Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.4045/tidsskr.16.0148 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A Clinical Drug as the Three-Photon Fluorescence Probe for In Vivo Microscopic Imaging of Mouse Kidney.
J Biophotonics
January 2025
State Key Laboratory of Extreme Photonics and Instrumentations, Centre for Optical and Electromagnetic Research, College of Optical Science and Engineering, International Research Center for Advanced Photonics, Zhejiang University, Hangzhou, China.
Three-photon fluorescence (3PF) microscopy encounters significant challenges in biological research and clinical applications, primarily due to the limited availability of high-performance probes. We took a shortcut by exploring the excellent 3PF property of berberine hydrochloride (BH), a clinically utilized drug derived from the traditional Chinese medicine, Coptis. Capitalizing on its renal metabolism characteristics, we employed BH for in vivo 3PF microscopic imaging of the mouse kidney.
View Article and Find Full Text PDFKeyboarding Instruction for a Japanese Child With Attention Deficit Hyperactivity Disorder and Dysgraphia Reduced Frustration in Handwriting: A Case Report.
Cureus
November 2024
Department of Speech-Language Pathology and Audiology, Faculty of Rehabilitation, Kawasaki University of Medical Welfare, Kurashiki, JPN.
Dysgraphia often goes unnoticed in schools, leading to delayed academic development and diminished self-esteem for affected students. This case report provides keyboarding instruction to a nine-year-old Japanese boy diagnosed with dysgraphia and observes its impact on his writing performance, including speed, accuracy, and composition, and mental burden. The patient was diagnosed with dysgraphia and refusal to write at school.
View Article and Find Full Text PDFConsumption of Endogenous Caspase-3 Activates Molecular Theranostic Nanoplatform against Inflammation-Induced Profibrotic Positive Feedback in Pulmonary Fibrosis.
Adv Sci (Weinh)
December 2024
School of Pharmacy, Jinzhou Medical University, Jinzhou, Liaoning, 121001, China.
The limited and backward diagnostic approaches elicit high mortality associated with pulmonary fibrosis (PF) because they fail to identify injury phase of PF. Developing a precisely theranostic nanoplatform presents a promising shortcut to reverse PF. Herein, a specific molecular nanotheranostic (Casp-GNMT), which is triggered by endogenous cysteinyl aspartate specific proteinase-3 (caspase-3), boosts antifibrotic efficacy through bioimaging synergistic with chemotherapy at molecular level, facilitating by ionizable lipid and reactive oxygen species sensitive lipid for precise and manageable therapy.
View Article and Find Full Text PDFWhere, why, and how is bias learned in medical image analysis models? A study of bias encoding within convolutional networks using synthetic data.
EBioMedicine
January 2025
Department of Radiology, University of Calgary, Calgary, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Alberta Children's Hospital Research Institute, University of Calgary, Calgary, Canada; Department of Clinical Neuroscience, University of Calgary, Calgary, Canada.
Background: Understanding the mechanisms of algorithmic bias is highly challenging due to the complexity and uncertainty of how various unknown sources of bias impact deep learning models trained with medical images. This study aims to bridge this knowledge gap by studying where, why, and how biases from medical images are encoded in these models.
Methods: We systematically studied layer-wise bias encoding in a convolutional neural network for disease classification using synthetic brain magnetic resonance imaging data with known disease and bias effects.
The risk of shortcutting in deep learning algorithms for medical imaging research.
Sci Rep
November 2024
Department of Orthopaedic Surgery, Dartmouth-Hitchcock Medical Center, One Medical Center Drive, Lebanon, NH, 03756, USA.
Article Synopsis
- Deep learning (DL) can recognize intricate patterns in data that humans might miss, but it often leads to misleading results due to its black-box nature and a problem known as algorithmic shortcutting.
- In a case study, simple convolutional neural networks (CNNs) were able to predict patient behaviors like avoiding refried beans or beer just by analyzing knee X-rays, showcasing the dangers of relying on shortcuts in data interpretation.
- The findings highlight that the models' predictions are influenced by confounding factors in the images that cannot be easily eliminated, indicating a need for stricter criteria when assessing research involving medical imaging.
Want 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!