Highlights We describe a deep learning approach for thalamic measurement on clinical T2-FLAIR. The algorithm performs comparably to FSL FIRST on high resolution T1. Clinical relevance on disability and cognition is confirmed.
Background and Purpose: FSL's FMRIB's Integrated Registration and Segmentation Tool (FSL-FIRST) is a widely used and well-validated tool. Automated thalamic segmentation is a common application and an important longitudinal measure for multiple sclerosis (MS).However, FSL-FIRST's algorithm is based on shape models derived from non-MS groups.As such, the present study sought to systematically assess common thalamic segmentation errors made by FSL-FIRST on MRIs from people with multiple sclerosis (PwMS).Methods: FSL-FIRST was applied to generate thalamic segmentation masks for 890 MR images in PwMS. Images and masks were reviewed systematically to classify and quantify errors, as well as associated anatomical variations and MRI abnormalities. For cases with overt errors (n = 362), thalamic masks were corrected and quantitative volumetric differences were calculated. Results:In the entire quantitative volumetric group, the mean volumetric error of FSL-FIRST was 2.74% (0.360 ml): among only corrected cases, the mean volumetric error was 6.79% (0.894 ml). The average percent volumetric error associated with seven error types, two anatomical variants, and motions artifacts are reported. Additional analyses showed that the presence of motion artifacts or anatomical variations significantly increased the probability of error (χ 2 = 18.14, p < .01 and χ 2 = 64.89, p < .001, respectively). Finally, thalamus volume error was negatively associated with degree of atrophy, such that smaller thalami were systematically overestimated (r = -.28, p < .001). Conclusions:In PwMS, FSL-FIRST thalamic segmentation miscalculates thalamic volumetry in a predictable fashion, and may be biased to overestimate highly atrophic thalami. As such, it is recommended that segmentations be reviewed and corrected manually when appropriate for specific studies.
Background Depression is a common mental health condition that poses a significant public health burden. Effective treatments for depression exist; however, access to evidence-based care remains limited. Mobile health (mHealth) apps offer an avenue for improving access. However, few mHealth apps are informed by evidence-based treatments and even fewer are empirically evaluated before dissemination. To address this gap, we developed RuminAid, an mHealth app that uses evidence-based treatment components to reduce depression by targeting a single key depressogenic process—rumination. Objective The primary objective of this study was to collect qualitative and quantitative feedback that could be used to improve the design of RuminAid before the software development phase. Methods We reviewed empirically supported interventions for depression and rumination and used the key aspects of each to create a storyboard version of RuminAid. We distributed an audio-guided presentation of the RuminAid storyboard to 22 individuals for viewing and solicited user feedback on app content, design, and perceived functionality across 7 focus group sessions. Results The consumer-rated quality of the storyboard version of RuminAid was in the acceptable to good range. Indeed, most participants reported that they thought RuminAid would be an engaging, functional, and informational app. Likewise, they endorsed overwhelming positive beliefs about the perceived impact of RuminAid; specifically, 96% (21/22) believed that RuminAid will help depressed ruminators with depression and rumination. Nevertheless, the results highlighted the need for improved app aesthetics (eg, a more appealing color scheme and modern design). Conclusions Focus group members reported that the quality of information was quite good and had the potential to help adults who struggle with depression and rumination but expressed concern that poor aesthetics would interfere with users’ desire to continue using the app. To address these comments, we hired a graphic designer and redesigned each screen to improve visual appeal. We also removed time gating from the app based on participant feedback and findings from related research. These changes helped elevate RuminAid and informed its initial software build for a pilot trial that focused on evaluating its feasibility and acceptability.
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.