三维体图像处理

对三维体数据进行滤波、分割和执行其他图像处理运算

对三维数据集执行像素运算、局部滤波、形态学及其他图像处理。

App

三维体查看器	查看三维体数据和已标注的三维体数据
三维体分割器	Segment 3-D grayscale or RGB volumetric images (自 R2020b 起)

函数

全部展开

三维体显示

`volshow`	Display volume
`sliceViewer`	Browse image slices (自 R2019b 起)
`orthosliceViewer`	Browse orthogonal slices in grayscale or RGB volume (自 R2019b 起)
`obliqueslice`	Extract oblique slice from 3-D volumetric data (自 R2020a 起)
`viewer3d`	Create 3-D viewer object (自 R2022b 起)
`Surface`	Display surface in 3-D viewer (自 R2022b 起)
`Light`	Light source (自 R2023b 起)
`Point`	Point annotation (自 R2024a 起)
`Line`	Line annotation (自 R2024a 起)

图像导入和转换

`adaptthresh`	使用局部一阶统计量的自适应图像阈值
`blockedImage`	Big or multiresolution image made from discrete blocks (自 R2021a 起)
`dicomread`	读取 DICOM 图像
`dicomreadVolume`	Create 4-D volume from set of DICOM images
`dicomContours`	Extract ROI data from DICOM-RT structure set (自 R2020a 起)
`imbinarize`	通过阈值化将二维灰度图像或三维体二值化
`niftiinfo`	Read metadata from NIfTI file
`niftiwrite`	Write volume to file using NIfTI format
`niftiread`	Read NIfTI image
`tiffreadVolume`	Read volume or time series image stack from TIFF file (自 R2020b 起)

图像算术

`imabsdiff`	两个图像的绝对差
`imadd`	将两个图像相加或在图像中添加常量
`imdivide`	将一个图像除以另一个图像或用常量除以图像
`immultiply`	将两个图像相乘或者将图像乘以常量
`imsubtract`	从一个图像中减去另一个图像或从图像中减去常量

几何变换和图像配准

`affineOutputView`	Create output view for warping images (自 R2019b 起)
`affinetform3d`	3-D affine geometric transformation (自 R2022b 起)
`imcrop3`	Crop 3-D image (自 R2019b 起)
`imref3d`	Reference 3-D image to world coordinates
`imregister`	Intensity-based image registration
`imregdemons`	Estimate displacement field that aligns two 2-D or 3-D images
`imresize3`	Resize 3-D volumetric intensity image
`imrotate3`	Rotate 3-D volumetric grayscale image
`imwarp`	对图像应用几何变换
`rigidtform3d`	3-D rigid geometric transformation (自 R2022b 起)
`simtform3d`	3-D similarity geometric transformation (自 R2022b 起)
`transltform3d`	3-D translation geometric transformation (自 R2022b 起)
`transformPointsForward`	Apply forward geometric transformation
`transformPointsInverse`	Apply inverse geometric transformation

图像滤波和增强

`fibermetric`	Enhance elongated or tubular structures in image using Frangi vesselness filter
`fspecial3`	Create predefined 3-D filter
`histeq`	使用直方图均衡增强对比度
`imadjustn`	Adjust intensity values in N-D volumetric image
`imboxfilt3`	3-D box filtering of 3-D images
`imfilter`	多维图像的 N 维滤波
`imgaussfilt3`	三维图像的三维高斯滤波
`imhistmatchn`	Adjust histogram of N-D image to match histogram of reference image
`imnoise`	向图像添加噪声
`integralBoxFilter3`	3-D box filtering of 3-D integral images
`integralImage3`	Calculate 3-D integral image
`medfilt3`	三维中位数滤波

形态学

`bwareaopen`	从二值图像中删除小对象
`bwconncomp`	查找二值图像中的连通分量并对其计数
`bwmorph3`	Morphological operations on binary volume
`bwskel`	Reduce all objects to lines in 2-D binary image or 3-D binary volume
`imbothat`	底帽滤波
`imclose`	对图像执行形态学闭运算
`imdilate`	膨胀图像
`imerode`	腐蚀图像
`imopen`	对图像执行形态学开运算
`imreconstruct`	Morphological reconstruction
`imregionalmax`	区域最大值
`imregionalmin`	区域最小值
`imtophat`	顶帽滤波
`offsetstrel`	Morphological offset structuring element
`strel`	形态学结构元素
`watershed`	分水岭变换

图像分割

`activecontour`	使用主动轮廓 (snake) 区域增长方法将图像分割成前景和背景
`bfscore`	Contour matching score for image segmentation
`dice`	Sørensen-Dice similarity coefficient for image segmentation
`gradientweight`	Calculate weights for image pixels based on image gradient
`graydiffweight`	Calculate weights for image pixels based on grayscale intensity difference
`imsegfmm`	Binary image segmentation using fast marching method
`imsegkmeans3`	K-means clustering based volume segmentation
`jaccard`	Jaccard similarity coefficient for image segmentation
`superpixels3`	3-D superpixel oversegmentation of 3-D image

图像分析

`bwselect3`	Select objects in binary volume
`edge3`	Find edges in 3-D grayscale volume
`imgradient3`	Find gradient magnitude and direction of 3-D image
`imgradientxyz`	Find directional gradients of 3-D image
`imhist`	图像数据的直方图
`regionprops3`	Measure properties of 3-D volumetric image regions

增强图像以进行深度学习

`blockedImageDatastore`	Datastore for use with blocks from `blockedImage` objects (自 R2021a 起)
`centerCropWindow3d`	Create cuboidal center cropping window (自 R2019b 起)
`randomCropWindow3d`	Create randomized cuboidal cropping window (自 R2019b 起)
`randomAffine3d`	Create randomized 3-D affine transformation (自 R2019b 起)
`randomPatchExtractionDatastore`	Datastore for extracting random 2-D or 3-D random patches from images or pixel label images

主题

显示三维体

Explore 3-D Volumetric Data with Volume Viewer App
View perpendicular cross-sections of 3-D volumetric data and adjust the rendering to reveal structures within the volume.
Explore 3-D Labeled Volumetric Data with Volume Viewer
View 3-D labeled volumetric data, and adjust the visualization such as the opacity and colormap, using the Volume Viewer app.
Display Interior Labels by Clipping Volume Planes
Interactively clip a quadrant of a volumetric image to expose a surface within the volume.
Display Interior Labels by Adjusting Volume Overlay Properties
Adjust the transparency of labeled volumetric data and the rendering style to reveal labels on the interior of the volume.
Display Volume Using Cinematic Rendering
View volumes with photorealistic lighting and shadows using cinematic rendering.
Display Translucent Volume with Advanced Light Scattering
This example shows how to display translucent volumes using realistic light scattering.
Remove Objects from Volume Display Using 3-D Scissors
This example shows how to interactively remove unwanted regions in a 3-D display, such as a patient bed in a CT scan, by using 3-D scissors.
Display Large 3-D Images Using Blocked Volume Visualization
This example shows how to display large 3-D image volumes using a blockedImage object and the volshow function.
探查来自具有各向异性体素间距的三维图像体的切片
显示一个三维图像体的切片，其体素间距在空间维度之间变化。

处理和分析三维体

Create Binary Mask Using Volume Segmenter
This example shows how to segment a volume in the Volume Segmenter app.
Work with Blocked Images Using Volume Segmenter
Segment a volumetric image that could be too large to fit into memory by converting the volume to a blocked image.
Compute 3-D Superpixels of Input Volumetric Intensity Image
Convert 3-D MRI data into a grayscale intensity image of superpixels.
Preprocess Volumes for Deep Learning (Deep Learning Toolbox)
Read and preprocess volumetric image and label data for 3-D deep learning.