№ lp_2_1_21544
File format: docx
Character count: 14015
File size: 5244 KB
Supplementary scientific appendix presenting CT image preprocessing protocols, body composition thresholds, radiomics feature selection procedures, and comparative performance results of multiple machine learning models across training and validation cohorts.
Document type:
Supplementary materials
Subject:
Radiomics feature extraction and machine learning model evaluation
Imaging modality:
Computed tomography (CT)
Preprocessing methods:
Intensity normalization, gray-level discretization, Gaussian transform, wavelet transform, voxel resampling
Voxel size:
1×1×1 mm³
Feature selection method:
mRMR algorithm with 1000-fold bootstrap resampling
Dimensionality reduction:
LASSO regression analysis
Model interpretation:
SHAP analysis
Machine learning algorithms:
LR, SVM, RF, ExtraTrees, LightGBM, MLP
Evaluation metrics:
AUC, ACC, SEN, SPE, PPV, NPV
Validation cohorts:
Training set, internal validation, external validation
Variables included:
Intra-radiomics features, Peri-radiomics features, Intra-Peri-radiomics features, body composition indices (VFI, SFI, SMI, IMFI, SMD, VSR, VMR)
Tables:
S1–S4
Figures:
S1–S11
Pagination:
Pages 2–14
Price: 8 / 10 USD
The file will be delivered to the email address provided at checkout within 12 hours.
The file will be delivered to the email address provided at checkout within 12 hours.
Don’t have cryptocurrency yet?
You can still complete your purchase in a few minutes:- Buy Crypto in a trusted app (Coinbase, Kraken, Cash App or any similar service).
- In the app, tap Send.
- Select network, paste our wallet address.
- Send the exact amount shown above.
The final amount may vary slightly depending on the payment method.
The file will be sent to the email address provided at checkout within 24 hours.
The product description is provided for reference. Actual content and formatting may differ slightly.
Year:
2023
Region / City:
Lexington, KY
Topic:
Environmental Conservation, Agricultural Programs
Document Type:
News Release
Organization / Institution:
USDA NRCS
Author:
USDA NRCS
Target Audience:
Landowners, Farmers, Agricultural Producers
Validity Period:
October 2, 2022 – November 3, 2023
Approval Date:
October 2, 2022
Amendment Date:
Not provided
Bid No:
SPO-11-506-FINAL
Year:
2026
Region / City:
North Carolina
Theme:
Real Estate, Procurement
Document Type:
Solicitation, Proposal
Organization:
North Carolina Department of Transportation, North Carolina Department of Information Technology
Author:
State of North Carolina
Target Audience:
Vendors, Contractors
Period of Validity:
February 6, 2026
Date of Approval:
February 6, 2026
Date of Changes:
None
Year:
2026
Field:
Neuroimaging / Cognitive Neuroscience
Document Type:
Supplementary Material
Institution:
University or Research Laboratory (not specified)
Methods:
fMRI preprocessing, longitudinal registration, ROI computation
Software:
SPM12, CAT12, DARTEL
Brain Regions:
PFC-PPC, PFC-BG, frontal pole, anterior cingulate cortex, basal ganglia, inferior frontal junction, dorsolateral prefrontal cortex, ventrolateral prefrontal cortex, superior and inferior parietal lobules
Data Resolution:
2 x 2 x 2 mm³
Smoothing:
8-mm FWHM Gaussian kernel
Masking Threshold:
0.2
Year:
2026
Region / City:
Taigu, Shanxi, China
Subject:
Food science, food processing, rheology
Document Type:
Research article
Institution:
Shanxi Agricultural University
Authors:
Tingting Sun, Huijun Yin, Lijing Yan, Xiaying Hao, Lihong Fu, Yaoxuan Jia, Xiaobin Li
Target Audience:
Food scientists, agricultural engineers
Keywords:
High-voltage pulsed electric field, Sanbai melon juice, rheological properties, fruit and vegetable juice, dynamic viscoelasticity
Abstract:
Study of the effect of high-voltage pulsed electric field pretreatment on the rheological properties of Sanbai melon juice, including shear viscosity and dynamic viscoelasticity.
Methodology:
Experimental analysis with two concentrations of Sanbai melon juice, measuring shear stress, viscosity at different temperatures, and viscoelastic properties.
Document type:
Supplementary materials
Research field:
Cognitive neuroscience
Topic:
Contamination obsessive-compulsive disorder and disgust conditioning
Methods:
fMRI data acquisition and preprocessing; stimulus selection; whole-brain analysis
Imaging modality:
Functional magnetic resonance imaging (fMRI)
MRI scanner:
Siemens Prisma 3.0T
Software:
E-prime 2.0
Stimulus categories:
Death; animals; food; hygiene; body products; envelope violations
Data formats:
DICOM; NIFTI
Preprocessing steps:
Conversion; slice timing correction; head movement correction; spatial segmentation; spatial alignment; spatial smoothing
Statistical analysis:
Whole-brain analysis with FWE correction
Figures:
Fig. S1; Fig. S2; Fig. S3; Fig. S5
Tables:
Table S1; Supplementary Table S2
References cited:
Burns et al. (1996); Foa et al. (2002); Gan et al. (2024); Haberkamp et al. (2017); Olatunji et al. (2007; 2015); Sydeman (2018); Wang et al. (2024)
Year:
2023
Region / City:
N/A
Topic:
MARC to BIBFRAME conversion
Document type:
Process documentation
Organization / Institution:
N/A
Author:
N/A
Target Audience:
Library professionals, cataloging staff
Effective period:
N/A
Approval date:
N/A
Modification date:
N/A
Year:
Not specified
Region / City:
Not specified
Topic:
Preprocessing methods for PLS-DA model
Document Type:
Supplementary material
Organization / Institution:
Not specified
Author:
Not specified
Target Audience:
Researchers in data analysis and preprocessing
Period of Validity:
Not specified
Approval Date:
Not specified
Date of Modifications:
Not specified
Year:
2020
Region / City:
Not specified
Topic:
Deep learning, convolutional neural networks, survival analysis, radiomics
Document type:
Scientific article
Institution / Organization:
Not specified
Author:
He Kaiming, Sanghyun Woo, Zwanenburg A et al.
Target audience:
Researchers in machine learning, medical imaging, and survival analysis
Period of validity:
Not specified
Approval date:
Not specified
Date of changes:
Not specified
Document type:
Supplementary material
Subject:
CT radiomics analysis of ground-glass nodules (GGNs)
Imaging modality:
Computed tomography (CT)
Slice thickness:
3 mm; 1 mm
Study groups:
Benign GGNs (n = 23); Malignant GGNs (n = 92); Adenocarcinoma group (n = 92; n = 54 for 1 mm CT)
Statistical methods:
Propensity score matching; Logistic regression model; LASSO algorithm; 10-fold cross-validation; ROC analysis; Intraclass correlation coefficient (ICC)
Matching ratio:
1:4
C-statistic:
0.7261
Matching method:
Greed matching within specified caliper distances
Distance metric:
0.7
Use of replacement:
With replacement
Feature categories:
Conventional indices; First order features; Second order features (GLCM, GLRLM, NGLDM, GLZLM)
Outcome measures:
AUC value; Rad-score; P-values for texture feature comparison
Year:
2026
Region:
Multicenter
Subject:
Medical imaging, radiomics
Document type:
Supplementary table
Institution:
Imaging Biomarker Standardization Initiative (IBSI)
Software used:
ITK-SNAP 4.0.1, nnU-Net v2, Python 3.9, Pyradiomics 3.1.0
Imaging modality:
Computed tomography (CT)
Patient preparation:
Fasting state
Contrast agent:
Iodinated
Segmentation method:
Manual modification and automatic segmentation
Radiomics features:
First Order Statistics, shape features, GLCM, GLDM, GLRLM, GLSZM, NGTDM
Data format:
DICOM converted to NIfTI
ROI delineation:
Liver and spleen
Experts involved:
2 radiologists with cross-validation by 1 senior radiologist
Acquisition phases:
Arterial, venous, delayed
Year:
2026
Region:
International (data from China and Western medical centers)
Subject:
Lung adenocarcinoma, radiomics, medical imaging, PET/CT
Document type:
Research supplementary material
Institution:
Philips Healthcare, Siemens Healthineers, GE Medical Systems
Authors:
Not explicitly listed in the text
Patient cohort:
Clinical IA stage lung adenocarcinoma patients
Imaging modalities:
CT, PET/CT
Radiomics features extracted:
1,709 features including shape, first-order, GLCM, GLRLM, GLSZM, GLDM
Model types:
CT-signs model, CT/PET radiomics models, Hybrid models with late and early fusion
Outcome measures:
Invasive adenocarcinoma vs AIS/MIA, high-risk vs low-risk histopathology, EGFR mutation prediction
Data processing tools:
SimpleITK, Python, Pyradiomics, H2O.ai auto-ML
Voxel size for resampling:
2×2×2 mm
Date of examination:
Not specified
Blood glucose threshold:
<6.6 mmol/L
Radiopharmaceutical:
[18F]FDG, purity >95%
Scan parameters:
CT 120 kV/80 mA, PET 3 min per bed, voxel sizes and matrix dimensions specified
Year:
2021-2023
Country:
China
Region / City:
Changsha, Hunan
Topic:
Hepatocellular carcinoma, microvascular invasion prediction
Document type:
Research article
Institution:
Hunan Provincial People’s Hospital and The First Affiliated Hospital of Hunan Normal University
Authors:
Chuanlin Yu, QianBiao Gu, Peng Liu, YaQiong He
Corresponding author:
YaQiong He
Methodology:
Retrospective analysis, dual-energy CT, radiomics, logistic regression
Sample size:
145 patients
Cohorts:
Training cohort 101 cases, validation cohort 44 cases
Clinical features analyzed:
Gender, tumor size, laboratory tests
Imaging features analyzed:
DECT quantitative parameters, portal venous phase, virtual monoenergetic images
Outcome measures:
Microvascular invasion (MVI) prediction
Key findings:
Combined clinical-radiomics model shows highest predictive performance for MVI
Application:
Preoperative prediction in hepatocellular carcinoma patients
Type of source:
Scientific research article
Year:
2021
Region / City:
Guangzhou and Chengdu, China
Topic:
Hepatocellular carcinoma, transarterial chemoembolization, radiomics
Document Type:
Original research article
Institution:
Nanfang Hospital, Southern Medical University; Affiliated Hospital of Chengdu University
Authors:
Xiang-Ke Niu, Xiao-Feng He
Target Audience:
Medical researchers, interventional radiologists, oncologists
Study Period:
March 2009 – March 2016
Received Date:
November 2, 2020
Revised Date:
December 7, 2020
Accepted Date:
December 16, 2020
Published Online:
January 14, 2021
Funding:
Health and Family Planning Commission of Sichuan Province, China, No. 17PJ430 and No. 18PJ150
Methodology:
Retrospective study, CT-based radiomics analysis, nomogram construction, validation with external cohort
Sample Size:
Training dataset n = 137; Validation dataset n = 81
Key Findings:
CT-based radiomics nomogram predicts TACE refractoriness and stratifies patients into high- and low-risk groups with different survival outcomes
Keywords:
Hepatocellular carcinoma, Transarterial chemoembolization, Refractoriness, Radiomics, Nomogram, Computed tomography