Segmentation
Segmentation, in the context of informatics for radiology, refers to the delineation of areas of interest in imaging in terms of pixels or voxels. Segmentation is often accomplished by computerized algorithms that vary in complexity from simply selecting pixels of similar values in proximity to those that include radiometric features or are based on machine learning. The underlying algorithms that can be used for segmentation include, but are not limited to thresholding (simply taking all the pixels within a certain value range), K-means and Otsu's algorithm. In order to evaluate segmentation algorithms researchers have used ROC analysis, odds ratios, the superiority evaluation method, the deviation evaluation model, Hausdorff distances, contour mean distances, regression analysis, volumetric differences and Dice similarity coefficients to compare segmentations to expert segmented gold standards or statistically generated gold standards.
Segmentation is usually a necessary step in creating modifiable three dimensional images for surface modeling, extended reality and/or medical 3D printing from imaging.
Practical points
Several software programs can be used to segment radiological images, usually but not exclusively CT or MRI. Here follows a list of segmentation tools optimized for radiological images that are free and open-source:
Related Radiopaedia articles
Artificial intelligence
- artificial intelligence (AI)
- imaging data sets
- computer-aided diagnosis (CAD)
- natural language processing
- machine learning (overview)
- visualizing and understanding neural networks
- common data preparation/preprocessing steps
- DICOM to bitmap conversion
- dimensionality reduction
- scaling
- centering
- normalization
- principal component analysis
- training, testing and validation datasets
- augmentation
- loss function
-
optimization algorithms
- ADAM
- momentum (Nesterov)
- stochastic gradient descent
- mini-batch gradient descent
-
regularisation
- linear and quadratic
- batch normalization
- ensembling
- rule-based expert systems
- glossary
- activation function
- anomaly detection
- automation bias
- backpropagation
- batch size
- computer vision
- concept drift
- cost function
- confusion matrix
- convolution
- cross validation
- curse of dimensionality
- dice similarity coefficient
- dimensionality reduction
- epoch
- explainable artificial intelligence/XAI
- feature extraction
- federated learning
- gradient descent
- ground truth
- hyperparameters
- image registration
- imputation
- iteration
- jaccard index
- linear algebra
- noise reduction
- normalization
- R (Programming language)
- Python (Programming language)
- segmentation
- semi-supervised learning
- synthetic and augmented data
- overfitting
- transfer learning