Journal: Brain Sciences

Article Title: Diffusion Measures of Subcortical Structures Using High-Field MRI

doi: 10.3390/brainsci13030391

Figure Lengend Snippet: Basic processing Lead−connectome pipeline. Minimally preprocessed human connectome project images are co-registered to the structural T1w image using SPM. Structural images are registered to templates using ANTs registration, generating inverse transforms to translate MNI PD25 template to b0 space. DSI Studio is used to apply Q−sampling on diffusion images to reconstruct diffusion orientations and generate diffusion network statistics of segmented ROIs and ROI diffusion connectivity.

Article Snippet: LEAD Connectome, a MATLAB-based structural connectomic analysis pipeline which utilizes DSI studio for generalized Q-ball imaging (GQI), was used to generate structural connectome for each 3T and 7T acquisition [ ].

Techniques: Sampling, Diffusion-based Assay

Journal: Brain Sciences

Article Title: Diffusion Measures of Subcortical Structures Using High-Field MRI

doi: 10.3390/brainsci13030391

Figure Lengend Snippet: Connectivity matrices of significant, FDR−corrected mean differences of diffusion measures, FA, MD, QA, between 3T and 7T connectomes. Positive values (near red on the color bar) represent higher value of 3T mean diffusion measure while negative values (near dark blue on the color bar) represent higher value of 7T mean diffusion measure. Insignificant values were set to 0.

Article Snippet: LEAD Connectome, a MATLAB-based structural connectomic analysis pipeline which utilizes DSI studio for generalized Q-ball imaging (GQI), was used to generate structural connectome for each 3T and 7T acquisition [ ].

Techniques: Diffusion-based Assay

Journal: ERJ Open Research

Article Title: Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study

doi: 10.1183/23120541.00968-2023

Figure Lengend Snippet: Proposed methods. Machine-learning (ML) models were constructed using different combinations of five demographic, eight quantitative computed tomography (qCT) and 95 texture-based CT radiomics measurements. The dataset was split into a 5-fold cross-validation training dataset (75% of the data) and testing dataset (25% of the data). The training dataset was used with feature selection methods to select five features, which were then input into a ML classifier to be trained. The ML models were then tested with the testing dataset for COPD status and COPD severity classification. ROC: receiver operating characteristic; SHAP: SHapely Additive exPlanations.

Article Snippet: To extract the texture-based CT radiomic features, an in-house-developed pipeline that uses the Standardized Environment for Radiomics Analysis [ ] (MATLAB-based framework) was constructed to calculate the features in compliance with the Image Biomarker Standardisation Initiative (IBSI) [ ].

Techniques: Construct, Computed Tomography, Biomarker Discovery, Selection

Journal: ERJ Open Research

Article Title: Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study

doi: 10.1183/23120541.00968-2023

Figure Lengend Snippet: Models comparing the impact of the addition of texture-based radiomics to conventional measurements (demographics and qCT features) for classifying COPD status and COPD severity in the testing dataset

Article Snippet: To extract the texture-based CT radiomic features, an in-house-developed pipeline that uses the Standardized Environment for Radiomics Analysis [ ] (MATLAB-based framework) was constructed to calculate the features in compliance with the Image Biomarker Standardisation Initiative (IBSI) [ ].

Techniques:

Journal: ERJ Open Research

Article Title: Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study

doi: 10.1183/23120541.00968-2023

Figure Lengend Snippet: Receiver operating characteristic curves and SHapely Additive exPlanations (SHAP) analysis for COPD status with different input feature set combinations. qCT: quantitative computed tomography; AUC: area under the receiver operating characteristic curve; HU 15 : 15th percentile of the density histogram; TAC: total airway count; LAC: low-attenuation clusters; GLCM jointavg : grey-level co-occurrence matrix (GLCM) joint average; GLDZM zdentr : grey-level distance zone matrix (GLDZM) zone distance entropy; GLDZM ldlge : GLDZM large distance low grey-level emphasis; GLDZM zdnunorm : GLDZM zone distance non-uniformity normalised. # : significantly different AUC from demographics and qCT model; ¶ : significantly different AUC from demographics and texture-based radiomics model.

Article Snippet: To extract the texture-based CT radiomic features, an in-house-developed pipeline that uses the Standardized Environment for Radiomics Analysis [ ] (MATLAB-based framework) was constructed to calculate the features in compliance with the Image Biomarker Standardisation Initiative (IBSI) [ ].

Techniques: Computed Tomography

Journal: ERJ Open Research

Article Title: Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study

doi: 10.1183/23120541.00968-2023

Figure Lengend Snippet: Receiver operating characteristic curves and SHapely Additive exPlanations (SHAP) analysis for COPD severity with different input feature set combinations. qCT: quantitative computed tomography; AUC: area under the receiver operating characteristic curve; NJC: normalised join count; TAC: total airway count; WA%: wall area %; GLDZM zdnunorm : grey-level distance zone matrix (GLDZM) zone distance non-uniformity normalised; GLDZM ldlge : GLDZM large distance low grey-level emphasis; GLCM jointavg : grey-level co-occurrence matrix joint average; GLDZM zdnu : GLDZM zone distance non-uniformity. # : significantly different AUC from demographics and qCT model; ¶ : significantly different AUC from demographics and texture-based radiomics model.

Article Snippet: To extract the texture-based CT radiomic features, an in-house-developed pipeline that uses the Standardized Environment for Radiomics Analysis [ ] (MATLAB-based framework) was constructed to calculate the features in compliance with the Image Biomarker Standardisation Initiative (IBSI) [ ].

Techniques: Computed Tomography

Journal: ERJ Open Research

Article Title: Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study

doi: 10.1183/23120541.00968-2023

Figure Lengend Snippet: Pearson's correlation coefficients (r) for CT features (all qCT and texture-based radiomics selected in the machine-learning models) with baseline spirometry measurements for the whole cohort

Article Snippet: To extract the texture-based CT radiomic features, an in-house-developed pipeline that uses the Standardized Environment for Radiomics Analysis [ ] (MATLAB-based framework) was constructed to calculate the features in compliance with the Image Biomarker Standardisation Initiative (IBSI) [ ].

Techniques: