Objective:To explore a simple method for improving the diagnostic accuracy of malignant lung nodules based on imaging features of lung nodules.Methods:A retrospective analysis was conducted on the imaging data of 114 ...Objective:To explore a simple method for improving the diagnostic accuracy of malignant lung nodules based on imaging features of lung nodules.Methods:A retrospective analysis was conducted on the imaging data of 114 patients who underwent lung nodule surgery in the Thoracic Surgery Department of the First People’s Hospital of Huzhou from June to September 2024.Imaging features of lung nodules were summarized and trained using a BP neural network.Results:Training with the BP neural network increased the diagnostic accuracy for distinguishing between benign and malignant lung nodules based on imaging features from 84.2%(manual assessment)to 94.1%.Conclusion:Training with the BP neural network significantly improves the diagnostic accuracy of lung nodule malignancy based solely on imaging features.展开更多
The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study s...The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.展开更多
Objective: to explore the efficacy of low-dose chest CT scanning combined with KARL3D iterative reconstruction technique. Methods: 100 patients who underwent chest CT examination in our hospital were randomly selected...Objective: to explore the efficacy of low-dose chest CT scanning combined with KARL3D iterative reconstruction technique. Methods: 100 patients who underwent chest CT examination in our hospital were randomly selected as the analysis objects and randomly divided into four groups, each with 25 cases. Group A was reconstructed by FBP algorithm and the pipeline current was 150mA;. The low-dose groups B, C and D were reconstructed by Karl algorithm with tube currents of 80mas, 60mas and 40mas respectively. The radiation dose and subjective and objective scores of the four groups were compared. SPSS210 statistical software was used for data analysis. Results: the radiation dose of group B, C and D using low dose tube current combined with karl3d iterative reconstruction technique was lower than that of group a (p < 0.05);The difference between the objective assessment (SD, SNR) and subjective score of the four groups was all p>0.05. Conclusion: The combination of low-dose iterative reconstruction technique and Karl 3D chest CT scan can obtain good images and reduce radiation dose, which is worthy of promotion in the industry.展开更多
Objectives: The purpose of this study is to identify how to manage oversensing of pacemakers in chest CT. Methods: Four different models of pacemakers were examined to select the pacemaker generating oversensing. To t...Objectives: The purpose of this study is to identify how to manage oversensing of pacemakers in chest CT. Methods: Four different models of pacemakers were examined to select the pacemaker generating oversensing. To the pacemaker with oversensing, intermittent switching X-ray was exposed using ECG-gated CT helical scan system at prospective CTA mode. IVY Model was used to synchronize the ECG. Only during in the alert period that is non-refractory and sensing is available, intermittent switching X-ray (300 msec/sec) was exposed in chest CT. For comparison, the same intermittent switching X-ray (300 msec/sec) was exposed in the refractory period when sensing was not available. Results: Oversensing was detected only in one of the four pacemakers tested. In this pacemaker, oversensing was generated by exposure of the intermittent switching X-ray in the alert (non-refractory) period, but oversensing was not observed in the refractory period. Conclusion: A pacemaker has alert and refractory periods. Oversensing of a pacemaker was found to be inhibited by selective ECG-synchronized exposure in the refractory period. Since all pacemakers have the refractory period, the results of this study can be widely applied to the patients with pacemakers in chest CT, and their chest CT can be operated safely.展开更多
Chest investigation is common in hospital practice. Chest X-ray is readily available and usually the first chest investigation. Thoracic CT scan constitutes an alternative and complimentary chest investigation. It is ...Chest investigation is common in hospital practice. Chest X-ray is readily available and usually the first chest investigation. Thoracic CT scan constitutes an alternative and complimentary chest investigation. It is currently the most efficient investigation for the chest and its contents. Objectives: To evaluate the relevance of chest CT Scan requests in two university teaching hospitals in Cameroon. Material and Methods: We conducted a cross-sectional, retrospective and descriptive study at the Radiology and imaging units of the Yaounde Central Hospital and the Yaounde University Teaching Hospital Centre. Included in our study were files of patients who had a chest CT scan investigation during three years. Results: We had a study population of 323 subjects. The age interval was 23 months to 91 years old. Pulmonologist were the most prescribers with 27.2%. We had 80% conformity of indications with French Society of Radiology (FSR) standards. 50 over of 323 indications were not recommended by the FSR. Conclusion: There is a conformity rate of 80% between indications and the FSR recommendations.展开更多
One of the most dangerous diseases that affect people worldwide is lung cancer.The survival rate is minimal,because of the complexity in identifying lung cancer at developed stages.Henceforth,earlier detection of lung...One of the most dangerous diseases that affect people worldwide is lung cancer.The survival rate is minimal,because of the complexity in identifying lung cancer at developed stages.Henceforth,earlier detection of lung cancer is significant.Several Machine Learning(ML)approaches have been modeled for lung cancer recognition with the advent of Artificial Intelligence.However,small-scale datasets and deprived generalizability to recognize unknown data are considered challenges in lung cancer detection.This work proposes an advanced deep learning model,named Generative Adversarial Network-Attention Gated Network(GA-AGN),which is the integration of Generative Adversarial Network(GAN)and Attention Gated Network(AGN).Initially,the chest CT scan images are subjected to the pre-processing phase,where image resizing and normalization are used to preprocess the images.Then,the data augmentation is performed using the GAN model that is trained by Elk Herd Optimizer(EHO).Subsequently,lung cancer detection is done by means of GA-AGN model.Ultimately analysis is performed by using three measures,like accuracy,sensitivity as well as specificity with values of 0.938,0.948 and 0.927.The overall analysis states that the proposed model attained better outcomes than the conventional models.展开更多
This study aims to estimate the lifetime attributable cancer risk (LAR) for pediatric chest computed tomography (CT) examinations in five age groups using recently published age and region-specific conversion coeffici...This study aims to estimate the lifetime attributable cancer risk (LAR) for pediatric chest computed tomography (CT) examinations in five age groups using recently published age and region-specific conversion coefficients multiplying the widely available scanner registered dose length products (DLP) displayed on the CT console and hence calculating the Effective Dose (ED). The ED is then multiplied by the International Commission on Radiological Protection (ICRP) published risk factor for LAR. The obtained LAR values are compared with the international literature. Factors that may affect the LAR value are reported and discussed. The study included one hundred twenty five chest CT examinations for both males and females aged from less than one year to fifteen years. The patients reported data are from one single medical institution and using two CT scanners from June 2022 to December 2023. The results of this study may serve as benchmark for institutional radiation dose reference levels and risk estimation.展开更多
Background This study aimed to explore the imaging characteristics,diversity and changing trend in CT scans of pediatric patients infected with Delta-variant strain by studying imaging features of children infected wi...Background This study aimed to explore the imaging characteristics,diversity and changing trend in CT scans of pediatric patients infected with Delta-variant strain by studying imaging features of children infected with Delta and comparing the results to those of children with original COVID-19.Methods A retrospective,comparative analysis of initial chest CT manifestations between 63 pediatric patients infected with Delta variant in 2021 and 23 pediatric patients with COVID-19 in 2020 was conducted.Corresponding imaging features were analyzed.In addition,the changing trend in imaging features of COVID-19 Delta-variant cases were explored by evaluating the initial and follow-up CT scans.Results Among 63 children with Delta-variant COVID-19 in 2021,34(53.9%)showed positive chest CT presentation;and their CT score(1.10±1.41)was signifcantly lower than that in 2020(2.56±3.5)(P=0.0073).Lesion distribution:lung lesions of Delta cases appear mainly in the lower lungs on both sides.Most children had single lobe involvement(18 cases,52.9%),14(41.2%)in the right lung alone,and 14(41.2%)in both lungs.A majority of Delta cases displayed initially ground glass(23 cases,67.6%)and nodular shadows(13 cases,38.2%)in the frst CT scan,with few extrapulmonary manifestations.The 34 children with abnormal chest CT for the frst time have a total of 92 chest CT examinations.These children showed a statistically signifcant diference between the 0-3 day group and the 4-7 day group(P=0.0392)and a signifcant diference between the 4-7 day group and the more than 8 days group(P=0.0003).Conclusions The early manifestations of COVID-19 in children with abnormal imaging are mostly small subpleural nodular ground glass opacity.The changes on the Delta-variant COVID-19 chest CT were milder than the original strain.The lesions reached a peak on CT in 4-7 days and quickly improved and absorbed after a week.Dynamic CT re-examination can achieve a good prognosis.展开更多
基金Zhejiang Medical and Health Technology Project(Project No.2020PY072)。
文摘Objective:To explore a simple method for improving the diagnostic accuracy of malignant lung nodules based on imaging features of lung nodules.Methods:A retrospective analysis was conducted on the imaging data of 114 patients who underwent lung nodule surgery in the Thoracic Surgery Department of the First People’s Hospital of Huzhou from June to September 2024.Imaging features of lung nodules were summarized and trained using a BP neural network.Results:Training with the BP neural network increased the diagnostic accuracy for distinguishing between benign and malignant lung nodules based on imaging features from 84.2%(manual assessment)to 94.1%.Conclusion:Training with the BP neural network significantly improves the diagnostic accuracy of lung nodule malignancy based solely on imaging features.
基金supported by the General Project of Natural Science Foundation of Hebei Province of China(H2019201378)the Foundation of the President of Hebei University(XZJJ201917)the Special Project for Cultivating Scientific and Technological Innovation Ability of University and Middle School Students of Hebei Province(2021H060306).
文摘The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.
文摘Objective: to explore the efficacy of low-dose chest CT scanning combined with KARL3D iterative reconstruction technique. Methods: 100 patients who underwent chest CT examination in our hospital were randomly selected as the analysis objects and randomly divided into four groups, each with 25 cases. Group A was reconstructed by FBP algorithm and the pipeline current was 150mA;. The low-dose groups B, C and D were reconstructed by Karl algorithm with tube currents of 80mas, 60mas and 40mas respectively. The radiation dose and subjective and objective scores of the four groups were compared. SPSS210 statistical software was used for data analysis. Results: the radiation dose of group B, C and D using low dose tube current combined with karl3d iterative reconstruction technique was lower than that of group a (p < 0.05);The difference between the objective assessment (SD, SNR) and subjective score of the four groups was all p>0.05. Conclusion: The combination of low-dose iterative reconstruction technique and Karl 3D chest CT scan can obtain good images and reduce radiation dose, which is worthy of promotion in the industry.
文摘Objectives: The purpose of this study is to identify how to manage oversensing of pacemakers in chest CT. Methods: Four different models of pacemakers were examined to select the pacemaker generating oversensing. To the pacemaker with oversensing, intermittent switching X-ray was exposed using ECG-gated CT helical scan system at prospective CTA mode. IVY Model was used to synchronize the ECG. Only during in the alert period that is non-refractory and sensing is available, intermittent switching X-ray (300 msec/sec) was exposed in chest CT. For comparison, the same intermittent switching X-ray (300 msec/sec) was exposed in the refractory period when sensing was not available. Results: Oversensing was detected only in one of the four pacemakers tested. In this pacemaker, oversensing was generated by exposure of the intermittent switching X-ray in the alert (non-refractory) period, but oversensing was not observed in the refractory period. Conclusion: A pacemaker has alert and refractory periods. Oversensing of a pacemaker was found to be inhibited by selective ECG-synchronized exposure in the refractory period. Since all pacemakers have the refractory period, the results of this study can be widely applied to the patients with pacemakers in chest CT, and their chest CT can be operated safely.
文摘Chest investigation is common in hospital practice. Chest X-ray is readily available and usually the first chest investigation. Thoracic CT scan constitutes an alternative and complimentary chest investigation. It is currently the most efficient investigation for the chest and its contents. Objectives: To evaluate the relevance of chest CT Scan requests in two university teaching hospitals in Cameroon. Material and Methods: We conducted a cross-sectional, retrospective and descriptive study at the Radiology and imaging units of the Yaounde Central Hospital and the Yaounde University Teaching Hospital Centre. Included in our study were files of patients who had a chest CT scan investigation during three years. Results: We had a study population of 323 subjects. The age interval was 23 months to 91 years old. Pulmonologist were the most prescribers with 27.2%. We had 80% conformity of indications with French Society of Radiology (FSR) standards. 50 over of 323 indications were not recommended by the FSR. Conclusion: There is a conformity rate of 80% between indications and the FSR recommendations.
文摘One of the most dangerous diseases that affect people worldwide is lung cancer.The survival rate is minimal,because of the complexity in identifying lung cancer at developed stages.Henceforth,earlier detection of lung cancer is significant.Several Machine Learning(ML)approaches have been modeled for lung cancer recognition with the advent of Artificial Intelligence.However,small-scale datasets and deprived generalizability to recognize unknown data are considered challenges in lung cancer detection.This work proposes an advanced deep learning model,named Generative Adversarial Network-Attention Gated Network(GA-AGN),which is the integration of Generative Adversarial Network(GAN)and Attention Gated Network(AGN).Initially,the chest CT scan images are subjected to the pre-processing phase,where image resizing and normalization are used to preprocess the images.Then,the data augmentation is performed using the GAN model that is trained by Elk Herd Optimizer(EHO).Subsequently,lung cancer detection is done by means of GA-AGN model.Ultimately analysis is performed by using three measures,like accuracy,sensitivity as well as specificity with values of 0.938,0.948 and 0.927.The overall analysis states that the proposed model attained better outcomes than the conventional models.
文摘This study aims to estimate the lifetime attributable cancer risk (LAR) for pediatric chest computed tomography (CT) examinations in five age groups using recently published age and region-specific conversion coefficients multiplying the widely available scanner registered dose length products (DLP) displayed on the CT console and hence calculating the Effective Dose (ED). The ED is then multiplied by the International Commission on Radiological Protection (ICRP) published risk factor for LAR. The obtained LAR values are compared with the international literature. Factors that may affect the LAR value are reported and discussed. The study included one hundred twenty five chest CT examinations for both males and females aged from less than one year to fifteen years. The patients reported data are from one single medical institution and using two CT scanners from June 2022 to December 2023. The results of this study may serve as benchmark for institutional radiation dose reference levels and risk estimation.
基金This study was supported by the China Postdoctoral Science Foundation 2020M681674(to Xuhua Ge)The Nanjing Medical Science and Technique Development Foundation(No.YKK20130)(to Zhuo Li)This work was reviewed and approved by the Medical Ethical Committee of Second Hospital of Nanjing(approval number 2020-LS-ky003).
文摘Background This study aimed to explore the imaging characteristics,diversity and changing trend in CT scans of pediatric patients infected with Delta-variant strain by studying imaging features of children infected with Delta and comparing the results to those of children with original COVID-19.Methods A retrospective,comparative analysis of initial chest CT manifestations between 63 pediatric patients infected with Delta variant in 2021 and 23 pediatric patients with COVID-19 in 2020 was conducted.Corresponding imaging features were analyzed.In addition,the changing trend in imaging features of COVID-19 Delta-variant cases were explored by evaluating the initial and follow-up CT scans.Results Among 63 children with Delta-variant COVID-19 in 2021,34(53.9%)showed positive chest CT presentation;and their CT score(1.10±1.41)was signifcantly lower than that in 2020(2.56±3.5)(P=0.0073).Lesion distribution:lung lesions of Delta cases appear mainly in the lower lungs on both sides.Most children had single lobe involvement(18 cases,52.9%),14(41.2%)in the right lung alone,and 14(41.2%)in both lungs.A majority of Delta cases displayed initially ground glass(23 cases,67.6%)and nodular shadows(13 cases,38.2%)in the frst CT scan,with few extrapulmonary manifestations.The 34 children with abnormal chest CT for the frst time have a total of 92 chest CT examinations.These children showed a statistically signifcant diference between the 0-3 day group and the 4-7 day group(P=0.0392)and a signifcant diference between the 4-7 day group and the more than 8 days group(P=0.0003).Conclusions The early manifestations of COVID-19 in children with abnormal imaging are mostly small subpleural nodular ground glass opacity.The changes on the Delta-variant COVID-19 chest CT were milder than the original strain.The lesions reached a peak on CT in 4-7 days and quickly improved and absorbed after a week.Dynamic CT re-examination can achieve a good prognosis.
