Purpose: To compare the diagnostic assessment of glaucoma specialists with an automated structure-function correlation report combining visual field (VF) and spectral-domain optical coherence tomography (SD-OCT) imagining in subjects with glaucoma.
Methods: This prospective, cross-sectional study was conducted at Wills Eye Hospital, Philadelphia, PA, USA. Subjects with glaucoma received ophthalmic examination, VF testing, and SD-OCT imaging. An automated report was generated describing structure-function correlations between the two structural elements [retinal nerve fiber layer (RNFL) and Bruch's membrane opening-minimum rim width (MRW)] and VF sectors. Three glaucoma specialists masked to the automated report and to each other identified clinically significant structure-function correlations between the VF and SD-OCT reports. Raw agreement and chance-corrected agreement (kappa statistics) between the automated report and the clinical assessments were compared.
Results: A total of 53 eyes from 45 subjects with glaucoma were included in this study. The overall agreement between the automated report and clinical assessment comparing MRW and VF was good at 74.8% with a kappa of 0.62 (95% CI 0.55-0.69). Agreements for the six different MRW sections were moderate to good with kappa values ranging from 0.54 to 0.69. For mean RNFL thickness and VF comparisons, agreement between the automated report and clinical assessment was 75.4% with a kappa of 0.62 (95% CI 0.54-0.70). For different RNFL sectors, kappa values ranged from 0.47 (moderate agreement) to 0.80 (good agreement).
Conclusions: This study suggests that the automated structure-function report combining results from the SD-OCT and the HEP may assist in the evaluation and management of glaucoma.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1007/s10792-018-0836-z | DOI Listing |
PLoS One
January 2025
IBM Research, Rio de Janeiro, Brazil.
For optimizing production yield while limiting negative environmental impact, sustainable agriculture benefits from real-time, on-the-spot chemical analysis of soil at low cost. Colorimetric paper sensors are ideal candidates, however, their automated readout and analysis in the field is needed. Using mobile technology for paper sensor readout could, in principle, enable the application of machine-learning models for transforming colorimetric data into threshold-based classes that represent chemical concentration.
View Article and Find Full Text PDFErgonomics
January 2025
Human Factors Research Group, University of Nottingham, University Park, Nottingham, United Kingdom.
In a novel, on-road study, using a 'Ghost Driver' to emulate an automated vehicle (AV), we captured over 10 hours of video (n = 520) and 64 survey responses documenting the behaviour and attitudes of pedestrians in response to the AV. Three prototype external human-machine interfaces (eHMIs) described the AV's behaviour, awareness and intention using elements of anthropomorphism: High (human face), Low (car motif), Abstract (partial representation of human features that lacked precise visual reference); these were evaluated against a (no eHMI) baseline. Despite many pedestrians reporting that they still relied on vehicular cues to negotiate their crossing, there was a desire/expectation expressed for explicit communication with future AVs.
View Article and Find Full Text PDFEur Radiol
January 2025
Department of Radiology, Geneva University Hospitals, Geneva, Switzerland.
Objectives: Evaluating the impact of an AI-based automated cardiac MRI (CMR) planning software on procedure errors and scan times compared to manual planning alone.
Material And Methods: Consecutive patients undergoing non-stress CMR were prospectively enrolled at a single center (August 2023-February 2024) and randomized into manual, or automated scan execution using prototype software. Patients with pacemakers, targeted indications, or inability to consent were excluded.
Radiol Artif Intell
January 2025
https://www.procancer-i.eu/.
Purpose To assess the impact of scanner manufacturer and scan protocol on the performance of deep learning models to classify prostate cancer (PCa) aggressiveness on biparametric MRI (bpMRI). Materials and Methods In this retrospective study, 5,478 cases from ProstateNet, a PCa bpMRI dataset with examinations from 13 centers, were used to develop five deep learning (DL) models to predict PCa aggressiveness with minimal lesion information and test how using data from different subgroups-scanner manufacturers and endorectal coil (ERC) use (Siemens, Philips, GE with and without ERC and the full dataset)-impacts model performance. Performance was assessed using the area under the receiver operating characteristic curve (AUC).
View Article and Find Full Text PDFAm J Nucl Med Mol Imaging
December 2024
Cyclotron and Radiochemistry Core, Karmanos Cancer Institute Detroit, MI, USA.
Colony-stimulating factor 1 receptor (CSF1R) is almost exclusively expressed on microglia in the human brain and thus, has promise as a biomarker for imaging microglia density as a proxy for neuroinflammation. [C]CPPC is a radiotracer with selective affinity to CSF1R, and has been evaluated for in-human microglia PET imaging. The flourine-18 labeled CPPC derivative, 5-cyano-N-(4-(4-(2-[F]fluoroethyl)piperazin-1-yl)-2-(piperidin-1-yl)phenyl)furan-2-carboxamide ([F]FCPPC), was previously synthesized, however, with a low radiochemical yield using manual radiosynthesis.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!