Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networ...Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.展开更多
Background Little is known regarding the association of changes in blood pressure level with risk of allcause and cardiovascular disease(CVD) mortality in young adults. Methods This cohort study from the 1999-2006 Nat...Background Little is known regarding the association of changes in blood pressure level with risk of allcause and cardiovascular disease(CVD) mortality in young adults. Methods This cohort study from the 1999-2006 National Health and Nutrition Examination Survey(NHANES) consisted of 9977 adults aged from 18 to 40 years by following up until the date of death or December 31, 2015. Participants were categorized by blood pressure readings using the blood pressure classification of the 2017 American College of Cardiology/American Heart Association(ACC/AHA) High Blood Pressure Clinical Practice Guidelines: normal(systolic, <120 mm Hg;diastolic, <80 mm Hg), elevated(systolic, 120-129 mm Hg;diastolic, <80 mm Hg), and hypertension(systolic,≥130 mm Hg;diastolic,≥80 mm Hg). Multivariable Cox proportional hazard models yielded adjusted hazard ratios(HRs) and 95% confidence intervals(CIs) of CVD and all-cause mortality. Results A total of 8356 participants(median age, 26.63 ± 7.01, 3758 women [44.97%]), of whom 265(3.17%) all-cause and 10(0.12%)CVD mortality were observed during a median follow-up duration of 152.96 ± 30.45 months. All-cause mortality incidence rates for normal blood pressure, elevated blood pressure, and hypertension were 172(2.91%), 43(3.52%), and 50(4.10%), respectively. With the normal blood pressure group being a reference, from elevated blood pressure to hypertension group, adjusted HRs for all-cause mortality were 1.24(95% CI, 0.63-2.42) and1.52(95% CI, 0.83-2.80)(P=0.162) after adjustment for potential confounders. Conclusions Among young adults, those with elevated blood pressure and hypertension, compared with those with normal blood pressure before the age of 40, as defined by the blood pressure classification in the 2017 ACC/AHA guidelines, are not significantly associated with increased risk of subsequent all-cause mortality.[S Chin J Cardiol 2019;20(4):201-210]展开更多
Blood cell disorders are among the leading causes of serious diseases such as leukemia,anemia,blood clotting disorders,and immune-related conditions.The global incidence of hematological diseases is increasing,affecti...Blood cell disorders are among the leading causes of serious diseases such as leukemia,anemia,blood clotting disorders,and immune-related conditions.The global incidence of hematological diseases is increasing,affecting both children and adults.In clinical practice,blood smear analysis is still largely performed manually,relying heavily on the experience and expertise of laboratory technicians or hematologists.This manual process introduces risks of diagnostic errors,especially in cases with rare or morphologically ambiguous cells.The situation is more critical in developing countries,where there is a shortage of specialized medical personnel and limited access to modern diagnostic tools.High testing costs and delays in diagnosis hinder access to quality healthcare services.In this context,the integration of Artificial Intelligence(AI),particularly Explainable AI(XAI)based on deep learning,offers a promising solution for improving the accuracy,efficiency,and transparency of hematological diagnostics.In this study,we propose a Ghost Residual Network(GRsNet)integrated with XAI techniques such as Gradient-weighted Class Activation Mapping(Grad-CAM),Local Interpretable Model-Agnostic Explanations(LIME),and SHapley Additive exPlanations(SHAP)for automatic blood cell classification.These techniques provide visual explanations by highlighting important regions in the input images,thereby supporting clinical decision-making.The proposed model is evaluated on two public datasets:Naturalize 2K-PBC and Microscopic Blood Cell,achieving a classification accuracy of up to 95%.The results demonstrate the model’s strong potential for automated hematological diagnosis,particularly in resource-constrained settings.It not only enhances diagnostic reliability but also contributes to advancing digital transformation and equitable access to AI-driven healthcare in developing regions.展开更多
OBJECTIVE:To study the features of the distribution and differentiation ofTraditional Chinese Medicine(TCM)syndromes in patients with diabetic peripheral neuropathy(DPN).METHODS:We collected clinical data on illness c...OBJECTIVE:To study the features of the distribution and differentiation ofTraditional Chinese Medicine(TCM)syndromes in patients with diabetic peripheral neuropathy(DPN).METHODS:We collected clinical data on illness course,age,fasting blood glucose,saccharogenic hemoglobin,TCM syndromes,tongue,and pulse of238 DPN patients.Differentiated main syndromes(Yin deficiency and exuberant heat,invasion of spleen by damp-heat,deficiency of both Qi and Yins,and deficiency of both Yin and Yang)and accompanying syndromes(blood stasis and phlegm-dampness)of diabetes were also recorded.The features of DPN syndromes were then analyzed.RESULTS:Among the four main syndromes of diabetes,deficiency of both Yin and Yang was the most common in the 238 DPN patients,of which89%-96%had blood stasis.CONCLUSION:The method of differentiating syndromes of diabetes can be applied to DPN patients.Deficiency of both Yin and Yang,often accompanied by blood stasis,is commonly seen.展开更多
基金the Deanship of Graduate Studies and Scientific Research at Najran University,Saudi Arabia,for their financial support through the Easy Track Research program,grant code(NU/EFP/MRC/13).
文摘Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.
基金supported by the Science and Technology Program of Guangzhou(No.201604020143/No.201604020018/No.201604020186/No.201803040012)the National Key Research and Development Program of China(No.2017FYC1307603/No.2016YFC1301305)the Key Area R&D Program of Guangdong Province(No.2019B020227005)
文摘Background Little is known regarding the association of changes in blood pressure level with risk of allcause and cardiovascular disease(CVD) mortality in young adults. Methods This cohort study from the 1999-2006 National Health and Nutrition Examination Survey(NHANES) consisted of 9977 adults aged from 18 to 40 years by following up until the date of death or December 31, 2015. Participants were categorized by blood pressure readings using the blood pressure classification of the 2017 American College of Cardiology/American Heart Association(ACC/AHA) High Blood Pressure Clinical Practice Guidelines: normal(systolic, <120 mm Hg;diastolic, <80 mm Hg), elevated(systolic, 120-129 mm Hg;diastolic, <80 mm Hg), and hypertension(systolic,≥130 mm Hg;diastolic,≥80 mm Hg). Multivariable Cox proportional hazard models yielded adjusted hazard ratios(HRs) and 95% confidence intervals(CIs) of CVD and all-cause mortality. Results A total of 8356 participants(median age, 26.63 ± 7.01, 3758 women [44.97%]), of whom 265(3.17%) all-cause and 10(0.12%)CVD mortality were observed during a median follow-up duration of 152.96 ± 30.45 months. All-cause mortality incidence rates for normal blood pressure, elevated blood pressure, and hypertension were 172(2.91%), 43(3.52%), and 50(4.10%), respectively. With the normal blood pressure group being a reference, from elevated blood pressure to hypertension group, adjusted HRs for all-cause mortality were 1.24(95% CI, 0.63-2.42) and1.52(95% CI, 0.83-2.80)(P=0.162) after adjustment for potential confounders. Conclusions Among young adults, those with elevated blood pressure and hypertension, compared with those with normal blood pressure before the age of 40, as defined by the blood pressure classification in the 2017 ACC/AHA guidelines, are not significantly associated with increased risk of subsequent all-cause mortality.[S Chin J Cardiol 2019;20(4):201-210]
文摘Blood cell disorders are among the leading causes of serious diseases such as leukemia,anemia,blood clotting disorders,and immune-related conditions.The global incidence of hematological diseases is increasing,affecting both children and adults.In clinical practice,blood smear analysis is still largely performed manually,relying heavily on the experience and expertise of laboratory technicians or hematologists.This manual process introduces risks of diagnostic errors,especially in cases with rare or morphologically ambiguous cells.The situation is more critical in developing countries,where there is a shortage of specialized medical personnel and limited access to modern diagnostic tools.High testing costs and delays in diagnosis hinder access to quality healthcare services.In this context,the integration of Artificial Intelligence(AI),particularly Explainable AI(XAI)based on deep learning,offers a promising solution for improving the accuracy,efficiency,and transparency of hematological diagnostics.In this study,we propose a Ghost Residual Network(GRsNet)integrated with XAI techniques such as Gradient-weighted Class Activation Mapping(Grad-CAM),Local Interpretable Model-Agnostic Explanations(LIME),and SHapley Additive exPlanations(SHAP)for automatic blood cell classification.These techniques provide visual explanations by highlighting important regions in the input images,thereby supporting clinical decision-making.The proposed model is evaluated on two public datasets:Naturalize 2K-PBC and Microscopic Blood Cell,achieving a classification accuracy of up to 95%.The results demonstrate the model’s strong potential for automated hematological diagnosis,particularly in resource-constrained settings.It not only enhances diagnostic reliability but also contributes to advancing digital transformation and equitable access to AI-driven healthcare in developing regions.
基金Supported by the National Fund of Natural Sciences(No.81173445)
文摘OBJECTIVE:To study the features of the distribution and differentiation ofTraditional Chinese Medicine(TCM)syndromes in patients with diabetic peripheral neuropathy(DPN).METHODS:We collected clinical data on illness course,age,fasting blood glucose,saccharogenic hemoglobin,TCM syndromes,tongue,and pulse of238 DPN patients.Differentiated main syndromes(Yin deficiency and exuberant heat,invasion of spleen by damp-heat,deficiency of both Qi and Yins,and deficiency of both Yin and Yang)and accompanying syndromes(blood stasis and phlegm-dampness)of diabetes were also recorded.The features of DPN syndromes were then analyzed.RESULTS:Among the four main syndromes of diabetes,deficiency of both Yin and Yang was the most common in the 238 DPN patients,of which89%-96%had blood stasis.CONCLUSION:The method of differentiating syndromes of diabetes can be applied to DPN patients.Deficiency of both Yin and Yang,often accompanied by blood stasis,is commonly seen.
