Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast ...Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast nodules of BI-RADS 3 or above were selected as the research subjects.After pathological diagnosis,24 cases were malignant breast nodules of BI-RADS 3 or above,while 139 cases were benign breast nodules of BI-RADS 3 or above.The diagnosis rate of malignant and benign breast nodules of BI-RADS 3 or above,including 95%CI,was observed and analyzed.Results:The malignant and benign detection rates of conventional ultrasound were 88.63%and 75.00%,respectively,and the malignant and benign detection rates of ultrasound imaging were 93.18%and 87.50%,respectively,with 95%CIs greater than 0.7.Conclusion:Ultrasound imaging can help improve the diagnostic accuracy of benign and malignant breast nodules of BI-RADS 3 and above and reduce the misdiagnosis rate.展开更多
In many fields, particularly that of health, the diagnosis of diseases is a very difficult task to carry out. Therefore, early detection of diseases using artificial intelligence tools can be of paramount importance i...In many fields, particularly that of health, the diagnosis of diseases is a very difficult task to carry out. Therefore, early detection of diseases using artificial intelligence tools can be of paramount importance in the medical field. In this study, we proposed an intelligent system capable of performing diagnoses for radiologists. The support system is designed to evaluate mammographic images, thereby classifying normal and abnormal patients. The proposed method (DiagBC for Breast Cancer Diagnosis) combines two (2) intelligent unsupervised learning algorithms (the C-Means clustering algorithm and the Gaussian Mixture Model) for the segmentation of medical images and an algorithm for supervised learning (a modified DenseNet) for the diagnosis of breast images. Ultimately, a prototype of the proposed system was implemented for the Magori Polyclinic in Niamey (Niger) making it possible to diagnose (or classify) breast cancer into two (2) classes: the normal class and the abnormal class.展开更多
Objective To investigate the difference in texture features on diffusion weighted imaging(DWI) images between breast benign and malignant tumors.Methods Patients including 56 with mass-like breast cancer, 16 with brea...Objective To investigate the difference in texture features on diffusion weighted imaging(DWI) images between breast benign and malignant tumors.Methods Patients including 56 with mass-like breast cancer, 16 with breast fibroadenoma, and 4 with intraductal papilloma of breast treated in the Hainan Hospital of Chinese PLA General Hospital were retrospectively enrolled in this study, and allocated to the benign group(20 patients) and the malignant group(56 patients) according to the post-surgically pathological results. Texture analysis was performed on axial DWI images, and five characteristic parameters including Angular Second Moment(ASM), Contrast, Correlation, Inverse Difference Moment(IDM), and Entropy were calculated. Independent sample t-test and Mann-Whitney U test were performed for intergroup comparison. Regression model was established by using Binary Logistic regression analysis, and receiver operating characteristic curve(ROC) analysis was carried out to evaluate the diagnostic efficiency. Results The texture features ASM, Contrast, Correlation and Entropy showed significant differences between the benign and malignant breast tumor groups(PASM= 0.014, Pcontrast= 0.019, Pcorrelation= 0.010, Pentropy= 0.007). The area under the ROC curve was 0.685, 0.681, 0.754, and 0.683 respectively for the positive texture variables mentioned above, and that for the combined variables(ASM, Contrast, and Entropy) was 0.802 in the model of Logistic regression. Binary Logistic regression analysis demonstrated that ASM, Contrast and Entropy were considered as thespecific imaging variables for the differential diagnosis of breast benign and malignant tumors.Conclusion The texture analysis of DWI may be a simple and effective tool in the differential diagnosis between breast benign and malignant tumors.展开更多
This editorial provides commentary on an article titled"Potential and limitationsof ChatGPT and generative artificial intelligence(AI)in medical safety education"recently published in the World Journal of Cl...This editorial provides commentary on an article titled"Potential and limitationsof ChatGPT and generative artificial intelligence(AI)in medical safety education"recently published in the World Journal of Clinical Cases.AI has enormous potentialfor various applications in the field of Kawasaki disease(KD).One is machinelearning(ML)to assist in the diagnosis of KD,and clinical prediction models havebeen constructed worldwide using ML;the second is using a gene signalcalculation toolbox to identify KD,which can be used to monitor key clinicalfeatures and laboratory parameters of disease severity;and the third is using deeplearning(DL)to assist in cardiac ultrasound detection.The performance of the DLalgorithm is similar to that of experienced cardiac experts in detecting coronaryartery lesions to promoting the diagnosis of KD.To effectively utilize AI in thediagnosis and treatment process of KD,it is crucial to improve the accuracy of AIdecision-making using more medical data,while addressing issues related topatient personal information protection and AI decision-making responsibility.AIprogress is expected to provide patients with accurate and effective medicalservices that will positively impact the diagnosis and treatment of KD in thefuture.展开更多
Objective:To study the diagnostic value of T2*-weighted first-pass perfusion imaging in breast tumors.Methods: We analyzed the magnetic resonance imaging(MRI)information along with the pathological and immunohistochem...Objective:To study the diagnostic value of T2*-weighted first-pass perfusion imaging in breast tumors.Methods: We analyzed the magnetic resonance imaging(MRI)information along with the pathological and immunohistochemistry re- sults.Magnetic resonance imaging was performed in 28 patients with breast tumor.The time to signal intensity curves were generated according to the T2*-weighted first-pass perfusion imaging.The curve’s maximal signal intensity drop rate and maximal signal intensity decrease time were analyzed and compared with the pathological diagnoses after surgery.Results: Malignant breast lesions showed higher maximal signal intensity drop rate(44.69%±17.07 vs.17.22%±7.49,P<0.001) than benign lesions,but there was no significant difference of maximal signal decrease time between those two lesions(23.94 s±4.92 vs.20.02 s±6.83,P>0.05).Conclusion:The T2*-weighted first-pass perfusion imaging has enough sensitivity and specificity in breast tumor diagnosis.展开更多
Deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast tumors.However,a Brightness mode(B-mode)ultrasound image derives train...Deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast tumors.However,a Brightness mode(B-mode)ultrasound image derives training feature samples that make closer isolation toward the infection part.Hence,it is expensive due to a metaheuristic search of features occupying the global region of interest(ROI)structures of input images.Thus,it may lead to the high computational complexity of the pre-trained DNN-based CABTD method.This paper proposes a novel ensemble pretrained DNN-based CABTD method using global-and local-ROI-structures of B-mode ultrasound images.It conveys the additional consideration of a local-ROI-structures for further enhan-cing the pretrained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual quality.The features are extracted at various depths(18,50,and 101)from the global and local ROI structures and feed to support vector machine for better classification.From the experimental results,it has been observed that the combined local and global ROI structure of small depth residual network ResNet18(0.8 in%)has produced significant improve-ment in pixel ratio as compared to ResNet50(0.5 in%)and ResNet101(0.3 in%),respectively.Subsequently,the pretrained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors(Benign and Malignant)and improve the diagnostic accuracy(86%)compared to Dense Net,Alex Net,VGG Net,and Google Net.Moreover,it reduces the computational complexity due to the small depth residual network ResNet18,respectively.展开更多
AIM:To summarize the application of deep learning in detecting ophthalmic disease with ultrawide-field fundus images and analyze the advantages,limitations,and possible solutions common to all tasks.METHODS:We searche...AIM:To summarize the application of deep learning in detecting ophthalmic disease with ultrawide-field fundus images and analyze the advantages,limitations,and possible solutions common to all tasks.METHODS:We searched three academic databases,including PubMed,Web of Science,and Ovid,with the date of August 2022.We matched and screened according to the target keywords and publication year and retrieved a total of 4358 research papers according to the keywords,of which 23 studies were retrieved on applying deep learning in diagnosing ophthalmic disease with ultrawide-field images.RESULTS:Deep learning in ultrawide-field images can detect various ophthalmic diseases and achieve great performance,including diabetic retinopathy,glaucoma,age-related macular degeneration,retinal vein occlusions,retinal detachment,and other peripheral retinal diseases.Compared to fundus images,the ultrawide-field fundus scanning laser ophthalmoscopy enables the capture of the ocular fundus up to 200°in a single exposure,which can observe more areas of the retina.CONCLUSION:The combination of ultrawide-field fundus images and artificial intelligence will achieve great performance in diagnosing multiple ophthalmic diseases in the future.展开更多
文摘Objective:To explore the diagnostic value of ultrasound imaging for breast nodules of breast imaging-reporting and data system(BI-RADS)category 3 and above.Methods:From June 2021 to July 2022,163 patients with breast nodules of BI-RADS 3 or above were selected as the research subjects.After pathological diagnosis,24 cases were malignant breast nodules of BI-RADS 3 or above,while 139 cases were benign breast nodules of BI-RADS 3 or above.The diagnosis rate of malignant and benign breast nodules of BI-RADS 3 or above,including 95%CI,was observed and analyzed.Results:The malignant and benign detection rates of conventional ultrasound were 88.63%and 75.00%,respectively,and the malignant and benign detection rates of ultrasound imaging were 93.18%and 87.50%,respectively,with 95%CIs greater than 0.7.Conclusion:Ultrasound imaging can help improve the diagnostic accuracy of benign and malignant breast nodules of BI-RADS 3 and above and reduce the misdiagnosis rate.
文摘In many fields, particularly that of health, the diagnosis of diseases is a very difficult task to carry out. Therefore, early detection of diseases using artificial intelligence tools can be of paramount importance in the medical field. In this study, we proposed an intelligent system capable of performing diagnoses for radiologists. The support system is designed to evaluate mammographic images, thereby classifying normal and abnormal patients. The proposed method (DiagBC for Breast Cancer Diagnosis) combines two (2) intelligent unsupervised learning algorithms (the C-Means clustering algorithm and the Gaussian Mixture Model) for the segmentation of medical images and an algorithm for supervised learning (a modified DenseNet) for the diagnosis of breast images. Ultimately, a prototype of the proposed system was implemented for the Magori Polyclinic in Niamey (Niger) making it possible to diagnose (or classify) breast cancer into two (2) classes: the normal class and the abnormal class.
文摘Objective To investigate the difference in texture features on diffusion weighted imaging(DWI) images between breast benign and malignant tumors.Methods Patients including 56 with mass-like breast cancer, 16 with breast fibroadenoma, and 4 with intraductal papilloma of breast treated in the Hainan Hospital of Chinese PLA General Hospital were retrospectively enrolled in this study, and allocated to the benign group(20 patients) and the malignant group(56 patients) according to the post-surgically pathological results. Texture analysis was performed on axial DWI images, and five characteristic parameters including Angular Second Moment(ASM), Contrast, Correlation, Inverse Difference Moment(IDM), and Entropy were calculated. Independent sample t-test and Mann-Whitney U test were performed for intergroup comparison. Regression model was established by using Binary Logistic regression analysis, and receiver operating characteristic curve(ROC) analysis was carried out to evaluate the diagnostic efficiency. Results The texture features ASM, Contrast, Correlation and Entropy showed significant differences between the benign and malignant breast tumor groups(PASM= 0.014, Pcontrast= 0.019, Pcorrelation= 0.010, Pentropy= 0.007). The area under the ROC curve was 0.685, 0.681, 0.754, and 0.683 respectively for the positive texture variables mentioned above, and that for the combined variables(ASM, Contrast, and Entropy) was 0.802 in the model of Logistic regression. Binary Logistic regression analysis demonstrated that ASM, Contrast and Entropy were considered as thespecific imaging variables for the differential diagnosis of breast benign and malignant tumors.Conclusion The texture analysis of DWI may be a simple and effective tool in the differential diagnosis between breast benign and malignant tumors.
文摘This editorial provides commentary on an article titled"Potential and limitationsof ChatGPT and generative artificial intelligence(AI)in medical safety education"recently published in the World Journal of Clinical Cases.AI has enormous potentialfor various applications in the field of Kawasaki disease(KD).One is machinelearning(ML)to assist in the diagnosis of KD,and clinical prediction models havebeen constructed worldwide using ML;the second is using a gene signalcalculation toolbox to identify KD,which can be used to monitor key clinicalfeatures and laboratory parameters of disease severity;and the third is using deeplearning(DL)to assist in cardiac ultrasound detection.The performance of the DLalgorithm is similar to that of experienced cardiac experts in detecting coronaryartery lesions to promoting the diagnosis of KD.To effectively utilize AI in thediagnosis and treatment process of KD,it is crucial to improve the accuracy of AIdecision-making using more medical data,while addressing issues related topatient personal information protection and AI decision-making responsibility.AIprogress is expected to provide patients with accurate and effective medicalservices that will positively impact the diagnosis and treatment of KD in thefuture.
基金a grant from the Medicine Scientific Development Foun-dation of Nanjing(No.zkx05021).
文摘Objective:To study the diagnostic value of T2*-weighted first-pass perfusion imaging in breast tumors.Methods: We analyzed the magnetic resonance imaging(MRI)information along with the pathological and immunohistochemistry re- sults.Magnetic resonance imaging was performed in 28 patients with breast tumor.The time to signal intensity curves were generated according to the T2*-weighted first-pass perfusion imaging.The curve’s maximal signal intensity drop rate and maximal signal intensity decrease time were analyzed and compared with the pathological diagnoses after surgery.Results: Malignant breast lesions showed higher maximal signal intensity drop rate(44.69%±17.07 vs.17.22%±7.49,P<0.001) than benign lesions,but there was no significant difference of maximal signal decrease time between those two lesions(23.94 s±4.92 vs.20.02 s±6.83,P>0.05).Conclusion:The T2*-weighted first-pass perfusion imaging has enough sensitivity and specificity in breast tumor diagnosis.
文摘Deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast tumors.However,a Brightness mode(B-mode)ultrasound image derives training feature samples that make closer isolation toward the infection part.Hence,it is expensive due to a metaheuristic search of features occupying the global region of interest(ROI)structures of input images.Thus,it may lead to the high computational complexity of the pre-trained DNN-based CABTD method.This paper proposes a novel ensemble pretrained DNN-based CABTD method using global-and local-ROI-structures of B-mode ultrasound images.It conveys the additional consideration of a local-ROI-structures for further enhan-cing the pretrained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual quality.The features are extracted at various depths(18,50,and 101)from the global and local ROI structures and feed to support vector machine for better classification.From the experimental results,it has been observed that the combined local and global ROI structure of small depth residual network ResNet18(0.8 in%)has produced significant improve-ment in pixel ratio as compared to ResNet50(0.5 in%)and ResNet101(0.3 in%),respectively.Subsequently,the pretrained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors(Benign and Malignant)and improve the diagnostic accuracy(86%)compared to Dense Net,Alex Net,VGG Net,and Google Net.Moreover,it reduces the computational complexity due to the small depth residual network ResNet18,respectively.
基金Supported by 1.3.5 Project for Disciplines of Excellence,West China Hospital,Sichuan University(No.ZYJC21025).
文摘AIM:To summarize the application of deep learning in detecting ophthalmic disease with ultrawide-field fundus images and analyze the advantages,limitations,and possible solutions common to all tasks.METHODS:We searched three academic databases,including PubMed,Web of Science,and Ovid,with the date of August 2022.We matched and screened according to the target keywords and publication year and retrieved a total of 4358 research papers according to the keywords,of which 23 studies were retrieved on applying deep learning in diagnosing ophthalmic disease with ultrawide-field images.RESULTS:Deep learning in ultrawide-field images can detect various ophthalmic diseases and achieve great performance,including diabetic retinopathy,glaucoma,age-related macular degeneration,retinal vein occlusions,retinal detachment,and other peripheral retinal diseases.Compared to fundus images,the ultrawide-field fundus scanning laser ophthalmoscopy enables the capture of the ocular fundus up to 200°in a single exposure,which can observe more areas of the retina.CONCLUSION:The combination of ultrawide-field fundus images and artificial intelligence will achieve great performance in diagnosing multiple ophthalmic diseases in the future.
