Learning objectives
Learning Objectives
The reader will be able to:
Define what Artificial Intelligence (AI) based segmentation software is
Explain the key terminology required to explain the methods by which AI segmentation software works
Provide current examples of AI segmentation software, including their interface
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...
Imaging findings OR Procedure details
Terminology
The authors found a lack of standardisation within studies when describing their methodologies and what AI they have used, if it is described at all. Some studies report software used, some the coding environment and some either have developed their own code, which they may or may not make available to readers. If we think of the methodology as describing how a study has been performed so it could be replicated for the same results, then most AI study methodologies are currently lacking sufficient...
Conclusion
Examples
The following table is an alphabetical list of the various code/coding structure/software the authors found from study methologies when they performed a literature review concerning the topic of automatic segmentation in radiology.
[Fig 2]
The following are examples of segmentation software used on a single, randomly selected, open-source CT abdomen. Authors uploaded the image and used semi-automatic (or automatic where available) methods to obtain a segmentation of body composition. They are intended to demonstrate user interface and not accuracy of segmentation (as it is...
Personal information
S. O'Hanlon:
Nothing to disclose
A. Gupta:
Nothing to disclose
References
Alkadhi H, Euler A. The Future of Computed Tomography: Personalized, Functional, and Precise. Invest Radiol. 2020 Sep;55(9):545-555. doi: 10.1097/RLI.0000000000000668. PMID: 32209817.
Mandić M et al, Automated assessment of regional muscle volume and hypertrophy using MRI. Nature.
Yushkevich PA, Pashchinskiy A, Oguz I, et al. User-Guided Segmentation of Multi-modality Medical Imaging Datasets with ITK-SNAP. Neuroinformatics. 2019;17(1):83-102. doi:10.1007/s12021-018-9385-x
Ning Q, Yu X, Gao Q, Xie J et al. An accurate interactive segmentation and volume calculation of orbital soft tissue for orbital reconstruction after enucleation. BMC Ophthalmology. 2019;...