Background: The accuracy and consistency of bone age assessments (BAA) using standard methods can vary with physicians' level of experience.
Methods: To assess the impact of information from an artificial intelligence (AI) deep learning convolutional neural network (CNN) model on BAA, specialists with different levels of experience (junior, mid-level, and senior) assessed radiographs from 316 children aged 4-18 years that had been randomly divided into two equal sets-group A and group B. Bone age (BA) was assessed independently by each specialist without additional information (group A) and with information from the model (group B).
Comput Med Imaging Graph
March 2021
Convolutional neural networks (CNNs) have become an increasingly popular tool for brain lesion segmentation in recent years due to its accuracy and efficiency. However, CNN-based brain lesion segmentation generally requires a large amount of annotated training data, which can be costly for medical imaging. In many scenarios, only a few annotations of brain lesions are available.
View Article and Find Full Text PDFPorous matrix stiffness modulates response to targeted therapy. Poroelastic behavior within porous matrix may modulate the molecule events in cell-matrix and cell-cell interaction like the complex formation of human epidermal growth factor receptor-2 (HER2)-Src-α6β4 integrin, influencing the targeted therapy with lapatinib.
View Article and Find Full Text PDFMultifunctional "smart" particles with magnetic, topographic, cell-targeting, and stimulus-responsive properties are obtained using a "live template" strategy. These particles exhibit improved efficiency in capture of target cancer cells by introducing synergistic topographic interactions, and enable the release of captured cells with high viability via reduction of disulfide bonds. Diverse multifunctional particles can be designed using the "live template" strategy.
View Article and Find Full Text PDFActivated tumor-associated fibroblasts (TAFs) with abundant fibroblast activation protein (FAP) expression attract tremendous attention in tumor progression studies. In this work, we report a rapid 24 h FAP activation method for fibroblasts using silicon nanowires (SiNWs) as culture substrates instead of growth factors or chemokines. In contrast with cells cultured on flat silicon which rarely express FAP, SiNW cultivated cells exhibit FAP levels similar to those found in cancerous tissue.
View Article and Find Full Text PDF