1 (en) * | 2016-11-07 | 2018-05-11 | 中国科学院自动化研究所 | Brain tumor automatic segmentation method by means of fusion of full convolutional neural network and conditional random field |
| US20200311914A1 (en) * | 2017-04-25 | 2020-10-01 | The Board Of Trustees Of Leland Stanford University | Dose reduction for medical imaging using deep convolutional neural networks |
| US20190122074A1 (en) * | 2017-10-19 | 2019-04-25 | General Electric Company | Deep learning architecture for automated image feature extraction |
| CN109872328A (en) * | 2019-01-25 | 2019-06-11 | 腾讯科技（深圳）有限公司 | A kind of brain image dividing method, device and storage medium |
| CN110120048A (en) * | 2019-04-12 | 2019-08-13 | 天津大学 | In conjunction with the three-dimensional brain tumor image partition method for improving U-Net and CMF |
| CN110120033A (en) * | 2019-04-12 | 2019-08-13 | 天津大学 | Based on improved U-Net neural network three-dimensional brain tumor image partition method |
| CN110264476A (en) * | 2019-06-19 | 2019-09-20 | 东北大学 | A kind of multiple dimensioned serial convolution deep learning microscopic image segmentation |
| CN110738660A (en) * | 2019-09-09 | 2020-01-31 | 五邑大学 | Spine CT image segmentation method and device based on improved U-net |
| CN110570431A (en) * | 2019-09-18 | 2019-12-13 | 东北大学 | Medical image segmentation method based on improved convolutional neural network |
| CN111192245A (en) * | 2019-12-26 | 2020-05-22 | 河南工业大学 | Brain tumor segmentation network and method based on U-Net network |
| CN112085162A (en) * | 2020-08-12 | 2020-12-15 | 北京师范大学 | Magnetic resonance brain tissue segmentation method and device based on neural network, computing equipment and storage medium |
| CN112164082A (en) * | 2020-10-09 | 2021-01-01 | 深圳市铱硙医疗科技有限公司 | Method for segmenting multi-modal MR brain image based on 3D convolutional neural network |
Non-Patent Citations (3)
| Title |
|---|
| CHEN CHEN ET AL: "3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI", 《ARXIV》 * |
| 邢波涛等: "改进的全卷积神经网络的脑肿瘤图像分割", 《信号处理》 * |
| 韩文忠等: "深度全卷积网络对MRI膀胱图像的分割", 《信号处理》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114972249A (en) * | 2022-05-24 | 2022-08-30 | 广州市华奕电子科技有限公司 | Liver tumor segmentation method based on lightweight convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410219B (en) | Image segmentation method and device based on pyramid fusion learning and computer readable storage medium | |
| CN111798462B (en) | Automatic delineation method of nasopharyngeal carcinoma radiotherapy target area based on CT image | |
| CN108053417B (en) | lung segmentation device of 3D U-Net network based on mixed rough segmentation characteristics | |
| CN112150428A (en) | Medical image segmentation method based on deep learning | |
| CN110751636B (en) | Fundus image retinal arteriosclerosis detection method based on improved coding and decoding network | |
| CN110910405A (en) | Brain tumor segmentation method and system based on multi-scale cavity convolutional neural network | |
| CN115496771A (en) | Brain tumor segmentation method based on brain three-dimensional MRI image design | |
| CN104268873A (en) | Breast tumor partition method based on nuclear magnetic resonance images | |
| CN113223005B (en) | Thyroid nodule automatic segmentation and grading intelligent system | |
| CN111784701A (en) | Ultrasonic image segmentation method and system combining boundary feature enhancement and multi-scale information | |
| Ramya et al. | A robust segmentation algorithm using morphological operators for detection of tumor in MRI | |
| CN113223015A (en) | Vascular wall image segmentation method, device, computer equipment and storage medium | |
| Feng et al. | Automatic localization and segmentation of focal cortical dysplasia in FLAIR‐negative patients using a convolutional neural network | |
| CN116188485A (en) | Image processing method, device, computer equipment and storage medium | |
| Tong et al. | A dual tri-path CNN system for brain tumor segmentation | |
| CN112950612A (en) | Brain tumor image segmentation method based on convolutional neural network | |
| CN114066911A (en) | BPE automatic extraction method and system based on breast and tumor segmentation | |
| Najjar et al. | Histogram features extraction for edge detection approach | |
| CN116403211B (en) | Segmentation and clustering method and system based on single-cell pathology image cell nuclei | |
| Nguyen et al. | ROI-based features for classification of skin diseases using a multi-layer neural network | |
| CN116958705A (en) | Medical image classifying system based on graph neural network | |
| CN114693622B (en) | Plaque erosion automatic detection system based on artificial intelligence | |
| CN116206160A (en) | Automatic identification network model and automatic sketching network model construction method for nasopharyngeal carcinoma lesion tissues based on convolutional neural network model | |
| CN115841472A (en) | Method, device, equipment and storage medium for identifying high-density characteristics of middle cerebral artery | |
| Imtiaz et al. | Segmentation of skin lesion using harris corner detection and region growing |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210611 |
|
| WD01 | Invention patent application deemed withdrawn after publication |