WO2021164417A1 - 基于深度学习网络的三维影像的管状结构分割图断裂修复方法 - Google Patents

基于深度学习网络的三维影像的管状结构分割图断裂修复方法 Download PDF

Info

Publication number
WO2021164417A1
WO2021164417A1 PCT/CN2020/139468 CN2020139468W WO2021164417A1 WO 2021164417 A1 WO2021164417 A1 WO 2021164417A1 CN 2020139468 W CN2020139468 W CN 2020139468W WO 2021164417 A1 WO2021164417 A1 WO 2021164417A1
Authority
WO
WIPO (PCT)
Prior art keywords
deep learning
learning network
segmentation
map
dimensional image
Prior art date
Application number
PCT/CN2020/139468
Other languages
English (en)
French (fr)
Inventor
魏军
沈烁
赖耀明
谢培梁
蔡飞跃
Original Assignee
广州柏视医疗科技有限公司
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 广州柏视医疗科技有限公司 filed Critical 广州柏视医疗科技有限公司
Publication of WO2021164417A1 publication Critical patent/WO2021164417A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • 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
    • 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
    • G06T2207/10012Stereo images
    • 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
    • G06T2207/30101Blood vessel; Artery; Vein; Vascular

Definitions

  • the invention relates to the field of medical images, and in particular to a method for repairing a segmented map of a tubular structure of a three-dimensional image based on a deep learning network.
  • the embodiment of the present invention provides a method for repairing a segmented map of a tubular structure based on a deep learning network in a three-dimensional image.
  • an embodiment of the present invention provides a method for repairing a fracture of a segmented map of a tubular structure of a three-dimensional image based on a deep learning network, which includes the following steps:
  • Step S1 Collect three-dimensional image data and perform preprocessing
  • Step S2 Re-sampling the pre-processed 3D image data to generate multiple candidate 3D data of the region of interest;
  • Step S3 Input the three-dimensional data of all candidate sense regions into the target segmentation deep learning network to obtain a target organ segmentation map in each region of interest;
  • Step S4 Perform distance transformation on the target organ segmentation map to obtain a distance transformation map, and input the target organ segmentation map and the distance transformation map into the fracture repair deep learning network to obtain a fracture repair map for each region of interest, and then combine all the fracture repair maps Stitch the combined result to the complete target organ segmentation result.
  • the preprocessing of the three-dimensional image data in step S1 includes the following steps: pixel value normalization and interpolation.
  • c is the window level
  • w is the window width
  • x is the pixel value
  • the interpolation method is: first parse the original three-dimensional image, obtain the image Spacing attributes (z 0 , y 0 , x 0 ); among them, the target image Spacing is (z 1 , y 1 , x 1 ), and calculate the Scaling factor (z 0 /z 1 , y 0 /y 1 , x 0 /x 1 ), and then according to the scaling factor in each direction, bilinear interpolation is used to obtain the interpolated three-dimensional data.
  • step S2 the method of resampling in step S2 is: taking the interpolated three-dimensional data according to the step size of 32 ⁇ 48 ⁇ 48, and extracting the three-dimensional image of the local patches with the size of 64 ⁇ 96 ⁇ 96 and overlapping each other.
  • the target segmentation deep learning network uses the convolution residual block and downsampling alternately 4 times to extract high-dimensional features, and then alternately performs 4 times through the convolution residual block and upsampling to restore the resolution of the original input image Rate.
  • the feature map of the target segmentation deep learning network after upsampling is fused with the low-level feature map of the same resolution.
  • the target segmentation deep learning network uses up-sampling feature maps of target organs of different depths to perform feature fusion.
  • the fracture repair deep learning network uses the convolution residual block and downsampling alternately once to extract high-dimensional features, and then alternates the convolution residual block and upsampling once to restore the original input image resolution .
  • an embodiment of the present invention provides a three-dimensional image-based deep learning network-based pipe structure segmentation map fracture repair system, including:
  • Preprocessing module used to preprocess 3D image data
  • Image resampling module used to resample the preprocessed 3D image data to generate multiple candidate 3D data of the region of interest;
  • Target organ extraction module used to input the three-dimensional data of all candidate sense regions into the target segmentation deep learning network to obtain the target organ segmentation map in each region of interest;
  • Fracture repair module used to perform distance transformation on the target organ segmentation map to obtain the distance transformation map.
  • the target organ segmentation map and the distance transformation map are input into the fracture repair deep learning network to obtain the fracture repair map for each region of interest.
  • Fracture repair images are stitched together to complete the segmentation result of the target organ.
  • the embodiment of the present invention provides a method and system for repairing a fracture of a three-dimensional image of a tubular structure segmentation map based on a deep learning network, which has the following advantages: the method and system for repairing a fracture of a tubular structure segmentation of the three-dimensional image uses the distance transformation information of the fracture as The identification information of the fracture position can realize automatic fracture repair without detecting the fracture position in advance, which is simple and effective, and improves the segmentation effect.
  • FIG. 1 is a flowchart of a method for repairing a fracture of a tubular structure segmentation map of a three-dimensional image based on a deep learning network according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of the structure of a deep learning network for target segmentation in a method provided by an embodiment of the present invention
  • FIG. 3 is a schematic diagram of the structure of a fracture repair deep learning network in a method provided by an embodiment of the present invention
  • Fig. 4 is a schematic diagram of a fracture repair system for a tubular structure segmentation diagram of a three-dimensional image based on a deep learning network provided by an embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for repairing a fracture of a three-dimensional image of a tubular structure based on a deep learning network provided by an embodiment of the present invention. As shown in FIG. The method for repairing the structure segmentation diagram fracture includes the following steps:
  • Step S1 Collect three-dimensional image data and perform preprocessing
  • step S1 of the embodiment of the present invention the preprocessing of the three-dimensional image data includes the following steps: pixel value normalization and interpolation.
  • the method of pixel value normalization is:
  • c is the window level
  • w is the window width
  • x is the pixel value
  • the interpolation method is: first parse the original three-dimensional image, obtain the image Spacing attribute (z 0 , y 0 , x 0 ); among them, the target image Spacing is (z 1 , y 1 , x 1 ), and calculate the zoom factor ( z 0 /z 1 , y 0 /y 1 , x 0 /x 1 ), and then according to the scaling factors in each direction, bilinear interpolation is used to obtain interpolated three-dimensional data.
  • Step S2 Re-sampling the pre-processed 3D image data to generate multiple candidate 3D data of the region of interest;
  • the re-sampling method is: taking the interpolated three-dimensional data according to the step size of 32 ⁇ 48 ⁇ 48, and extracting the three-dimensional image of the local patch with the size of 64 ⁇ 96 ⁇ 96 and overlapping each other.
  • Step S3 Input the three-dimensional data of all candidate sense regions into the target segmentation deep learning network to obtain a target organ segmentation map in each region of interest;
  • Step S4 Perform distance transformation on the target organ segmentation map to obtain a distance transformation map, and input the target organ segmentation map and the distance transformation map into the fracture repair deep learning network to obtain a fracture repair map for each region of interest, and then combine all the fracture repair maps Stitch the combined result to the complete target organ segmentation result.
  • the deep learning network of the three-dimensional image arteriovenous segmentation method adopts the two-stage recognition of the target segmentation deep learning network and the fracture repair deep learning network, that is, first use the target segmentation deep learning network to extract the target organ to obtain the target organ segmentation map, and then The target organ segmentation map is transformed by distance to obtain the distance transformation map, and the target organ segmentation map and the distance transformation map are input into the fracture repair deep learning network for fracture repair.
  • the target segmentation deep learning network and the fracture repair deep learning network are both output probability maps.
  • the target segmentation deep learning network uses the convolution residual block and downsampling alternately 4 times to extract high-dimensional features, and then alternately performs 4 times through the convolution residual block and upsampling to restore to The resolution of the original input image.
  • the up-sampled feature map of the target segmentation deep learning network is merged with the low-level feature map of the same resolution.
  • the target segmentation deep learning network uses up-sampling for feature fusion of target organ feature maps of different depths.
  • the fracture repair deep learning network uses the convolution residual block and downsampling alternately once to extract high-dimensional features, and then alternates the convolution residual block and upsampling once to restore the original input image Resolution.
  • the fracture repair deep learning network uses dilated convolution in the 4th, 5th, 6th, 7th, and 8th residual blocks; and uses skip connections to supplement low-level Detailed information.
  • FIG. 4 is a schematic structural diagram of a pipe structure segmentation map fracture repair system based on a deep learning network based on a three-dimensional image of a deep learning network provided by an embodiment of the present invention, and the system includes:
  • Preprocessing module used to preprocess 3D image data
  • Image resampling module used to resample the preprocessed 3D image data to generate multiple candidate 3D data of the region of interest;
  • Target organ extraction module used to input the three-dimensional data of all candidate sense regions into the target segmentation deep learning network to obtain the target organ segmentation map in each region of interest;
  • Fracture repair module used to perform distance transformation on the target organ segmentation map to obtain the distance transformation map.
  • the target organ segmentation map and the distance transformation map are input into the fracture repair deep learning network to obtain the fracture repair map for each region of interest.
  • Fracture repair images are stitched together to complete the segmentation result of the target organ.
  • the method and system for repairing the fracture of a segmented map of a tubular structure based on a three-dimensional image of a deep learning network uses the distance transformation information of the fracture as the identification information of the fracture position, which can be realized without detecting the fracture position in advance. Automatic fracture repair, simple and effective, improves the segmentation effect.
  • the device embodiments described above are merely illustrative.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units.
  • Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement it without creative work.
  • each implementation manner can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware.
  • the above technical solution essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic A disc, an optical disc, etc., include several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical 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

一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法及系统,方法包括以下步骤:步骤S1:采集三维影像数据,并进行预处理;步骤S2:对预处理后的三维影像数据进行重采样,生成多个候选的感兴趣区域的三维数据;步骤S3:将所有候选感兴趣区域的三维数据输入目标分割深度学习网络,得到每一个感兴趣区域内的目标器官分割图;步骤S4:将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络,得到每一个感兴趣区域的断裂修复图,将所有的断裂修复图拼接组合在一起得到完整的目标器官分割结果。方法能够实现自动断裂修复,简单而有效,提高了分割效果。

Description

基于深度学习网络的三维影像的管状结构分割图断裂修复方法 技术领域
本发明涉及医疗图像领域,尤其涉及一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法。
背景技术
在正常人体解剖结构里,存在很多管状结构的器官,例如动脉、静脉、支气管、神经等等。在疾病的诊断与治疗过程中,这些器官重建非常重要,具有重要的临床价值。
目前针对不同的管状器官,在自动重建后的分割图像中,会出现噪声、断裂等异常情况,严重影响疾病的诊断与治疗。
公开于该背景技术部分的信息仅仅旨在增加对本实用新型的总体背景的理解,而不应当被视为承认或以任何形式暗示该信息构成已为本领域一般技术人员所公知的现有技术。
发明内容
针对现有技术存在的问题,本发明实施例提供一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法。
第一方面,本发明实施例提供一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法,包括以下步骤:
步骤S1:采集三维影像数据,并进行预处理;
步骤S2:对预处理后的三维影像数据进行重采样,生成多个候选的感兴趣区域的三维数据;
步骤S3:将所有候选感区域的三维数据输入目标分割深度学习网络,得到每一个感兴趣区域内的目标器官分割图;
步骤S4:将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络,得到每一个感兴趣区域的断裂修复图,将所有的断裂修复图拼接组合在一起的到完整的目标器官分割结果。
进一步地,步骤S1中对三维图像数据的预处理包括以下步骤:像素值规范化和插值。
进一步地,像素值规范化的方法为:
min=c-w/2
max=c+w/2
if x<min then x=0
if x>max then x=1
Figure PCTCN2020139468-appb-000001
其中c为窗位,w为窗宽,x为像素值。
进一步地,插值的方法为:先解析原始三维图像,获取图像Spacing属性(z 0,y 0,x 0);其中,目标图像Spacing为(z 1,y 1,x 1),计算各个方向的缩放因子(z 0/z 1,y 0/y 1,x 0/x 1),再根据各方向的缩放因子,利用双线性插值,得到插值后的三维数据。
进一步地,步骤S2中的重采样的方法为:将插值后的三维数据,按照步长为32×48×48,提取大小为64×96×96且有相互重叠的局部片块三维图像。
进一步地,目标分割深度学习网络利用卷积残差块和降采样交替进行4次,提取高维特征,然后再通过卷积残差块和上采样交替进行4次,恢复到原来输入图像的分辨率。
进一步地,目标分割深度学习网络在上采样后的特征图与低层次同分辨率的特征图进行融合。
进一步地,目标分割深度学习网络将不同深度的目标器官特征图利用上 采样进行特征融合。
进一步地,断裂修复深度学习网络利用卷积残差块和降采样交替进行1次,提取高维特征,然后再通过卷积残差块和上采样交替进行1次,恢复原来输入图像的分辨率。
第二方面,本发明实施例提供一种基于深度学习网络的三维影像的管状结构分割图断裂修复系统,包括:
预处理模块:用于对三维图像数据进行预处理;
图像重采样模块:用于对预处理后的三维影像数据进行重采样,生成多个候选的感兴趣区域的三维数据;
目标器官提取模块:用于将所有候选感区域的三维数据输入目标分割深度学习网络,得到每一个感兴趣区域内的目标器官分割图;
断裂修复模块:用于将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络,得到每一个感兴趣区域的断裂修复图,将所有的断裂修复图拼接组合在一起的到完整的目标器官分割结果。
本发明实施例提供的一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法及系统具有如下优点:该三维影像的管状结构分割图断裂修复方法及系统利用断裂处的距离变换信息作为断裂位置识别信息,无需事先检测断裂位置,即可实现自动断裂修复,简单而有效,提高了分割效果。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的基于深度学习网络的三维影像的管状结构分割图断裂修复方法流程图;
图2为本发明实施例提供的方法中目标分割深度学习网络结构示意图;
图3为本发明实施例提供的方法中断裂修复深度学习网络结构示意图;
图4本发明实施例提供的基于深度学习网络的三维影像的管状结构分割图断裂修复系统的原理图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
除非另有其它明确表示,否则在整个说明书和权利要求书中,术语“包括”或其变换如“包含”或“包括有”等等将被理解为包括所陈述的元件或组成部分,而并未排除其它元件或其它组成部分。
图1为本发明实施例提供的一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法流程图,如图1所示,本发明提出的一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法,包括下述步骤:
步骤S1:采集三维影像数据,并进行预处理;
本发明实施例的步骤S1中,对三维图像数据的预处理包括以下步骤:像素值规范化和插值。
其中,像素值规范化的方法为:
min=c-w/2
max=c+w/2
if x<min then x=0
if x>max then x=1
Figure PCTCN2020139468-appb-000002
其中c为窗位,w为窗宽,x为像素值。
插值的方法为:先解析原始三维图像,获取图像Spacing属性(z 0,y 0,x 0);其中,目标图像Spacing为(z 1,y 1,x 1),计算各个方向的缩放因子(z 0/z 1,y 0/y 1,x 0/x 1), 再根据各方向的缩放因子,利用双线性插值,得到插值后的三维数据。
步骤S2:对预处理后的三维影像数据进行重采样,生成多个候选的感兴趣区域的三维数据;
本发明实施例的步骤S2中,重采样方法为:将插值后的三维数据,按照步长为32×48×48,提取大小为64×96×96且有相互重叠的局部片块三维图像。
步骤S3:将所有候选感区域的三维数据输入目标分割深度学习网络,得到每一个感兴趣区域内的目标器官分割图;
步骤S4:将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络,得到每一个感兴趣区域的断裂修复图,将所有的断裂修复图拼接组合在一起的到完整的目标器官分割结果。
该三维影像动静脉分割方法的深度学习网络采用了目标分割深度学习网络与断裂修复深度学习网络的两阶段的识别,即先用目标分割深度学习网络进目标器官提取,得到目标器官分割图,再将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络进行断裂修复。
其中,目标分割深度学习网络与断裂修复深度学习网络都是输出概率图。
其中,如图2所示,目标分割深度学习网络利用卷积残差块和降采样交替进行4次,提取高维特征,然后再通过卷积残差块和上采样交替进行4次,恢复到原来输入图像的分辨率。
其中,为了能够补充低层次的与位置相关的信息,目标分割深度学习网络在上采样后的特征图与低层次同分辨率的特征图进行融合。
其中,为了加强不同尺寸的目标器官的关注,目标分割深度学习网络将不同深度的目标器官特征图利用上采样进行特征融合。
如图3所示,断裂修复深度学习网络利用卷积残差块和降采样交替进行1次,提取高维特征,然后再通过卷积残差块和上采样交替进行1次,恢复原来输入图像的分辨率。
其中,为了扩大感受野并捕抓多尺度特征,断裂修复深度学习网络在第4、5、6、7、8的残差块里,使用了dilated卷积;并利用skip connection,补充低层次的细节信息。
基于上述任一实施例,图4为本发明实施例提供的一种基于深度学习网络的三维影像的管状结构分割图断裂修复系统的结构示意图,该系统包括:
预处理模块:用于对三维图像数据进行预处理;
图像重采样模块:用于对预处理后的三维影像数据进行重采样,生成多个候选的感兴趣区域的三维数据;
目标器官提取模块:用于将所有候选感区域的三维数据输入目标分割深度学习网络,得到每一个感兴趣区域内的目标器官分割图;
断裂修复模块:用于将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络,得到每一个感兴趣区域的断裂修复图,将所有的断裂修复图拼接组合在一起的到完整的目标器官分割结果。
综上所述,本发明实施例提供的基于深度学习网络的三维影像的管状结构分割图断裂修复方法及系统利用断裂处的距离变换信息作为断裂位置识别信息,无需事先检测断裂位置,即可实现自动断裂修复,简单而有效,提高了分割效果。
以上所描述的装置实施例仅仅是示意性的,其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下,即可以理解并实施。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件。基于这样的理解,上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品可以存储在计算机可 读存储介质中,如ROM/RAM、磁碟、光盘等,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是:以上实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (5)

  1. 一种基于深度学习网络的三维影像的管状结构分割图断裂修复方法,其特征在于,包括以下步骤:
    步骤S1:采集三维影像数据,并进行预处理;
    步骤S2:对预处理后的三维影像数据进行重采样,生成多个候选的感兴趣区域的三维数据;
    步骤S3:将所有候选感区域的三维数据输入目标分割深度学习网络,得到每一个感兴趣区域内的目标器官分割图;所述目标分割深度学习网络利用卷积残差块和降采样交替进行4次,提取高维特征,然后再通过卷积残差块和上采样交替进行4次,恢复到原来输入图像的分辨率;所述目标分割深度学习网络在上采样后的特征图与低层次同分辨率的特征图进行融合;所述目标分割深度学习网络将不同深度的目标器官特征图利用上采样进行特征融合;
    步骤S4:将目标器官分割图进行距离变换得到距离变换图,将目标器官分割图与距离变换图一起输入断裂修复深度学习网络,得到每一个感兴趣区域的断裂修复图,将所有的断裂修复图拼接组合在一起的到完整的目标器官分割结果;所述断裂修复深度学习网络利用卷积残差块和降采样交替进行1次,提取高维特征,然后再通过卷积残差块和上采样交替进行1次,恢复原来输入图像的分辨率。
  2. 根据权利要求1所述的基于深度学习网络的三维影像的管状结构分割图断裂修复方法,其特征在于,所述步骤S1中对三维图像数据的预处理包括以下步骤:像素值规范化和插值。
  3. 根据权利要求2所述的基于深度学习网络的三维影像的管状结构分割图断裂修复方法,其特征在于,所述像素值规范化的方法为:
    min=c-w/2
    max=c+2/2
    if x<min then x=0
    if x>max then x=1
    Figure PCTCN2020139468-appb-100001
    其中c为窗位,w为窗宽,x为像素值。
  4. 根据权利要求3所述的基于深度学习网络的三维影像的管状结构分割图断裂修复方法,其特征在于,所述插值的方法为:先解析原始三维图像,获取图像Spacing属性(z 0,y 0,x 0);其中,目标图像Spacing为(z 1,y 1,x 1),计算各个方向的缩放因子(z 0/z 1,y 0/y 1,x 0/x 1),再根据各方向的缩放因子,利用双线性插值,得到插值后的三维数据。
  5. 根据权利要求4所述的基于深度学习网络的三维影像的管状结构分割图断裂修复方法,其特征在于,所述步骤S2中的重采样的方法为:将插值后的三维数据,按照步长为32×48×48,提取大小为64×96×96且有相互重叠的局部片块三维图像。
PCT/CN2020/139468 2020-02-18 2020-12-25 基于深度学习网络的三维影像的管状结构分割图断裂修复方法 WO2021164417A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010098343.1A CN111260670B (zh) 2020-02-18 2020-02-18 基于深度学习网络的三维影像的管状结构分割图断裂修复方法及系统
CN202010098343.1 2020-02-18

Publications (1)

Publication Number Publication Date
WO2021164417A1 true WO2021164417A1 (zh) 2021-08-26

Family

ID=70952766

Family Applications (2)

Application Number Title Priority Date Filing Date
PCT/CN2020/139471 WO2021164418A1 (zh) 2020-02-18 2020-12-25 基于深度学习网络的三维影像的管状结构分割图断裂修复系统
PCT/CN2020/139468 WO2021164417A1 (zh) 2020-02-18 2020-12-25 基于深度学习网络的三维影像的管状结构分割图断裂修复方法

Family Applications Before (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/139471 WO2021164418A1 (zh) 2020-02-18 2020-12-25 基于深度学习网络的三维影像的管状结构分割图断裂修复系统

Country Status (2)

Country Link
CN (2) CN112508969B (zh)
WO (2) WO2021164418A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112508969B (zh) * 2020-02-18 2021-12-07 广州柏视医疗科技有限公司 基于深度学习网络的三维影像的管状结构分割图断裂修复系统
CN113808146B (zh) * 2021-10-18 2023-08-18 山东大学 一种医学图像多器官分割方法及系统
CN114049359B (zh) * 2021-11-22 2024-04-16 北京航空航天大学 医学影像器官分割方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6785409B1 (en) * 2000-10-24 2004-08-31 Koninklijke Philips Electronics, N.V. Segmentation method and apparatus for medical images using diffusion propagation, pixel classification, and mathematical morphology
CN109583576A (zh) * 2018-12-17 2019-04-05 上海联影智能医疗科技有限公司 一种医学图像处理装置及方法
CN110458830A (zh) * 2019-03-08 2019-11-15 腾讯科技(深圳)有限公司 图像处理方法、装置、服务器及存储介质
CN110599465A (zh) * 2019-08-28 2019-12-20 上海联影智能医疗科技有限公司 图像定位方法、装置、计算机设备和存储介质
CN111260670A (zh) * 2020-02-18 2020-06-09 广州柏视医疗科技有限公司 基于深度学习网络的三维影像的管状结构分割图断裂修复方法及系统

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080159604A1 (en) * 2005-12-30 2008-07-03 Allan Wang Method and system for imaging to identify vascularization
CN103295195B (zh) * 2013-05-16 2017-07-07 深圳市旭东数字医学影像技术有限公司 低对比度图像的脉管增强的方法及其系统
CN106204733B (zh) * 2016-07-22 2024-04-19 青岛大学附属医院 肝脏和肾脏ct图像联合三维构建系统
JP7184489B2 (ja) * 2016-09-18 2022-12-06 イェダ リサーチ アンド ディベロップメント カンパニー リミテッド 蛍光照明に基づいて3d画像を生成するためのシステムおよび方法
KR101754291B1 (ko) * 2017-04-04 2017-07-06 이현섭 개인 맞춤형 뇌질병 진단 및 상태 판정을 위한 의료 영상 처리 시스템 및 방법
US10709399B2 (en) * 2017-11-30 2020-07-14 Shenzhen Keya Medical Technology Corporation Methods and devices for performing three-dimensional blood vessel reconstruction using angiographic images
US11335464B2 (en) * 2018-01-12 2022-05-17 Siemens Medical Solutions Usa, Inc. Integrated precision medicine by combining quantitative imaging techniques with quantitative genomics for improved decision making
CN109523507B (zh) * 2018-09-26 2023-09-19 苏州六莲科技有限公司 一种病变图像生成的方法、装置及计算机可读存储介质
CN109377458B (zh) * 2018-09-30 2020-06-12 数坤(北京)网络科技有限公司 一种冠脉分割断裂的修复方法及装置
CN109448005B (zh) * 2018-10-31 2019-12-27 数坤(北京)网络科技有限公司 一种用于冠状动脉的网络模型分割方法及设备
CN109903292A (zh) * 2019-01-24 2019-06-18 西安交通大学 一种基于全卷积神经网络的三维图像分割方法及系统
CN109785325A (zh) * 2019-01-30 2019-05-21 陕西中医药大学 一种基于深度学习的多模态医学影像的方法
CN109934816B (zh) * 2019-03-21 2021-05-11 数坤(北京)网络科技有限公司 一种互补模型的方法、设备及计算机可读存储介质
CN109961446B (zh) * 2019-03-27 2021-06-01 深圳视见医疗科技有限公司 Ct/mr三维图像分割处理方法、装置、设备及介质
CN110288524B (zh) * 2019-05-09 2020-10-30 广东启迪图卫科技股份有限公司 基于增强型上采样和辨别融合机制的深度学习超分辨率方法
CN110287956B (zh) * 2019-06-13 2021-05-25 北京理工大学 血管中心线自动匹配方法及装置
CN110765856B (zh) * 2019-09-12 2022-08-12 南京邮电大学 基于卷积的低质量手指静脉图像边缘检测算法
CN110570446A (zh) * 2019-09-20 2019-12-13 河南工业大学 一种基于生成对抗网络的眼底视网膜图像分割方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6785409B1 (en) * 2000-10-24 2004-08-31 Koninklijke Philips Electronics, N.V. Segmentation method and apparatus for medical images using diffusion propagation, pixel classification, and mathematical morphology
CN109583576A (zh) * 2018-12-17 2019-04-05 上海联影智能医疗科技有限公司 一种医学图像处理装置及方法
CN110458830A (zh) * 2019-03-08 2019-11-15 腾讯科技(深圳)有限公司 图像处理方法、装置、服务器及存储介质
CN110599465A (zh) * 2019-08-28 2019-12-20 上海联影智能医疗科技有限公司 图像定位方法、装置、计算机设备和存储介质
CN111260670A (zh) * 2020-02-18 2020-06-09 广州柏视医疗科技有限公司 基于深度学习网络的三维影像的管状结构分割图断裂修复方法及系统

Also Published As

Publication number Publication date
CN112508969B (zh) 2021-12-07
CN111260670A (zh) 2020-06-09
CN111260670B (zh) 2021-02-19
WO2021164418A1 (zh) 2021-08-26
CN112508969A (zh) 2021-03-16

Similar Documents

Publication Publication Date Title
WO2021164417A1 (zh) 基于深度学习网络的三维影像的管状结构分割图断裂修复方法
CN108765363B (zh) 一种基于人工智能的冠脉cta自动后处理系统
CN112950651B (zh) 基于深度学习网络的纵隔淋巴引流区的自动勾画方法
CN109584246B (zh) 基于多尺度特征金字塔的dcm心肌诊疗放射影像分割方法
WO2019200753A1 (zh) 病变监测方法、装置、计算机设备和存储介质
US8194936B2 (en) Optimal registration of multiple deformed images using a physical model of the imaging distortion
CN112862824A (zh) 新型冠状病毒肺炎病灶检测方法、系统、装置和存储介质
JP2023550844A (ja) 深層形状学習に基づく肝臓ct自動分割方法
WO2022237139A1 (zh) 一种基于LaneSegNet的车道线检测方法及系统
CN110110808B (zh) 一种对图像进行目标标注的方法、装置及计算机记录介质
JPWO2019167884A1 (ja) 機械学習方法及び装置、プログラム、学習済みモデル、並びに判別装置
CN109325915A (zh) 一种用于低分辨率监控视频的超分辨率重建方法
CN112381164B (zh) 一种基于多分支注意力机制的超声图像分类方法和装置
CN113223005B (zh) 一种甲状腺结节自动分割及分级的智能系统
CN113012155A (zh) 髋关节图像中骨骼分割方法、电子设备及存储介质
CN110008992B (zh) 一种用于前列腺癌辅助诊断的深度学习方法
US11830193B2 (en) Recognition method of intracranial vascular lesions based on transfer learning
CN112634196A (zh) 一种基于智慧医疗的医学图像分割与显示方法
CN113299363A (zh) 一种基于yolov5的皮肤科非处方药售药方法
CN112508873A (zh) 基于迁移学习的颅内血管模拟三维狭窄化模型的建立方法
Zheng et al. Multi-strategy mutual learning network for deformable medical image registration
CN117409002A (zh) 一种用于创伤的视觉识别检测系统及其检测方法
CN111325756A (zh) 基于深度学习网络的三维影像动静脉分割方法及系统
CN115937609A (zh) 基于局部和全局信息的角膜病图像检测分类方法及装置
CN111918611A (zh) 胸部x线图像的异常显示控制方法、异常显示控制程序、异常显示控制装置以及服务器装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20919525

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20919525

Country of ref document: EP

Kind code of ref document: A1