Medicine & Health

455 items

British Journal of Radiology Oct 1, 2026
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
Integrating AI quantitative CT, photon-counting CT, and FFR-CT brings coronary plaque burden and ischemia assessment into one CCTA workflow
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
This review surveys recent advances in coronary CT angiography (CCTA) for coronary artery disease: AI-driven plaque and stenosis quantification can cut analysis time from over 25 minutes to typically under 60 seconds per case with correlation coefficients of 0.92-0.95 against intravascular ultrasound, photon-counting detector CT (PCD-CT) reduces calcium blooming at ultra-high resolution and reclassifies some cases to lower CAD-RADS categories, and FFR-CT adds noninvasive lesion-specific physiologic assessment, so that combining the three can support more refined risk stratification for major adverse cardiovascular events and preventive therapy decisions.
SMU Scholar (Southern Methodist University) Oct 1, 2026
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
Huang Cheng's dissertation proposes a multimodal retinal AI framework for glaucoma and contributes datasets including GSS-RetVein
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
This dissertation integrates multimodal retinal imaging, including fundus photography, OCT, and OCTA, to build a suite of deep learning frameworks spanning vessel segmentation networks, biomarker discovery pipelines, and multimodal fusion models for detecting early glaucomatous changes with high precision, robustness, and interpretability, and contributes several curated datasets including GSS-RetVein as standardized benchmarks for cross-domain validation, reporting that the proposed models outperform existing state-of-the-art approaches across multiple public and clinical datasets with marked improvements in diagnostic sensitivity and specificity.
Diabetes Oct 1, 2026
In 24,638 UK Biobank participants with prediabetes, LASSO and elastic net selection of nuclear magnetic resonance metabolomic markers yielded 16 biomarkers, and k-means clustering in the training set (12,322 participants) identified low-, intermediate-, and high-metabolic-risk subtypes that showed progressively higher risks of type 2 diabetes, cardiovascular disease, and chronic kidney disease in the validation set (12,316 participants), with diet-quality associations differing across subtypes and Mendelian randomization suggesting potential causal links for several metabolomic biomarkers.
In 24,638 UK Biobank participants with prediabetes, LASSO and elastic net selection of nuclear magnetic resonance metabolomic markers yielded 16 biomarkers, and k-means clustering in the training set (12,322 participants) identified low-, intermediate-, and high-metabolic-risk subtypes that showed progressively higher risks of type 2 diabetes, cardiovascular disease, and chronic kidney disease in the validation set (12,316 participants), with diet-quality associations differing across subtypes and Mendelian randomization suggesting potential causal links for several metabolomic biomarkers.
Metabolomic clustering of 24,638 UK Biobank participants with prediabetes yields three subtypes with progressively higher type 2 diabetes, cardiovascular, and chronic kidney disease risk
In 24,638 UK Biobank participants with prediabetes, LASSO and elastic net selection of nuclear magnetic resonance metabolomic markers yielded 16 biomarkers, and k-means clustering in the training set (12,322 participants) identified low-, intermediate-, and high-metabolic-risk subtypes that showed progressively higher risks of type 2 diabetes, cardiovascular disease, and chronic kidney disease in the validation set (12,316 participants), with diet-quality associations differing across subtypes and Mendelian randomization suggesting potential causal links for several metabolomic biomarkers.
In 24,638 UK Biobank participants with prediabetes, LASSO and elastic net selection of nuclear magnetic resonance metabolomic markers yielded 16 biomarkers, and k-means clustering in the training set (12,322 participants) identified low-, intermediate-, and high-metabolic-risk subtypes that showed progressively higher risks of type 2 diabetes, cardiovascular disease, and chronic kidney disease in the validation set (12,316 participants), with diet-quality associations differing across subtypes and Mendelian randomization suggesting potential causal links for several metabolomic biomarkers.
发表出处待核验 Oct 1, 2026
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
A radiomics model automatically separated thermograms of 98 CRPS patients from 56 healthy controls with AUC 0.93, outperforming three clinicians
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).
Archivos Argentinos de Pediatria Oct 1, 2026
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
AI model reached only 0.56 accuracy on seven-category BITSS infant stool grading, rising to 0.76 when collapsed to four groups
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
Using 1312 photographs of infant stool in diapers (1100 meeting quality criteria, of which 896 had majority agreement among three pediatric gastroenterologists as the reference set), the study trained 20 convolutional neural network models on Teachable Machine with an 85/15 training and internal-validation split and assessed agreement with specialists on the BITSS: the best seven-category model reached overall accuracy 0.56 with linear and quadratic weighted Kappa of 0.59 and 0.75, while a four-category grouping (constipated, formed, soft, liquid) reached accuracy 0.76 with weighted Kappa of 0.69 and 0.78, whereas agreement among the three specialists showed a Fleiss Kappa of only 0.24 and 24.7% complete agreement.
American Journal of Respiratory Cell and Molecular Biology Oct 1, 2026
Saavedra and colleagues used CITE-seq to profile circulating CD3+ T cells from 18 adults with cystic fibrosis before and after starting elexacaftor-tezacaftor-ivacaftor (ETI), finding CFTR modulation induces transcriptional reprogramming most pronounced in CD4+ memory T cells (upregulation of PNP and MT1X, enrichment of mitochondrial metabolism and oxidative phosphorylation pathways, and decline in chromatin remodeling and inflammatory activation genes), while Seahorse metabolic flux analysis, splenocytes from CFTR F508del homozygous mice, and CRISPR-Cas9 knockdown of CFTR in primary human lymphocytes all show reduced oxygen consumption, glycolytic capacity, and ATP production in CF lymphocytes, and changes in CD4+ memory T cell gene expression correlate with FEV1 improvement and reduced h
Saavedra and colleagues used CITE-seq to profile circulating CD3+ T cells from 18 adults with cystic fibrosis before and after starting elexacaftor-tezacaftor-ivacaftor (ETI), finding CFTR modulation induces transcriptional reprogramming most pronounced in CD4+ memory T cells (upregulation of PNP and MT1X, enrichment of mitochondrial metabolism and oxidative phosphorylation pathways, and decline in chromatin remodeling and inflammatory activation genes), while Seahorse metabolic flux analysis, splenocytes from CFTR F508del homozygous mice, and CRISPR-Cas9 knockdown of CFTR in primary human lymphocytes all show reduced oxygen consumption, glycolytic capacity, and ATP production in CF lymphocytes, and changes in CD4+ memory T cell gene expression correlate with FEV1 improvement and reduced h
Saavedra et al. find that restoring CFTR with ETI shifts CD4+ memory T cells in CF toward oxidative metabolism, with metabolic gene changes linked to FEV1 improvement and fewer hospitalizations
Saavedra and colleagues used CITE-seq to profile circulating CD3+ T cells from 18 adults with cystic fibrosis before and after starting elexacaftor-tezacaftor-ivacaftor (ETI), finding CFTR modulation induces transcriptional reprogramming most pronounced in CD4+ memory T cells (upregulation of PNP and MT1X, enrichment of mitochondrial metabolism and oxidative phosphorylation pathways, and decline in chromatin remodeling and inflammatory activation genes), while Seahorse metabolic flux analysis, splenocytes from CFTR F508del homozygous mice, and CRISPR-Cas9 knockdown of CFTR in primary human lymphocytes all show reduced oxygen consumption, glycolytic capacity, and ATP production in CF lymphocytes, and changes in CD4+ memory T cell gene expression correlate with FEV1 improvement and reduced h
Saavedra and colleagues used CITE-seq to profile circulating CD3+ T cells from 18 adults with cystic fibrosis before and after starting elexacaftor-tezacaftor-ivacaftor (ETI), finding CFTR modulation induces transcriptional reprogramming most pronounced in CD4+ memory T cells (upregulation of PNP and MT1X, enrichment of mitochondrial metabolism and oxidative phosphorylation pathways, and decline in chromatin remodeling and inflammatory activation genes), while Seahorse metabolic flux analysis, splenocytes from CFTR F508del homozygous mice, and CRISPR-Cas9 knockdown of CFTR in primary human lymphocytes all show reduced oxygen consumption, glycolytic capacity, and ATP production in CF lymphocytes, and changes in CD4+ memory T cell gene expression correlate with FEV1 improvement and reduced h
European Journal Pharmaceutical and Medical Research Oct 1, 2026
Using celecoxib as the model drug, this study applied a 2^3 factorial design to vary gelling agent type (Carbopol 934 vs. HPMC), liquid paraffin concentration (5.0% vs. 7.5% w/w), and emulsifier blend concentration (Tween 20/Span 20 at 1.5% vs. 2.5% w/w), prepared and characterized eight batches (F1–F8) of topical emulgel, and identified F6 (2.5% HPMC, 5% liquid paraffin, 2.5% surfactant) as optimal, with 93.2±1.2% cumulative in vitro release over 36 hours versus 45% for the standard formulation, release kinetics best fitted by the Higuchi diffusion model (R2=0.996), ex-vivo porcine skin cumulative transdermal delivery of 75.6±1.9% (4267±107 μg/cm2) with cutaneous retention of 12.8±1.
Using celecoxib as the model drug, this study applied a 2^3 factorial design to vary gelling agent type (Carbopol 934 vs. HPMC), liquid paraffin concentration (5.0% vs. 7.5% w/w), and emulsifier blend concentration (Tween 20/Span 20 at 1.5% vs. 2.5% w/w), prepared and characterized eight batches (F1–F8) of topical emulgel, and identified F6 (2.5% HPMC, 5% liquid paraffin, 2.5% surfactant) as optimal, with 93.2±1.2% cumulative in vitro release over 36 hours versus 45% for the standard formulation, release kinetics best fitted by the Higuchi diffusion model (R2=0.996), ex-vivo porcine skin cumulative transdermal delivery of 75.6±1.9% (4267±107 μg/cm2) with cutaneous retention of 12.8±1.
After 2^3 factorial optimization of a celecoxib topical emulgel, formulation F6 released 93.2% cumulatively over 36 hours and delivered 75.6% across porcine skin
Using celecoxib as the model drug, this study applied a 2^3 factorial design to vary gelling agent type (Carbopol 934 vs. HPMC), liquid paraffin concentration (5.0% vs. 7.5% w/w), and emulsifier blend concentration (Tween 20/Span 20 at 1.5% vs. 2.5% w/w), prepared and characterized eight batches (F1–F8) of topical emulgel, and identified F6 (2.5% HPMC, 5% liquid paraffin, 2.5% surfactant) as optimal, with 93.2±1.2% cumulative in vitro release over 36 hours versus 45% for the standard formulation, release kinetics best fitted by the Higuchi diffusion model (R2=0.996), ex-vivo porcine skin cumulative transdermal delivery of 75.6±1.9% (4267±107 μg/cm2) with cutaneous retention of 12.8±1.
Using celecoxib as the model drug, this study applied a 2^3 factorial design to vary gelling agent type (Carbopol 934 vs. HPMC), liquid paraffin concentration (5.0% vs. 7.5% w/w), and emulsifier blend concentration (Tween 20/Span 20 at 1.5% vs. 2.5% w/w), prepared and characterized eight batches (F1–F8) of topical emulgel, and identified F6 (2.5% HPMC, 5% liquid paraffin, 2.5% surfactant) as optimal, with 93.2±1.2% cumulative in vitro release over 36 hours versus 45% for the standard formulation, release kinetics best fitted by the Higuchi diffusion model (R2=0.996), ex-vivo porcine skin cumulative transdermal delivery of 75.6±1.9% (4267±107 μg/cm2) with cutaneous retention of 12.8±1.
American Journal of Respiratory and Critical Care Medicine Oct 1, 2026
Using a myeloid-specific Tsc2 deletion mouse model that recapitulates key features of human cardiac sarcoidosis, and integrating single-cell RNA sequencing, bioinformatic analyses, histopathology, in vitro functional studies in murine and human macrophages, and in vivo pharmacologic inhibition, the study found that constitutive mTORC1 activation induces a fibrogenic macrophage (FibMac) population in the heart characterized by Cd63, Spp1, Gpnmb, and Fabp5 expression and arising through a TGF-β-dependent monocyte-to-FibMac differentiation process, and identified MMP12 as a macrophage-intrinsic inducer and dominant effector of this program: recombinant MMP12 was sufficient to enforce fibrogenic differentiation, clustering, and epithelioid features in mouse and human macrophages, whereas selec
Using a myeloid-specific Tsc2 deletion mouse model that recapitulates key features of human cardiac sarcoidosis, and integrating single-cell RNA sequencing, bioinformatic analyses, histopathology, in vitro functional studies in murine and human macrophages, and in vivo pharmacologic inhibition, the study found that constitutive mTORC1 activation induces a fibrogenic macrophage (FibMac) population in the heart characterized by Cd63, Spp1, Gpnmb, and Fabp5 expression and arising through a TGF-β-dependent monocyte-to-FibMac differentiation process, and identified MMP12 as a macrophage-intrinsic inducer and dominant effector of this program: recombinant MMP12 was sufficient to enforce fibrogenic differentiation, clustering, and epithelioid features in mouse and human macrophages, whereas selec
MMP12 identified as a macrophage-intrinsic driver of fibrosis: its inhibition reduces myocardial fibrosis and improves cardiac conduction
Using a myeloid-specific Tsc2 deletion mouse model that recapitulates key features of human cardiac sarcoidosis, and integrating single-cell RNA sequencing, bioinformatic analyses, histopathology, in vitro functional studies in murine and human macrophages, and in vivo pharmacologic inhibition, the study found that constitutive mTORC1 activation induces a fibrogenic macrophage (FibMac) population in the heart characterized by Cd63, Spp1, Gpnmb, and Fabp5 expression and arising through a TGF-β-dependent monocyte-to-FibMac differentiation process, and identified MMP12 as a macrophage-intrinsic inducer and dominant effector of this program: recombinant MMP12 was sufficient to enforce fibrogenic differentiation, clustering, and epithelioid features in mouse and human macrophages, whereas selec
Using a myeloid-specific Tsc2 deletion mouse model that recapitulates key features of human cardiac sarcoidosis, and integrating single-cell RNA sequencing, bioinformatic analyses, histopathology, in vitro functional studies in murine and human macrophages, and in vivo pharmacologic inhibition, the study found that constitutive mTORC1 activation induces a fibrogenic macrophage (FibMac) population in the heart characterized by Cd63, Spp1, Gpnmb, and Fabp5 expression and arising through a TGF-β-dependent monocyte-to-FibMac differentiation process, and identified MMP12 as a macrophage-intrinsic inducer and dominant effector of this program: recombinant MMP12 was sufficient to enforce fibrogenic differentiation, clustering, and epithelioid features in mouse and human macrophages, whereas selec
American Journal of Respiratory and Critical Care Medicine Oct 1, 2026
An international multidisciplinary working group of 41 experts systematically reviewed 922 citations up to March 17, 2025, revised the 2016 acute exacerbation (AE) definition—previously limited to idiopathic pulmonary fibrosis (IPF)—into an AE-fILD definition applicable across all fibrotic interstitial lung diseases (anchored in diffuse alveolar damage with or without organizing pneumonia), proposed the broader concept of acute respiratory worsening (ARW) to capture acute deteriorations not attributable to DAD, and summarized evidence on epidemiology, risk factors, prognosis, and management while discussing AE as a clinical trial endpoint.
An international multidisciplinary working group of 41 experts systematically reviewed 922 citations up to March 17, 2025, revised the 2016 acute exacerbation (AE) definition—previously limited to idiopathic pulmonary fibrosis (IPF)—into an AE-fILD definition applicable across all fibrotic interstitial lung diseases (anchored in diffuse alveolar damage with or without organizing pneumonia), proposed the broader concept of acute respiratory worsening (ARW) to capture acute deteriorations not attributable to DAD, and summarized evidence on epidemiology, risk factors, prognosis, and management while discussing AE as a clinical trial endpoint.
After reviewing 922 citations, 41 international experts extended the acute exacerbation definition from IPF to all fibrotic interstitial lung diseases and proposed a new acute respiratory worsening framework
An international multidisciplinary working group of 41 experts systematically reviewed 922 citations up to March 17, 2025, revised the 2016 acute exacerbation (AE) definition—previously limited to idiopathic pulmonary fibrosis (IPF)—into an AE-fILD definition applicable across all fibrotic interstitial lung diseases (anchored in diffuse alveolar damage with or without organizing pneumonia), proposed the broader concept of acute respiratory worsening (ARW) to capture acute deteriorations not attributable to DAD, and summarized evidence on epidemiology, risk factors, prognosis, and management while discussing AE as a clinical trial endpoint.
An international multidisciplinary working group of 41 experts systematically reviewed 922 citations up to March 17, 2025, revised the 2016 acute exacerbation (AE) definition—previously limited to idiopathic pulmonary fibrosis (IPF)—into an AE-fILD definition applicable across all fibrotic interstitial lung diseases (anchored in diffuse alveolar damage with or without organizing pneumonia), proposed the broader concept of acute respiratory worsening (ARW) to capture acute deteriorations not attributable to DAD, and summarized evidence on epidemiology, risk factors, prognosis, and management while discussing AE as a clinical trial endpoint.
Journal of Cataract & Refractive Surgery Oct 1, 2026
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
Two-center study of 127 nuclear cataract cases: AS-OCT image features correlate with LOCS III grading, with automated grading accuracy of 0.81 and 0.87
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.
This two-center clinical validation study recruited 127 individuals with different severities of nuclear cataract from Thailand (n = 81) and Shenzhen, China (n = 46), imaged them with AS-OCT and graded images under the LOCS III standard, developed automated machine learning models to extract nuclear region annotation and analyzed feature-based quantifiers, finding that pixel-based features such as mean, variance, root mean square, interquartile range, and percentiles significantly correlate with NC grading (P < .01), that variance, standard deviation, and median showed high consistency while kurtosis and skewness were negatively correlated, and that the prediction model achieved 0.81 accuracy at the SZRM center (F1 0.82) and 0.87 at the Thai center (F1 0.

Page 3 · showing 10