Dataset Information

Research on 3D virtual vision matching based on interactive color segmentation.

ABSTRACT: Given the prevalent issues surrounding accuracy and efficiency in contemporary stereo-matching algorithms, this research introduces an innovative image segmentation-based approach. The proposed methodology integrates residual and Swim Transformer modules into the established 3D Unet framework, yielding the Res-Swim-UNet image segmentation model. The algorithm estimates the disparateness of segmented outputs by employing regression techniques, culminating in a comprehensive disparity map. Experimental findings underscore the superiority of the proposed algorithm across all evaluated metrics. Specifically, the proposed network demonstrates marked improvements, with IoU and mPA enhancements of 2.9% and 162%, respectively. Notably, the average matching error rate of the algorithm registers at 2.02%, underscoring its efficacy in achieving precise stereoscopic matching. Moreover, the model's enhanced generalization capability and robustness underscore its potential for widespread applicability.

SUBMITTER: Wang Y

PROVIDER: S-EPMC11232617 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Research on 3D virtual vision matching based on interactive color segmentation.

Wang Yahui Y Wang Haiwen H Jin Juan J Kuang Yingfeng Y

PeerJ. Computer science 20240628

Given the prevalent issues surrounding accuracy and efficiency in contemporary stereo-matching algorithms, this research introduces an innovative image segmentation-based approach. The proposed methodology integrates residual and Swim Transformer modules into the established 3D Unet framework, yielding the Res-Swim-UNet image segmentation model. The algorithm estimates the disparateness of segmented outputs by employing regression techniques, culminating in a comprehensive disparity map. Experim ...[more]

PMID: 38983224

Similar Datasets

Project description:BackgroundPostoperative physical rehabilitation is crucial after total joint replacement (TJR). However, completing the recommended levels of postoperative physical exercise is challenging for many older adults with TJR. Lack of adequate postoperative physical exercise has negative consequences on rehabilitation outcomes. Innovative rehabilitation tools for postoperative physical exercises are needed to ensure successful rehabilitation outcomes among older adults with TJR.ObjectiveThe aim of this study is to explore key knowledge users' perspectives about how to design an interactive vision-based three-dimensional augmented reality system (3D ARS) to support in-home postoperative physical rehabilitation for older adults with TJR.MethodsWe conducted a qualitative descriptive study involving 11 semi-structured interviews and six focus groups with 42 older adults with TJR and four unrelated family caregivers. Data were analysed using thematic analysis.ResultsParticipant insights were grouped into two main themes: (1) dreaming up possibilities and (2) being pragmatic. The first theme captured participants' reflections on the potential utility of a 3D ARS for postoperative physical rehabilitation and features that could be embedded in the 3D ARS to support successful postoperative physical rehabilitation. The second theme captured participants' reflections on practical issues and considerations that could impact access and usage of the 3D ARS.ConclusionThese findings provide researchers, rehabilitation providers and system developers with the foundations for designing, implementing and evaluating innovative augmented reality tools that support effective in-home physical rehabilitation among older adults with TJR.Patient or public contributionResearch users (i.e., individuals and organisations invested in and using the research findings) were actively engaged throughout this work. Specifically, a meeting was held between the research team and representatives of an Expert by Experience team (individuals with lived experience), which was established to support the National Research Council's (organisation) Aging in Place programme. During this meeting, the idea to develop and evaluate an ARS for postoperative physical rehabilitation of older adults with TJR was supported. Research users had the opportunity to review the current study protocol and provide feedback on the study design, offering direction to maximize the relevance and usefulness of our findings to the National Research Council Canada's Aging in Place programme. Research users contributed to participant recruitment efforts and the development of the interview guide. Two Experts by Experience also agreed to be on the Advisory Panel for this multi-phased study, supporting active engagement and centring the voice of research users in knowledge creation and implementation. These experts reviewed a brief report of the current study findings, and continue to guide how the study findings are used to inform the next phase of this multi-phased research.

Project description:The visualization of medical images with advanced techniques, such as augmented reality and virtual reality, represent a breakthrough for medical professionals. In contrast to more traditional visualization tools lacking 3D capabilities, these systems use the three available dimensions. To visualize medical images in 3D, the anatomical areas of interest must be segmented. Currently, manual segmentation, which is the most commonly used technique, and semi-automatic approaches can be time consuming because a doctor is required, making segmentation for each individual case unfeasible. Using new technologies, such as computer vision and artificial intelligence for segmentation algorithms and augmented and virtual reality for visualization techniques implementation, we designed a complete platform to solve this problem and allow medical professionals to work more frequently with anatomical 3D models obtained from medical imaging. As a result, the Nextmed project, due to the different implemented software applications, permits the importation of digital imaging and communication on medicine (dicom) images on a secure cloud platform and the automatic segmentation of certain anatomical structures with new algorithms that improve upon the current research results. A 3D mesh of the segmented structure is then automatically generated that can be printed in 3D or visualized using both augmented and virtual reality, with the designed software systems. The Nextmed project is unique, as it covers the whole process from uploading dicom images to automatic segmentation, 3D reconstruction, 3D visualization, and manipulation using augmented and virtual reality. There are many researches about application of augmented and virtual reality for medical image 3D visualization; however, they are not automated platforms. Although some other anatomical structures can be studied, we focused on one case: a lung study. Analyzing the application of the platform to more than 1000 dicom images and studying the results with medical specialists, we concluded that the installation of this system in hospitals would provide a considerable improvement as a tool for medical image visualization.

Dataset Information

Research on 3D virtual vision matching based on interactive color segmentation.

Publications

Research on 3D virtual vision matching based on interactive color segmentation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets