Diagnosing alveolar septal thickening remains challenging, and predicting alveolar diffusion is crucial for preoperative radiological assessment of pulmonary conditions in patients. Non-invasive screening of early-stage patients using imaging techniques holds significant clinical importance. In response to this challenge, we effectively predict alveolar diffusion in adenocarcinoma nodules using a radiomics and deep learning combined method, named the Spread Through Air Space (STAS) Prediction Model. Specifically, by fusing radiomic features from the lung cancer nodule lesion region with deep learning features, the mutual enhancement of feature representation leads to a remarkable area under the curve (AUC) of 0.830 in the binary classification task (STAS patients vs. non-STAS patients) for the radiomics model. Moreover, the deep learning model, utilizing ResNet-18 network to extract deep features from tumor blocks, achieves an AUC of 0.841. The combined model, incorporating both deep learning and traditional radiomic features, outperforms standalone deep learning and radiomics models by 3.50% and 4.60%, respectively. The introduction of radiomic features enhances the model’s interpretability, demonstrating promising clinical applicability.
Multiplex assays have attracted considerable interest to meet the growing demand for clinical diagnosis, gene expression,
drug discovery, and so on. Most of the assays are based on molecular binding or recognition events. In this point,
different probe biomolecules could be immobilized to encoded carriers, which can be mixed and subjected to an assay
simultaneously and then many binding events can be distinguished by their codes. Herein we summarize our work on
photonic beads as novel encoded carriers of biomolecules in multiplex bioassays. We have successfully fabricated
different kinds of encoded photonic beads with controlled size and monodispersity by microfluidic device. The beads
with opal structure and inverse opal structure could be used in multiplex labeling detection and label-free detection of
biomolecules, respectively. These photonic beads provide a new coding strategy of suspension array for low cost,
sensitive and simultaneous multiplex bioassay.
In the present paper, we overview fabrication methods to produce density-controlled tin and xenon targets for generating
extreme ultraviolet (EUV) light. The target can be classified as a mass-limited target. In the case of tin, EUV was
relatively monochromatic, and its conversion efficiency was higher than bulk tin. Using the nano-template method, the
cellular foam size was controlled by the template size. The density was 0.5 ~1.5 g/cm3. In the case of the 0.5 g/cm3
foam, its morphology was controlled by changing the ethanol content of the precursor tin solution. The morphology
difference was useful to control the angular distribution of EUV radiation. SnO2 nanofiber, which is oriented low-density
material, was fabricated continuously using a electrospinning method. The width and the shape of the fiber were
controlled by optimizing precursor solution. A transparent film with tin and SnO2 elliptic spheres were prepared using
liquid crystalline cellulose derivative. Low density xenon was prepared from liquid xenon using a swirl atomizer to
produce a density of 0.2 g/cm3.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.