. Purpose: Automation of organ segmentation, via convolutional neural networks (CNNs), is key to facilitate the work of medical practitioners by ensuring that the adequate radiation dose is delivered to the target area while avoiding harmful exposure of healthy organs. The issue with CNNs is that they require large amounts of data transfer and storage which makes the use of image compression a necessity. Compression will affect image quality which in turn affects the segmentation process. We address the dilemma involved with handling large amounts of data while preserving segmentation accuracy. Approach: We analyze and improve 2D and 3D U-Net robustness against JPEG 2000 compression for male pelvic organ segmentation. We conduct three experiments on 56 cone beam computed tomography (CT) and 74 CT scans targeting bladder and rectum segmentation. The two objectives of the experiments are to compare the compression robustness of 2D versus 3D U-Net and to improve the 3D U-Net compression tolerance via fine-tuning. Results: We show that a 3D U-Net is 50% more robust to compression than a 2D U-Net. Moreover, by fine-tuning the 3D U-Net, we can double its compression tolerance compared to a 2D U-Net. Furthermore, we determine that fine-tuning the network to a compression ratio of 64:1 will ensure its flexibility to be used at compression ratios equal or lower. Conclusions: We reduce the potential risk involved with using image compression on automated organ segmentation. We demonstrate that a 3D U-Net can be fine-tuned to handle high compression ratios while preserving segmentation accuracy.
Excessive cracking due to restraint of thermal and shrinkage strains is a widespread problem in the concrete construction industry. In design, restraint induced cracking is managed by the provision of reinforcement intended to distribute internal strains in such a way as to control the cracking pattern and limit crack widths. The area of secondary (horizontal) reinforcement required in members such as retaining walls and water tanks is often governed by the need to control early age thermal cracking. This paper presents results from four edge restrained walls tested at Imperial College London and the University of Leeds as part of an Engineering and Physical Sciences Research Council funded project into restraint induced cracking. The paper describes the development of volumetric strain and cracking in the tested walls. The cracking performance is assessed by comparing the restrained strain with the tensile strain capacity of concrete.degree of restraint, early age, edge restraint, imposed strain, thermal strain 1 | BACKGROUND | IntroductionConcrete structures undergo early age as well as longterm (LT) volumetric changes due to several actions including early-age thermal (EAT) strains and LT shrinkage strains. 1 If these strains are restrained either internally (by reinforcement or another part of the same cross section) or externally by adjoining members, stresses develop in the concrete with a magnitude proportional to the restrained strain. This phenomenon can lead to cracking if the stress levels exceed the tensile strength of the concrete. 2 Little experimental work has been carried out to investigate cracking in edge restrained members which are the subject of this paper. Stoffers 3 examined the influence of reinforcement ratio, wall aspect ratio and presence or absence of wall curvature in 18 tests of reduced scale micro-concrete walls with cross section of 60 Â 375 mm 2 . The maximum reinforcement diameter was 3 mm. Kheder et al. 4 examined the influence of wall aspect ratio. They tested 14 reduced-scale mortar walls Discussion on this paper must be submitted within two months of the print publication. The discussion will then be published in print, along with the authors' closure, if any, approximately nine months after the print publication.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.