Search Articles

View query in Help articles search
e.g. mhealth

Search Results (1 to 10 of 73 Results)

Download search results: CSV END BibTex RIS

Convolutional Neural Network Models for Visual Classification of Pressure Ulcer Stages: Cross-Sectional Study

Convolutional Neural Network Models for Visual Classification of Pressure Ulcer Stages: Cross-Sectional Study

CNNs automatically extract and learn hierarchical features from grid-like data, such as images, and have achieved performance levels comparable to or surpassing those of human experts in various medical imaging domains [8]. In dermatological and wound imaging, CNNs have demonstrated promising results, matching or even exceeding the diagnostic accuracy of dermatologists in classifying skin cancer and other skin lesions [9].

Changbin Lei, Yan Jiang, Ke Xu, Shanshan Liu, Hua Cao, Cong Wang

JMIR Med Inform 2025;13:e62774

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Using Deep Learning to Perform Automatic Quantitative Measurement of Masseter and Tongue Muscles in Persons With Dementia: Cross-Sectional Study

Using Deep Learning to Perform Automatic Quantitative Measurement of Masseter and Tongue Muscles in Persons With Dementia: Cross-Sectional Study

However, techniques such as dual X-ray absorptiometry or body magnetic resonance imaging (MRI) are necessary to accurately assess lean or muscle mass. These methods can increase costs and time and are impractical in settings such as dementia clinics [6]. Dementia patients are highly affected by sarcopenia, with a prevalence of around 60%‐70% [7,8].

Mahdi Imani, Miguel G Borda, Sara Vogrin, Erik Meijering, Dag Aarsland, Gustavo Duque

JMIR Aging 2025;8:e63686

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 3

Improving Pediatric Patients’ Magnetic Resonance Imaging Experience With an In-Bore Solution: Design and Usability Study

Improving Pediatric Patients’ Magnetic Resonance Imaging Experience With an In-Bore Solution: Design and Usability Study

Using magnetic resonance imaging (MRI), physicians can diagnose a host of different pediatric conditions without exposing children to harmful ionizing radiation. Every year, millions of children get an MRI examination. To be able to have a successful examination, children need to enter a room with a large machine, lie down on a table that slides into this machine, and keep very still for an extended period of time (20-40 min, with some examinations taking up to an hour [1]).

Annerieke Heuvelink, Privender Saini, Özgür Taşar, Sanne Nauts

JMIR Serious Games 2025;13:e55720

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Large Language Models–Supported Thrombectomy Decision-Making in Acute Ischemic Stroke Based on Radiology Reports: Feasibility Qualitative Study

Large Language Models–Supported Thrombectomy Decision-Making in Acute Ischemic Stroke Based on Radiology Reports: Feasibility Qualitative Study

For example, recent studies show the application of AI in cancer imaging analysis or in detecting acute intracranial hemorrhage on computed tomography (CT) or magnetic resonance imaging scans [18,19]. Similar studies have also shown promising results in the use of AI in the diagnosis of ischemic stroke (IS), with potential improvement of diagnostic accuracy and reduction of variability in the decision-making process. However, these studies all focus on the AI-based processing of visual information [18,20].

Jonathan Kottlors, Robert Hahnfeldt, Lukas Görtz, Andra-Iza Iuga, Philipp Fervers, Johannes Bremm, David Zopfs, Kai R Laukamp, Oezguer A Onur, Simon Lennartz, Michael Schönfeld, David Maintz, Christoph Kabbasch, Thorsten Persigehl, Marc Schlamann

J Med Internet Res 2025;27:e48328

Download Citation: END BibTex RIS

Download PDF Download XML

Advancing Privacy-Preserving Health Care Analytics and Implementation of the Personal Health Train: Federated Deep Learning Study

Advancing Privacy-Preserving Health Care Analytics and Implementation of the Personal Health Train: Federated Deep Learning Study

Similarly, the National Institutes of Health has set up an “Imaging Data Commons” to provide secure access to a large collection of publicly available cancer imaging data colocated with analysis tools and resources [16]. Other researchers have shown that blockchain encryption technology can be used to securely store and share sensitive medical data [17].

Ananya Choudhury, Leroy Volmer, Frank Martin, Rianne Fijten, Leonard Wee, Andre Dekker, Johan van Soest

JMIR AI 2025;4:e60847

Download Citation: END BibTex RIS

Download PDF Download XML

Mortality Risk Prediction in Patients With Antimelanoma Differentiation–Associated, Gene 5 Antibody–Positive, Dermatomyositis–Associated Interstitial Lung Disease: Algorithm Development and Validation

Mortality Risk Prediction in Patients With Antimelanoma Differentiation–Associated, Gene 5 Antibody–Positive, Dermatomyositis–Associated Interstitial Lung Disease: Algorithm Development and Validation

Lian et al [10] developed the FLAIR score, which includes 5 key indicators: ferritin levels, lactate dehydrogenase (LDH) levels, the anti-MDA5 antibody grade, the high-resolution computed tomography (HRCT) imaging score, and RP-ILD [10]. However, the FLAIR score was designed to predict mortality in patients with amyopathic DM.

Hui Li, Ruyi Zou, Hongxia Xin, Ping He, Bin Xi, Yaqiong Tian, Qi Zhao, Xin Yan, Xiaohua Qiu, Yujuan Gao, Yin Liu, Min Cao, Bi Chen, Qian Han, Juan Chen, Guochun Wang, Hourong Cai

J Med Internet Res 2025;27:e62836

Download Citation: END BibTex RIS

Download PDF Download XML

Multiparametric MRI Assessment of Morpho-Functional Muscle Changes Following a 6-Month FES-Cycling Training Program: Pilot Study in People With a Complete Spinal Cord Injury

Multiparametric MRI Assessment of Morpho-Functional Muscle Changes Following a 6-Month FES-Cycling Training Program: Pilot Study in People With a Complete Spinal Cord Injury

In particular, the use of MRI (magnetic resonance imaging) is limited to basic protocols, typically consisting of T1-weighted sequences, primarily focused on the quantification of muscle volume and CSA [13,15,19,21-24] thus not fully exploiting the strength and versatility of noninvasive MRI techniques in capturing other crucial aspects such as fat infiltration, tissue inflammation, and microstructural changes.

Alfonso Mastropietro, Denis Peruzzo, Maria Giovanna Taccogna, Nicole Sanna, Nicola Casali, Roberta Nossa, Emilia Biffi, Emilia Ambrosini, Alessandra Pedrocchi, Giovanna Rizzo

JMIR Rehabil Assist Technol 2025;12:e64825

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1

Enhancing Ultrasound Image Quality Across Disease Domains: Application of Cycle-Consistent Generative Adversarial Network and Perceptual Loss

Enhancing Ultrasound Image Quality Across Disease Domains: Application of Cycle-Consistent Generative Adversarial Network and Perceptual Loss

These smaller devices promise to democratize access to medical imaging by making it more affordable and widely available. Yet, the miniaturization and cost-effectiveness often come at the expense of image quality, a trade-off primarily attributable to hardware constraints [5-7]. Machine learning algorithms have been explored to enhance low-quality images without the need for hardware improvements [8].

Shreeram Athreya, Ashwath Radhachandran, Vedrana Ivezić, Vivek R Sant, Corey W Arnold, William Speier

JMIR Biomed Eng 2024;9:e58911

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 2