Abstract
Background and PurposeIn clinical diagnosis, medical image segmentation plays a key role in the analysis of pathological regions. Despite advances in automatic and semi-automatic segmentation techniques, time-effective correction tools are commonly needed to improve segmentation results. Therefore, these tools must provide faster corrections with a lower number of interactions, and a user-independent solution to reduce the time frame between image acquisition and diagnosis.MethodsWe present a new interactive method for correcting image segmentations. Our method provides 3D shape corrections through 2D interactions. This approach enables an intuitive and natural corrections of 3D segmentation results. The developed method has been implemented into a software tool and has been evaluated for the task of lumbar muscle and knee joint segmentations from MR images.ResultsExperimental results show that full segmentation corrections could be performed within an average correction time of 5.5±3.3 minutes and an average of 56.5±33.1 user interactions, while maintaining the quality of the final segmentation result within an average Dice coefficient of 0.92±0.02 for both anatomies. In addition, for users with different levels of expertise, our method yields a correction time and number of interaction decrease from 38±19.2 minutes to 6.4±4.3 minutes, and 339±157.1 to 67.7±39.6 interactions, respectively.
Highlights
Medical image segmentation is still an on-going research topic
Experimental results show that full segmentation corrections could be performed within an average correction time of 5.5±3.3 minutes and an average of 56.5±33.1 user interactions, while maintaining the quality of the final segmentation result within an average Dice coefficient of 0.92±0.02 for both anatomies
In comparison with the standard correction process used in clinics, we demonstrate the ability of the proposed approach to yield a substantial correction speed-up on segmentations produced with active shape model-based (ASM) [26]
Summary
Medical image segmentation is still an on-going research topic. The wide range of imaging protocols with their respective scanning parameters makes it difficult to have an unique solution for image segmentation [1, 2]. The segmentation task has become a process where a post-correction and checking has to be performed to achieve an optimal solution Another problem that arises with interactive corrections is the processing and analysis of a massive amount of data, which lowers the successfulness of these techniques in light of high-throughput data analysis. As we will show, the correction procedure of lumbar muscle segmentation using a Brushing Tool takes between 24 minutes and 68 minutes, depending on the expertise of the user using the tool and his knowledge of the anatomy (cf results section). Despite advances in automatic and semi-automatic segmentation techniques, time-effective correction tools are commonly needed to improve segmentation results These tools must provide faster corrections with a lower number of interactions, and a user-independent solution to reduce the time frame between image acquisition and diagnosis.
Sign-in/Register to view highlights & summary 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.
