Objective: Prospectively validate the accuracy of smartphone-based digital cranial measurements for the diagnosis and treatment of deformational plagiocephaly and/or brachycephaly (DPB), compared with calipers used in the standard of care.
Design/methods: Bird's-eye-view head photos were captured via smartphone, and their heads were measured with hand calipers by an expert user. CI/CVAI/CVA were calculated from photos and caliper measurements, and from 3D photogrammetry of the head as ground truth. Digital and caliper measurements were compared against 3D-based ground truth using mean absolute error, Spearman correlation coefficient, and Bland-Altman method. Statistical significance between methods was assessed using Wilcoxon Rank-Sum test.
Participants: 71 infants aged 2-11 months (20 female, 51 male) with DPB.
Results: The mean absolute errors for CI, CVAI, CVA were 1.63 ± 1.44, 1.45 ± 1.29, 2.38 ± 1.86 mm for smartphone, and 2.60 ± 1.96, 1.43 ± 1.22, 2.04 ± 1.81 mm for calipers, respectively. The correlation coefficients for CI, CVAI, CVA between smartphone and ground truth were 0.90, 0.94, 0.80 (p < 0.001), and 0.87, 0.93, 0.84 (p < 0.001) between calipers and ground truth, respectively. Bland-Altman results were (0.08, [-4.18, 4.34]), (-0.05, [-3.85, 3.76]), (-0.82, [-6.52, 4.87]) for smartphone, and (1.41, [-4.34, 7.15]), (0.28, [-3.37, 3.94]), (0.16, [-5.18, 5.49]) for caliper measurements respectively. Digital and caliper measurements were similar (p = 0.12) except for CI, where digital measurements were more accurate (p = 0.04).
Conclusion: Smartphone-based cranial measurements have very high correlation with 3D-based ground truth, and they are comparable or superior to caliper measurements. Digital measurements can be performed in pediatric offices or from home to help with the early detection and treatment of DPB.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1177/10556656241271681 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Biomarkers.
Alzheimers Dement
December 2024
Department of Clinical Sciences Lund, Lund University, Lund, Lund, Sweden.
Background: The medial temporal lobe (MTL) is the epicenter of both primary and concomitant molecular pathologies in Alzheimer's disease (AD). The intricate anatomy of the MTL has been the subject of extensive study over the past two centuries. However, current PET and MRI AD biomarkers use often crude parcellations of the MTL that have not been sufficiently validated vis-à-vis anatomical ground truth.
View Article and Find Full Text PDFBackground: Cortical brain atrophy is an excellent marker of clinical decline and can support future clinical course prediction in cognitive impairment. We used a U-Net image-generation deep learning network to predict future cortical atrophy rates in elderly populations, with initial T1-weighted (T1w-) MRI or baseline amyloid-PET serving as inputs to the model.
Method: MRI and PET data were retrospectively collected from Alzheimer's Disease Imaging Initiative (ADNI) and all participants had two serial T1w-MRI scans (Figure 1A,B).
Biomarkers.
Alzheimers Dement
December 2024
Glenn Biggs Institute for Alzheimer's & Neurodegenerative Diseases, University of Texas Health Sciences Center at San Antonio, San Antonio, TX, USA.
Background: Deep learning has shown promising results regarding Alzheimer's disease (AD) studies. In the meantime, heatmap methods have emerged as a popular tool to visualize deep learning models, enhancing the transparency and explainability of deep learning. However, when no ground truth is available, the heatmap methods are particularly difficult to trust.
View Article and Find Full Text PDFBiomarkers.
Alzheimers Dement
December 2024
Artificial Intelligence in Biomedical Imaging Laboratory (AIBIL), Center for and Data Science for Integrated Diagnostics (AI2D), Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
Background: The Spatial Pattern of Abnormality for REcognition of Alzheimer's Disease (SPARE-AD) index ∖citep{davatzikos2009longitudinal} is one such marker that robustly discriminates between early brain changes observed in cognitively normal aging (CN), mild cognitive impairment (MCI), and Alzheimer's Disease (AD) phenotypes. The adoption of such markers to the clinical setting combined with the ability to forecast their future trajectories would be of great value during clinical assessment, and could improve clinical trial design through targeted risk stratification.
Method: Subjects scanned using the same scanner with more than four longitudinal MRI acquisitions from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Baltimore Longitudinal Study of Aging (BLSA) study cohorts were used for method development.
Background: Cross-modality translation between MRI and PET presents significant challenges due to the distinct mechanisms underlying those modalities. Currently, the leading method for this translation is CycleGAN. Previous studies have proved a strong correlation between BBBMs and brain amyloid status measured by PET.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!