Artificial intelligence (AI)-based radiomics has attracted considerable research attention in the field of medical imaging, including ultrasound diagnosis. Ultrasound imaging has unique advantages such as high tempora...Artificial intelligence (AI)-based radiomics has attracted considerable research attention in the field of medical imaging, including ultrasound diagnosis. Ultrasound imaging has unique advantages such as high temporal resolution, low cost, and no radiation exposure. This renders it a preferred imaging modality for several clinical scenarios. This review includes a detailed introduction to imaging modalities, including Brightness-mode ultrasound, color Doppler flow imaging, ultrasound elastography, contrast-enhanced ultrasound, and multi-modal fusion analysis. It provides an overview of the current status and prospects of AI-based radiomics in ultrasound diagnosis, highlighting the application of AI-based radiomics to static ultrasound images, dynamic ultrasound videos, and multi-modal ultrasound fusion analysis.展开更多
Objective To study the role of bladder trabeculation found by B-mode ultrasound in evaluating the degree of bladder outlet obstruction ( BOO ) and the bladder function in benign prostatic hyperplasia ( BPH) patients. ...Objective To study the role of bladder trabeculation found by B-mode ultrasound in evaluating the degree of bladder outlet obstruction ( BOO ) and the bladder function in benign prostatic hyperplasia ( BPH) patients. Methods Conducted prospective research to determine differences in clinical data and urodynamic展开更多
BACKGROUND Intestinal lymphoma is a rare tumor.Contrast-enhanced ultrasound(CEUS)findings of intestinal lymphoma have not been reported previously,and the relationship between CEUS and clinicopathological features and...BACKGROUND Intestinal lymphoma is a rare tumor.Contrast-enhanced ultrasound(CEUS)findings of intestinal lymphoma have not been reported previously,and the relationship between CEUS and clinicopathological features and prognostic factors is still unknown.AIM To describe the B-mode US and CEUS features of intestinal lymphoma and investigate the correlation of CEUS and histopathological features.METHODS This was a single-center retrospective study.Eighteen patients with histologically confirmed intestinal lymphoma underwent B-mode US and CEUS examinations between October 2016 and November 2019.We summarized the features of Bmode US and CUES imaging of intestinal lymphoma and compared the frequency of tumor necrosis in intestinal lymphomas with reference to different pathological subtypes(aggressive or indolent)and clinical stage(early or advanced).The time–intensity curve parameters of CEUS were also compared between patients with normal and elevated serum lactate dehydrogenase.RESULTS In B-mode imaging,four patterns were observed in intestinal lymphoma:Mass type(12/18,66.7%),infiltration type(1/18,5.6%),mesentery type(4/18,22.2%)and mixed type(1/18,5.6%).All cases were hypoechoic and no cystic areas were detected.On CEUS,most cases(17/18,94.4%)showed arterial hyperechoic enhancement.All cases showed arterial enhancement followed by venous wash out.A relatively high rate of tumor necrosis(11/18,61.1%)was observed in this study.Tumor necrosis on CEUS was more frequent in aggressive subtypes(10/13,76.9%)than in indolent subtypes(1/5,20.0%)(P=0.047).There were no correlations between tumor necrosis and lesion size and Ann Arbor stage.There was no significant difference in time–intensity curve parameters between normal and elevated lactate dehydrogenase groups.CONCLUSION B-mode US and CEUS findings of intestinal lymphoma are characteristic.We observed a high rate of tumor necrosis,which appeared more frequently in aggressive pathological subtypes of intestinal lymphoma.展开更多
An automatic method for measuring the fetal mean abdominal diameter (MAD) or abdominal circumference (AC) with ultrasound is proposed. From a correctly presented abdominal section suitable for MAD or AC measurement, t...An automatic method for measuring the fetal mean abdominal diameter (MAD) or abdominal circumference (AC) with ultrasound is proposed. From a correctly presented abdominal section suitable for MAD or AC measurement, the location of fetal abdomen is detected by image processing. Thereafter, an active contour model is converged along the abdominal boundary for measurement purposes. The validation data set contained 310 images of fetuses with gestational age (GA) from 14 to 41 weeks. The measurement success rate was 88.1%. By manually indicating the location of the abdomen, the success rate was further improved to 95.8% for the failed cases. The correlation between manual and automatic measurements was 0.95 and the intraclass correlation coefficient (ICC) was 0.976 (95% confidence interval (CI);0.969 - 0.981). The average method execution time was 0.3 s. The mean error was lower in young fetuses (0.4%) than in older fetuses (-2.1%). The proposed cross-platform method was implemented on a portable, low-cost ultrasound machine prototype targeted for low- and middle-income countries (LMIC);the results achieved were comparable to those of other state-of-the-art automatic methods.展开更多
This paper deals with the temperature correlation of gray scale of B-mode ultrasound image from heated tissue. In this study, many in-vitro fresh pig livers are heated in a temperature range from 28 ℃ to 45℃, from w...This paper deals with the temperature correlation of gray scale of B-mode ultrasound image from heated tissue. In this study, many in-vitro fresh pig livers are heated in a temperature range from 28 ℃ to 45℃, from which a series of B-mode ultrasonic images of livers were obtained. The gray-value is evaluated from the ultrasound images respectively. A correlation of the mean gray value of the selected regions (12×12 pixels) in B-mode ultrasonic images of liver and its temperature was pointed out. And the experiment results agreed the evaluation well. And it is possible to monitor the tissue temperature changing in hyperthermia using this correlation.展开更多
<strong>Introduction:</strong> In our practice, renal measurements in patients with normal renal function usually appear to be lower compared to standards reported in reference literature. The standards ar...<strong>Introduction:</strong> In our practice, renal measurements in patients with normal renal function usually appear to be lower compared to standards reported in reference literature. The standards are probably different in our context. Given the importance of renal biometrics in nephrological practice, we felt it necessary to carry out this preliminary study in order to identify an order of reference measurements appropriate to our context. <strong>Methods:</strong> This was a cross-sectional study that took place from 18 August to 04 November 2018 at the Yalgado Ouedrarogo University Hospital Center. The first 100 subjects aged between 18 and 30 years who met the following inclusion criteria were selected: to be black african Burkinabe and to have normal renal function. The height, width and thickness of each kidney were measured using ultra-sound scanners. For statistical tests, a value of p < 0.05 was considered statistically significant. <strong>Results:</strong> The average age was 23.9 ± 6.1 years and the sex ratio was 2.2. Mean heights, widths and renal thicknesses were 94.5 ± 14.5, 38.7 ± 10.7 and 36.3 ± 10.3 mm, and 96.7 ± 16.7, 42.7 ± 16.7 and 36.8 ± 10.8 mm respectively for right and left kidneys. The distribution of the different renal dimensions in our sample followed a normal distribution. In the particular case of the right kidney, the probability that its height was between 79.2 and 109.7 mm was 0.95 and the probability that it was less than 79.2 mm or greater than 109.7 mm was 0.05. Renal height was significantly higher in subjects with height greater than 1.70 m (p ≤ 0.02). The left kidneys were on average significantly larger than the right kidneys (p = 0.0001). <strong>Conclusions:</strong> Our study is not extrapolable to the general population of Burkina Faso. It suggests, however, that the kidneys of the apparently healthy Burkinabe subject are smaller than what is reported in anatomy reference books. Our work, which is preliminary, should be deepened through a national survey. In the meantime, we should consider, in the nephrological assessment of the Burkinabe patient, the results of the renal biometrics we report.展开更多
目的探讨分析自动乳腺容积成像系统联合普通手持超声在乳腺肿物良恶性鉴别诊断中的价值。方法选取2022年4月—2023年3月在齐齐哈尔市第二医院超声科检查的符合纳入标准的乳腺肿物患者60名,均行自动乳腺容积成像系统(automated breast vo...目的探讨分析自动乳腺容积成像系统联合普通手持超声在乳腺肿物良恶性鉴别诊断中的价值。方法选取2022年4月—2023年3月在齐齐哈尔市第二医院超声科检查的符合纳入标准的乳腺肿物患者60名,均行自动乳腺容积成像系统(automated breast volume scanner,ABVS)检查和普通二维超声(handheld ultrasound,HHUS)检查,对声像图特点进行数据统计分析、随访观察图像和相应专业指数变化,以组织病理学诊断为金标准。结果HHUS准确率为76.4%,ABVS准确率为77.4%,二者联合准确率为87.7%;ABVS与HHUS敏感度比较,差异无统计学意义(χ^(2)=0.405,P>0.05),二者联合与HHUS、ABVS的敏感度和特异度分别比较,差异有统计学意义(P<0.05)。结论二者联合应用于乳腺癌的筛查及诊断,具有重要临床指导意义。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
基金the National Natural Science Foundation of China,Nos.92159305,92259303,62027901,81930053,and 82272029Beijing Science Fund for Distinguished Young Scholars,No.JQ22013and Excellent Member Project of the Youth Innovation Promotion Association CAS,No.2016124.
文摘Artificial intelligence (AI)-based radiomics has attracted considerable research attention in the field of medical imaging, including ultrasound diagnosis. Ultrasound imaging has unique advantages such as high temporal resolution, low cost, and no radiation exposure. This renders it a preferred imaging modality for several clinical scenarios. This review includes a detailed introduction to imaging modalities, including Brightness-mode ultrasound, color Doppler flow imaging, ultrasound elastography, contrast-enhanced ultrasound, and multi-modal fusion analysis. It provides an overview of the current status and prospects of AI-based radiomics in ultrasound diagnosis, highlighting the application of AI-based radiomics to static ultrasound images, dynamic ultrasound videos, and multi-modal ultrasound fusion analysis.
文摘Objective To study the role of bladder trabeculation found by B-mode ultrasound in evaluating the degree of bladder outlet obstruction ( BOO ) and the bladder function in benign prostatic hyperplasia ( BPH) patients. Methods Conducted prospective research to determine differences in clinical data and urodynamic
基金National Natural Science Foundation of China,No.81974268Medical and Health Science and Technology Innovation Project of Chinese Academy of Medical Sciences,No.2017-I2M-1-006Beijing Hope Run Special Fund of Cancer Foundation of China,No.LC2017B19 and No.LC2016A04.
文摘BACKGROUND Intestinal lymphoma is a rare tumor.Contrast-enhanced ultrasound(CEUS)findings of intestinal lymphoma have not been reported previously,and the relationship between CEUS and clinicopathological features and prognostic factors is still unknown.AIM To describe the B-mode US and CEUS features of intestinal lymphoma and investigate the correlation of CEUS and histopathological features.METHODS This was a single-center retrospective study.Eighteen patients with histologically confirmed intestinal lymphoma underwent B-mode US and CEUS examinations between October 2016 and November 2019.We summarized the features of Bmode US and CUES imaging of intestinal lymphoma and compared the frequency of tumor necrosis in intestinal lymphomas with reference to different pathological subtypes(aggressive or indolent)and clinical stage(early or advanced).The time–intensity curve parameters of CEUS were also compared between patients with normal and elevated serum lactate dehydrogenase.RESULTS In B-mode imaging,four patterns were observed in intestinal lymphoma:Mass type(12/18,66.7%),infiltration type(1/18,5.6%),mesentery type(4/18,22.2%)and mixed type(1/18,5.6%).All cases were hypoechoic and no cystic areas were detected.On CEUS,most cases(17/18,94.4%)showed arterial hyperechoic enhancement.All cases showed arterial enhancement followed by venous wash out.A relatively high rate of tumor necrosis(11/18,61.1%)was observed in this study.Tumor necrosis on CEUS was more frequent in aggressive subtypes(10/13,76.9%)than in indolent subtypes(1/5,20.0%)(P=0.047).There were no correlations between tumor necrosis and lesion size and Ann Arbor stage.There was no significant difference in time–intensity curve parameters between normal and elevated lactate dehydrogenase groups.CONCLUSION B-mode US and CEUS findings of intestinal lymphoma are characteristic.We observed a high rate of tumor necrosis,which appeared more frequently in aggressive pathological subtypes of intestinal lymphoma.
文摘An automatic method for measuring the fetal mean abdominal diameter (MAD) or abdominal circumference (AC) with ultrasound is proposed. From a correctly presented abdominal section suitable for MAD or AC measurement, the location of fetal abdomen is detected by image processing. Thereafter, an active contour model is converged along the abdominal boundary for measurement purposes. The validation data set contained 310 images of fetuses with gestational age (GA) from 14 to 41 weeks. The measurement success rate was 88.1%. By manually indicating the location of the abdomen, the success rate was further improved to 95.8% for the failed cases. The correlation between manual and automatic measurements was 0.95 and the intraclass correlation coefficient (ICC) was 0.976 (95% confidence interval (CI);0.969 - 0.981). The average method execution time was 0.3 s. The mean error was lower in young fetuses (0.4%) than in older fetuses (-2.1%). The proposed cross-platform method was implemented on a portable, low-cost ultrasound machine prototype targeted for low- and middle-income countries (LMIC);the results achieved were comparable to those of other state-of-the-art automatic methods.
基金The research was supported by National Nature Science Foundation (30470450) Education Committee Foundation( KP0608200201 ) Elitist Foundation( KW5800200351 ) from Beijing City,China.
文摘This paper deals with the temperature correlation of gray scale of B-mode ultrasound image from heated tissue. In this study, many in-vitro fresh pig livers are heated in a temperature range from 28 ℃ to 45℃, from which a series of B-mode ultrasonic images of livers were obtained. The gray-value is evaluated from the ultrasound images respectively. A correlation of the mean gray value of the selected regions (12×12 pixels) in B-mode ultrasonic images of liver and its temperature was pointed out. And the experiment results agreed the evaluation well. And it is possible to monitor the tissue temperature changing in hyperthermia using this correlation.
文摘<strong>Introduction:</strong> In our practice, renal measurements in patients with normal renal function usually appear to be lower compared to standards reported in reference literature. The standards are probably different in our context. Given the importance of renal biometrics in nephrological practice, we felt it necessary to carry out this preliminary study in order to identify an order of reference measurements appropriate to our context. <strong>Methods:</strong> This was a cross-sectional study that took place from 18 August to 04 November 2018 at the Yalgado Ouedrarogo University Hospital Center. The first 100 subjects aged between 18 and 30 years who met the following inclusion criteria were selected: to be black african Burkinabe and to have normal renal function. The height, width and thickness of each kidney were measured using ultra-sound scanners. For statistical tests, a value of p < 0.05 was considered statistically significant. <strong>Results:</strong> The average age was 23.9 ± 6.1 years and the sex ratio was 2.2. Mean heights, widths and renal thicknesses were 94.5 ± 14.5, 38.7 ± 10.7 and 36.3 ± 10.3 mm, and 96.7 ± 16.7, 42.7 ± 16.7 and 36.8 ± 10.8 mm respectively for right and left kidneys. The distribution of the different renal dimensions in our sample followed a normal distribution. In the particular case of the right kidney, the probability that its height was between 79.2 and 109.7 mm was 0.95 and the probability that it was less than 79.2 mm or greater than 109.7 mm was 0.05. Renal height was significantly higher in subjects with height greater than 1.70 m (p ≤ 0.02). The left kidneys were on average significantly larger than the right kidneys (p = 0.0001). <strong>Conclusions:</strong> Our study is not extrapolable to the general population of Burkina Faso. It suggests, however, that the kidneys of the apparently healthy Burkinabe subject are smaller than what is reported in anatomy reference books. Our work, which is preliminary, should be deepened through a national survey. In the meantime, we should consider, in the nephrological assessment of the Burkinabe patient, the results of the renal biometrics we report.
文摘目的探讨分析自动乳腺容积成像系统联合普通手持超声在乳腺肿物良恶性鉴别诊断中的价值。方法选取2022年4月—2023年3月在齐齐哈尔市第二医院超声科检查的符合纳入标准的乳腺肿物患者60名,均行自动乳腺容积成像系统(automated breast volume scanner,ABVS)检查和普通二维超声(handheld ultrasound,HHUS)检查,对声像图特点进行数据统计分析、随访观察图像和相应专业指数变化,以组织病理学诊断为金标准。结果HHUS准确率为76.4%,ABVS准确率为77.4%,二者联合准确率为87.7%;ABVS与HHUS敏感度比较,差异无统计学意义(χ^(2)=0.405,P>0.05),二者联合与HHUS、ABVS的敏感度和特异度分别比较,差异有统计学意义(P<0.05)。结论二者联合应用于乳腺癌的筛查及诊断,具有重要临床指导意义。
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.
