Neural network-based screening (NNS) of cervical smears can be performed as a so-called "hybrid screening method," in which parts of the cases are additionally studied by light microscope, and it can also be used as "pure" NNS, in which the cytological diagnosis is based only on the digital images, generated by the NNS system. A random enriched sample of 985 cases, in a previous study diagnosed by hybrid NNS, was drawn to be screened by pure NNS. This study population comprised 192 women with (pre)neoplasia of the cervix, and 793 negative cases. With pure NNS, more cases were recognized as severely abnormal; with hybrid NNS, more cases were cytologically diagnosed as low-grade. For a threshold value > or = HSIL (high-grade squamous intraepithelial lesions), the areas under the receiver operating characteristic (ROC) curves (AUC) were 81% (95% CI, 75-88%) for pure NNS vs. 78% (95% CI, 75-81%) for hybrid NNS. For low-grade squamous intraepithelial lesions (LSIL), the AUC was significantly higher for hybrid NNS (81%; 95% CI, 77-85%) than for pure NNS (75%; 95% CI, 70-80%). Pure NNS provides optimized prediction of HSIL cases or negative outcome. For the detection of LSIL, light microscopy has additional value.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1002/dc.1093 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Recurrent neural network-aided processing of incomplete free induction decays in H-MRS of the brain.
J Magn Reson
November 2024
Department of Radiology, Seoul National University Hospital, Seoul, South Korea; Department of Medical Sciences, Seoul National University, Seoul, South Korea. Electronic address:
Article Synopsis
- Researchers explored using recurrent neural networks (RNNs) to process incomplete free induction decays (FIDs) in proton magnetic resonance spectroscopy (H-MRS) for brain metabolite quantification.
- They developed two types of RNNs: one that restores incomplete FIDs (rRNN) and another that directly quantifies metabolites from these incomplete data (cRNN).
- Both methods showed strong correlations with traditional quantification techniques on in vivo data but require further improvements for metabolites with low to medium signal-to-noise ratios.
Visualization of Solvent Effect and Oxygen Content via a Red Room-Temperature Phosphorescent Material.
ACS Appl Mater Interfaces
August 2024
Key Laboratory for Advanced Materials and Feringa Nobel Prize Scientist Joint Research Center, Frontiers Science Center for Materiobiology and Dynamic Chemistry, School of Chemistry and Molecular Engineering, East China University of Science and Technology, Meilong Road 130, Shanghai 200237, China.
The development of pure organic room-temperature phosphorescent (RTP) materials greatly facilitates the integrated application of luminescent materials. Herein, a type of photoactivated red RTP material was constructed by simply doping 4-(benzo[][1,2,5]thiadiazol-5-ylthio)benzonitrile (p-NNS) into a poly(methyl methacrylate) (PMMA) matrix. The obtained film realized a controllable photoactivation process by regulation of diverse solvent levels, demonstrating potential advantages in optical anti-counterfeiting applications.
View Article and Find Full Text PDFCharacterization of the Coordination and Solvation Dynamics of Solvated Systems─Implications for the Analysis of Molecular Interactions in Solutions and Pure HO.
J Chem Theory Comput
April 2024
Institute of General, Inorganic and Theoretical Chemistry Center for Chemistry and Biomedicine, University of Innsbruck Innrain 80-82, A-6020 Innsbruck, Austria.
The characterization of solvation shells of atoms, ions, and molecules in solution is essential to relate solvation properties to chemical phenomena such as complex formation and reactivity. Different definitions of the first-shell coordination sphere from simulation data can lead to potentially conflicting data on the structural properties and associated ligand exchange dynamics. The definition of a solvation shell is typically based on a given threshold distance determined from the respective solute-solvent pair distribution function () (i.
View Article and Find Full Text PDFModification of a Common β-diketiminate NacNac Framework via Sequential Lithiation and Small Molecule Insertion.
Chemistry
March 2024
Department of Pure and Applied Chemistry, University of Strathclyde, Glasgow, G1 1XL, UK.
A widely utilised class of ligands in synthesis and catalysis, β-diketiminate (BDI) or NacNac compounds were initially considered innocent in the sense that they remained intact in all their applications. That changed when the γ-C-H unit of their NCCCN backbone was found to engage in reactions with electrophiles. Here, we show that this special reactivity can be used advantageously to prepare tripodal modifications of the common NacNac ligand derived from 2,6-diisopropylphenyl-β-methyldiketimine [NacNacH (Me, Dipp)].
View Article and Find Full Text PDFDe Rham compatible Deep Neural Network FEM.
Neural Netw
August 2023
IWR, Universität Heidelberg, Im Neuenheimer Feld 205, 69120 Heidelberg, Germany. Electronic address:
On general regular simplicial partitions T of bounded polytopal domains Ω⊂R, d∈{2,3}, we construct exact neural network (NN) emulations of all lowest order finite element spaces in the discrete de Rham complex. These include the spaces of piecewise constant functions, continuous piecewise linear (CPwL) functions, the classical "Raviart-Thomas element", and the "Nédélec edge element". For all but the CPwL case, our network architectures employ both ReLU (rectified linear unit) and BiSU (binary step unit) activations to capture discontinuities.
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!