Main Content

Segmentation and Analysis

Medical image segmentation using deep learning, labeling app, or image processing algorithms, and radiomics analysis

Image segmentation is the process of partitioning an image into regions. Semantic segmentation associates each pixel or voxel in an image with a class label that describes the meaning of an image region, such as bone, tumor, or background. You can perform medical image semantic segmentation using deep learning, the interactive Medical Image Labeler app, or image processing algorithms. Deep learning workflows require Deep Learning Toolbox™ and Computer Vision Toolbox™. Analyze segmented images using radiomics, which calculates standardized image features related to shape, intensity, and texture.


Medical Image LabelerInteractively explore, label, and publish animations of 2-D or 3-D medical image data (Since R2022b)


expand all

imbinarizeBinarize 2-D grayscale image or 3-D volume by thresholding
graythreshGlobal image threshold using Otsu's method
multithreshMultilevel image thresholds using Otsu’s method
otsuthreshGlobal histogram threshold using Otsu's method
adaptthreshAdaptive image threshold using local first-order statistics
grayconnectedSelect contiguous image region with similar gray values using flood-fill technique
watershedWatershed transform
activecontourSegment image into foreground and background using active contours (snakes) region growing technique
imsegfmmBinary image segmentation using fast marching method
gradientweightCalculate weights for image pixels based on image gradient
graydiffweightCalculate weights for image pixels based on grayscale intensity difference
imsegkmeansK-means clustering based image segmentation
imsegkmeans3K-means clustering based volume segmentation
superpixels2-D superpixel oversegmentation of images
superpixels33-D superpixel oversegmentation of 3-D image

Load and Prepare Training Data

groundTruthMedicalGround truth label data for medical images (Since R2022b)
changeFilePathsChange file paths in ground truth data for medical images (Since R2022b)
mergeMerge two or more groundTruthMedical objects (Since R2022b)
imageDatastoreDatastore for image data
pixelLabelDatastoreDatastore for pixel label data
randomPatchExtractionDatastoreDatastore for extracting random 2-D or 3-D random patches from images or pixel label images
combineCombine data from multiple datastores (Since R2019a)
transformTransform datastore (Since R2019a)

Import Network

importKerasLayers(To be removed) Import layers from Keras network
importTensorFlowLayers(To be removed) Import layers from TensorFlow network (Since R2021a)
importONNXLayers(To be removed) Import layers from ONNX network

Design Networks

fcnLayersCreate fully convolutional network layers for semantic segmentation
segnetLayersCreate SegNet layers for semantic segmentation
unet3dLayersCreate 3-D U-Net layers for semantic segmentation of volumetric images (Since R2019b)
unetLayersCreate U-Net layers for semantic segmentation
pixelClassificationLayerCreate pixel classification layer for semantic segmentation
dicePixelClassificationLayerCreate pixel classification layer using generalized Dice loss for semantic segmentation (Since R2019b)

Segment Images

semanticsegSemantic image segmentation using deep learning
labeloverlayOverlay label matrix regions on 2-D image
volshowDisplay volume
jaccardJaccard similarity coefficient for image segmentation
diceSørensen-Dice similarity coefficient for image segmentation
bfscoreContour matching score for image segmentation
radiomicsPrepare data and ROI for radiomics feature extraction (Since R2023b)
shapeFeaturesRadiomics shape features (Since R2023b)
intensityFeaturesRadiomics intensity features (Since R2023b)
textureFeaturesRadiomics texture features (Since R2023b)


Segmentation Using Deep Learning

Radiomics Analysis

Related Information