Abstract
Extensions to auto-context segmentation are proposed and applied to segmentation of multiple organs in porcine offal as a component of an envisaged system for post-mortem inspection at abbatoir. In common with multi-part segmentation of many biological objects, challenges include variations in configuration, orientation, shape, and appearance, as well as inter-part occlusion and missing parts. Auto-context uses context information about inferred class labels and can be effective in such settings. Whereas auto-context uses a fixed prior atlas, we describe an adaptive atlas method better suited to represent the multimodal distribution of segmentation maps. We also design integral context features to enhance context representation. These methods are evaluated on a dataset captured at abbatoir and compared to a method based on conditional random fields. Results demonstrate the appropriateness of auto-context and the beneficial effects of the proposed extensions for this application.
Highlights
Segmentation of non-rigid biological objects into their constituent parts presents various challenges
We report a direct comparison of all of these methods applied to segmentation of multiple organs in pig offal, and we compare with a conditional random field
We introduced the problem of multiple organ segmentation at abattoir and proposed solutions based on an auto-context approach
Summary
Segmentation of non-rigid biological objects into their constituent parts presents various challenges. We address a segmentation task in which parts are organs in body images captured at abbatoir This constitutes one stage in an envisaged on-site system for screening of pathologies; these are characteristically organspecific. There are moves towards visual-only inspection of pig carcasses and offal without palpation, in order to minimise risk of cross contamination [5,6] This along with the potential to detect a greater number of pathologies with improved reproducibility than currently possible with manual inspection [7] motivates development of automated visual inspection. Reliable segmentation of organs would constitute an important step towards this goal In this context even modest improvements in organ segmentation could be significant as regions assigned to the wrong organ may lead to missed or falsely detected pathologies. Stommel et al [12] envisaged a system for robotic sorting of ovine offal that would involve recognition of multiple organs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
