Type:
Educational Exhibit
Keywords:
Artificial Intelligence, CT, MR, Computer Applications-General, Segmentation, Technology assessment, Education and training
Authors:
P. Gray, S. O'Hanlon, A. Gupta; WA/AU
DOI:
10.26044/ranzcr2021/R-0345
Background
Background
Segmentation is the delineation of areas of interest within an image.
Segmentation techniques have many potential applications in medical imaging and related fields. They are useful in comparing imaging studies over time and they potentiate further interrogation of textural analysis. Both methods are becoming more commonplace in image analysis. It is therefore useful to have an understanding of segmentation techniques best suited for purpose.
Many segmentation techniques are available from manual, to semi-automated (still requiring user input or adjustments) and automated segmentation. The premise from which they are based are varied, utilising 'manual tracing/annotation', to 'threshold techniques' to deep learning techniques.
There are a vast number of studies regarding segmentation. However the authors found a paucity of objective overviews of segmentation techniques, for Radiologists looking to find the best software to use in their work or research, inclusive of availability and price.