As the rise in cancer cases, there is an increasing demand to develop accurate and rapid diagnostic tools for early intervention. Pathologists are looking to augment manual analysis with computer-based evaluation to develop more efficient cancer diagnostics reports. The processing of these reports from manual evaluation is time-consuming, where the pathologists focus on accurately segmenting individual cancer cells, a vital step in analysis. This paper describes the design and validation of an application which has been developed based on deep learning networks. The application includes a workflow of image pre-processing followed by synthetic image generation, which is crucial due to the lack of training data in pathology settings. The next steps are the segmentation of nuclei regions and overlapping nuclei splitting. An improved approach has been considered based on a cycle-consistent GAN network for synthetic image generation. The synthetic images were utilized in a modified U-net network. Accurately outlining the individual nucleus border assisted an automated system that split the nuclei cluster into the individual nucleus. The SSIM and PSNR values of synthetic images corresponding to original were 0.204 and 10.610. The DSC value of the network trained by the synthetic data was 0.984 which was higher than the network trained by original images (0.805). The developed application provided better individual nuclei segmentation performance, where the average accuracy of different group images was 0.97. This higher accuracy suggests the benefit of using synthetic images in a situation to avoid the scarcity of labeled histopathology images in deep networks.
1 April 2020 in Journal of Ambient Intelligence and Humanized Computing
The aim of this scoping review is to understand the extent of issues of resilience implied by the interactions of older people with financial, social, and health related technologies. Older people aged 60+, technology use or non-use, and issues of resilience studied over the last four years (2019-2022) demarcate the scope of this review. Key exclusion criteria are older adults living in long-term care facilities, nursing homes, care homes and hospital in-patients. It also excludes studies on the perspectives of older peoples’ clinicians. The review will be carried out according to the Joanna Briggs Institute (JBI) scoping review methodology. The key information sources are SCOPUS, Web of Science, CINAHL, PsychINFO, and MEDLINE databases. The forms of grey literature included are reports from government and non-government organizations, as well as studies from the ProQuest Dissertations & Theses - Global database. The search is limited to studies written in English. For the first step in the search strategy, keywords and index terms will be identified via SCOPUS, Web of Science, and MEDLINE databases. This is followed by a search via the above databases. Third, a search of the reference lists of all included articles will form part of the full-text screening process. Two researchers will independently screen the titles and abstracts of the literature and then read the full text of the included literature, applying the inclusion criteria and searching reference lists. All data will be presented in tables and charts to answer the review question.
Surgical subspecialties have successfully combined robotic technology with traditional practices. In doing so, they have benefited from increased precision in techniques, reduced incidence of surgical complications, and reduced MSK disorders. This scoping review aims to examine the extent of cobotics in obstetric ultrasound. The review was conducted using the JBI PRISMA protocol to map the topic of robotics in obstetric ultrasound. Teleoperated remote ultrasound formed the largest combined clinical cohort of 67 patients. Limitations of the 20‐week scan concerned incomplete visualization of fetal structures. These included cavum septi pellucidi, cardiac outflow tracts, kidneys, lips and spine. Third trimester scans omitted umbilical artery Doppler measures. Patients having telerobotic ultrasound report the experience as “comfortable” and would agree to repeat the robotic scan in the future. Obstetric cobotic literature was found to focus on the following subtopics: robotic‐assisted ultrasound, automated image acquisition, image stitching and fusion, teleoperated remote ultrasound, and ultrasound‐guided robotic surgery. Ultrasound‐guided robotic surgery was performed for maternal partial nephrectomy and cervical cerclage. The most mature application of obstetric cobotics is seen in teleoperated remote ultrasound, where pilot trials have used clinical patients. Other areas are early in the research phase, with investigation for proof of concept testing.