Objective: The purpose of this study was to evaluate agreement in predictions made by a bone age prediction application ("app") among three data input methods.
Methods: The 16Bit Bone Age app is a browser-based deep learning application for predicting bone age on pediatric hand radiographs; recommended data input methods are direct image file upload or smartphone-capture of image. We collected 50 hand radiographs, split equally among 5 bone age groups. Three observers used the 16Bit Bone Age app to assess these images using 3 different data input methods: (1) direct image upload, (2) smartphone photo of image in radiology reading room, and (3) smartphone photo of image in a clinic.
Results: Interobserver agreement was excellent for direct upload (ICC = 1.00) and for photos in reading room (ICC = 0.96) and good for photos in clinic (ICC = 0.82), respectively. Intraobserver agreement for the entire test set across the 3 data input methods was variable with ICCs of 0.95, 0.96, and 0.57 for the 3 observers, respectively.
Discussion: Our findings indicate that different data input methods can result in discordant bone age predictions from the 16Bit Bone Age app. Further study is needed to determine the impact of data input methods, such as smartphone image capture, on deep learning app performance and accuracy.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00256-021-03897-3 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Sellar and perisellar meningiomas: effects on pituitary function in a Spanish cohort observational study.
Pituitary
December 2024
Department of Endocrinology and Nutrition, Hospital Universitario de Puerta de Hierro Majadahonda, Madrid, Spain.
Purpose: Studies focused on the effects of sellar and/or perisellar (S/PS) meningiomas on pituitary function are scarce. The primary objective of the present study was to determinate the effects that S/PS meningiomas and their treatments have on pituitary function. Also, we described the clinical characteristics and therapeutic outcomes of the cohort of adult Spanish patients.
View Article and Find Full Text PDFExhaled breath metabolites reveal postmenopausal gut-bone cross-talk and non-invasive markers for osteoporosis.
Commun Med (Lond)
December 2024
Rostock Medical Breath Research Analytics and Technologies (ROMBAT), Department of Anesthesiology, Intensive Care Medicine and Pain Therapy, Rostock University Medical Center, Rostock, Germany.
Background: Menopause driven decline in estrogen exposes women to risk of osteoporosis. Detection of early onset and silent progression are keys to prevent fractures and associated burdens.
Methods: In a discovery cohort of 120 postmenopausal women, we combined repeated quantitative pulse-echo ultrasonography of bone, assessment of grip strength and serum bone markers with mass-spectrometric analysis of exhaled metabolites to find breath volatile markers and quantitative cutoff levels for osteoporosis.
Imaging observation of intervertebral disc degeneration in patients with old thoracolumbar fracture-related kyphotic deformity.
Sci Rep
December 2024
Affiliated Fuyang People's Hospital of Anhui Medical University, Sanqing Road 501, Fuyang, 236000, Anhui, China.
Old thoracolumbar fracture with kyphosis (OTLFK) often results in low back pain, with intervertebral disc degeneration being a significant contributor. We hypothesized that patients with OTLFK exhibit distinct patterns of disc degeneration compared to those with chronic low back pain without kyphotic deformity. This study aimed to investigate the characteristics of disc degeneration in OTLFK patients and explore its association with sagittal spinal parameters and endplate injury.
View Article and Find Full Text PDFPharmacological inactivation of a non-canonical gp130 signaling arm attenuates chronic systemic inflammation and multimorbidity induced by a high-fat diet.
Sci Rep
December 2024
Department of Orthopaedic Surgery, Keck School of Medicine, Stem Cell Research and Regenerative Medicine, University of Southern California, Los Angeles, CA, USA.
Interleukin-6 (IL-6) is a major pro-inflammatory cytokine that demonstrates a robust correlation with age and body mass index (BMI) as part of the senescence-associated secretory phenotype. IL-6 cytokines also play a crucial role in metabolic homeostasis and regenerative processes primarily via the canonical STAT3 pathway. Thus, selective modulation of IL-6 signaling may offer a unique opportunity for therapeutic interventions.
View Article and Find Full Text PDFHDL-C is inversely associated with the incidence of osteoarthritis among the USA: evidence from the NHANES program of 1999-2020.
Sci Rep
December 2024
Department of Orthopedic Surgery, National Clinical Research Center for Geriatric Disorders, Hunan Engineering Research Center of Biomedical Metal and Ceramic Implants, Xiangya Hospital, Central South University, Changsha, 410008, China.
Osteoarthritis (OA) has been the most common arthritis affecting public health all over the world. Previous experimental research reported that increased low-density lipoprotein cholesterol, along with decreased high-density lipoprotein cholesterol may be associated with increased ectopic bone formation and possible knee OA, while clinical evidence is absent. This study aimed to investigate the association between blood high-density lipoprotein cholesterol (HDL-C) and OA.
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!