Objective:To explore the value of nomogram model based on multimodal ultrasound features for predicting the malignant risk of micro lesions in breast areola region.Methods:The case data of Beijing Tiantan Hospital affiliated to Capital Medical University from May 2020 to July 2024 were retrospectively analyzed. A total of 50 patients with benign intraductal papilloma（bIDP group）and 54 patients with malignant risk breast tumor（mrBT group）were found to have micro lesions in breast areola region and confirmed by puncture or surgical pathology. Clinical data，conventional ultrasound and contrast-enhanced ultrasound features were compared between the two groups. Multivariate Logistic regression analysis and Lasso regression analysis were performed on statistically significant factors to screen out influencing factors. ROC curves were plotted to evaluate diagnostic efficacy，nomogram model and clinical decision curves were constructed to evaluate clinical benefits.Results:The differences of age，nipple discharge presentation，conventional ultrasound features（including boundary，morphology，aspect ratio，internal echo，internal microcalcification，far-field echo，peripheral irregular hyperechoic ring，dilate of peripheral ducts），and contrast-enhanced ultrasound features（including wash-in time，enhancement intensity，enhancement mode，enhancement scope，blood perfusion defect，crab foot sign，penetrating vessels）were statistically significant between the bIDP group and mrBTgroup（all P<0.05）. Regression analysis showed that age，uniformity of internal echo within the lesion，dilation of surrounding ducts，and enhanced crab foot sign were the affect factors for the diagnosis of mrBT（all P<0.05）. Based on these factors，a nomogram model was constructed with an area under ROC curve（AUC）of 0.907（95% CI=0.851-0.963），a sensitivity of 0.907，and a specificity of 0.780. The decision curve analysis showed that the collective model had good predictive performance. Conclusions:The nomogram model based on multimodal ultrasound features has good value in predicting malignant risk micro breast tumor of areola region.

Objective To observe the value of singular value decomposition(SVD)combined with block-matching and three-dimensional(BM3D)filtering for improving imaging quality of contrast-enhanced ultrasound(CEUS).Methods Three subject who would undergo liver,kidney and ovarian CEUS examination respectively were prospectively enrolled,and 250 images unaffected by respiratory movements were acquired in each one.SVD filtering was performed alone and combined with BM3D filtering,and contrast-to-tissue ratio(CTR),contrast-to-noise ratio(CNR)and signal-to-noise ratio(SNR)of the obtained CEUS images were calculated and compared.Results Compared with original CEUS images,CTR,CNR and SNR of SVD alone filtered CEUS images improved,which all further improved after combining with BM3D filtering.Conclusion SVD combined with BM3D filtering could significantly suppress the background tissue signals and remove noise,improving imaging quality of CEUS.

Objective To observe the value of singular value decomposition(SVD)combined with block-matching and three-dimensional(BM3D)filtering for improving imaging quality of contrast-enhanced ultrasound(CEUS).Methods Three subject who would undergo liver,kidney and ovarian CEUS examination respectively were prospectively enrolled,and 250 images unaffected by respiratory movements were acquired in each one.SVD filtering was performed alone and combined with BM3D filtering,and contrast-to-tissue ratio(CTR),contrast-to-noise ratio(CNR)and signal-to-noise ratio(SNR)of the obtained CEUS images were calculated and compared.Results Compared with original CEUS images,CTR,CNR and SNR of SVD alone filtered CEUS images improved,which all further improved after combining with BM3D filtering.Conclusion SVD combined with BM3D filtering could significantly suppress the background tissue signals and remove noise,improving imaging quality of CEUS.

Objective:To explore the value of nomogram model based on multimodal ultrasound features for predicting the malignant risk of micro lesions in breast areola region.Methods:The case data of Beijing Tiantan Hospital affiliated to Capital Medical University from May 2020 to July 2024 were retrospectively analyzed. A total of 50 patients with benign intraductal papilloma（bIDP group）and 54 patients with malignant risk breast tumor（mrBT group）were found to have micro lesions in breast areola region and confirmed by puncture or surgical pathology. Clinical data，conventional ultrasound and contrast-enhanced ultrasound features were compared between the two groups. Multivariate Logistic regression analysis and Lasso regression analysis were performed on statistically significant factors to screen out influencing factors. ROC curves were plotted to evaluate diagnostic efficacy，nomogram model and clinical decision curves were constructed to evaluate clinical benefits.Results:The differences of age，nipple discharge presentation，conventional ultrasound features（including boundary，morphology，aspect ratio，internal echo，internal microcalcification，far-field echo，peripheral irregular hyperechoic ring，dilate of peripheral ducts），and contrast-enhanced ultrasound features（including wash-in time，enhancement intensity，enhancement mode，enhancement scope，blood perfusion defect，crab foot sign，penetrating vessels）were statistically significant between the bIDP group and mrBTgroup（all P<0.05）. Regression analysis showed that age，uniformity of internal echo within the lesion，dilation of surrounding ducts，and enhanced crab foot sign were the affect factors for the diagnosis of mrBT（all P<0.05）. Based on these factors，a nomogram model was constructed with an area under ROC curve（AUC）of 0.907（95% CI=0.851-0.963），a sensitivity of 0.907，and a specificity of 0.780. The decision curve analysis showed that the collective model had good predictive performance. Conclusions:The nomogram model based on multimodal ultrasound features has good value in predicting malignant risk micro breast tumor of areola region.

Objective To observe the value of ultrasound vector flow imaging(VFI)combined with singular value decomposition(SVD)filtering for depicting deep microvasculature flow velocity of liver.Methods Grayscale ultrasound,CDFI and contrast-enhanced ultrasound(CEUS)were prospectively performed in a patient with suspected liver hemangioma.Images of CEUS were dealt with SVD filtering.Cross-correlation algorithm was used to obtain images of VFI based on grayscale ultrasound,original CEUS and SVD filtered CEUS,respectively,and the ability of the above images for depicting liver microvascular flow direction and velocity were compared.Results The signal-to-noise ratio(SNR)of liver grayscale ultrasound,original CEUS and SVD filtered CEUS images was 7.56,17.65 and 22.43 dB,respectively,while their contrast-to-issue ratio(CTR)was 1.12,7.56 and 16.34 dB,respectively.Compared with VFI based on grayscale ultrasound and original CEUS,VFI based on SVD filtered CEUS could display faster velocity and more uniform direction of blood flow.Before and after SVD filtering,liver microvascular flow velocity measured with VFI was 1.91(0.81,4.11)and 6.83(4.25,9.41)mm/s,respectively,which were significantly different(Z=-10.671,P＜0.001).Conclusion Combined with SVD filtering could significantly improve the efficiency of VFI for depicting liver deep microvasculature flow velocity.

Objective To observe the feasibility of Fourier ring correlation(FRC)for measuring the overall resolution of ultrasonic microvascular images.Methods Liver contrast-enhanced ultrasound(CEUS)images of 1 patient with suspected hepatic hemangioma(dataset 1)were processed with singular value decomposition(SVD)filter(dataset 2)and Frangi filter(dataset 3),respectively.Three ROI were selected on CEUS image in each dataset,and the signal-intensity curves were drawn,and local resolution of CEUS image in each dataset was measured using full width at half maxima(FWHM)method.Then the above datasets were divided into odd frame subset and even frame subset,respectively,which were converted into frequency domain using fast Fourier transform.FRC curves were generated to calculate the overall resolution of each kind images.Results The signal-to-noise ratio(SNR)of CEUS images in dataset 1,2,3 was(19.94±2.33),(30.36±0.78)and(69.52±16.38)dB,respectively,the local resolution was(4.07±9.82),(1.53±0.04)and(1.27±0.06)mm,both successively increased(all P＜0.05).The overall resolution of CEUS images in dataset 1,2,3 was 2.07,0.91 and 0.51 mm,respectively.Conclusion FRC was feasible for measuring the overall resolution of ultrasonic microvascular images.

Objective To observe the effect of extracting different speed contrast-enhanced ultrasound(CEUS)signals using singular value decomposition filtering and implementing fused imaging for improving visualization of microvascular structures.Methods Singular value decomposition and filtering were performed on 200 frames of mouse subcutaneous tumor and 250 frames of human liver CEUS image datasets.The singular value inflection point was used as the threshold for separating low-speed and high-speed contrast signals by exponential projection of singular values on the singular value sequence.The low-speed and high-speed signals in dataset were extracted,and dual-modal fusion imaging was performed on the processed images.The image resolution differences of ultrasound microvascular imaging regions with different flow velocities were evaluated.Results The high-speed blood flow images processed by the high singular value sequence range retained the fast-moving contrast signals which mainly showed the thicker blood vessel structures,while the low-speed blood flow images processed by the low singular value sequence range retained the low-speed moving contrast signals which reflected the microvascular structures on high singular value images.The fusion imaging displayed microvascular network more completely.Conclusion Appropriate selection of singular value range was crucial to optimization of CEUS images using singular value decomposition filtering.Fusion imaging was beneficial to improving visualization of microvascular structures.

ST segment morphology is closely related to cardiovascular disease. It is used not only for characterizing different diseases, but also for predicting the severity of the disease. However, the short duration, low energy, variable morphology and interference from various noises make ST segment morphology classification a difficult task. In this paper, we address the problems of single feature extraction and low classification accuracy of ST segment morphology classification, and use the gradient of ST surface to improve the accuracy of ST segment morphology multi-classification. In this paper, we identify five ST segment morphologies: normal, upward-sloping elevation, arch-back elevation, horizontal depression, and arch-back depression. Firstly, we select an ST segment candidate segment according to the QRS wave group location and medical statistical law. Secondly, we extract ST segment area, mean value, difference with reference baseline, slope, and mean squared error features. In addition, the ST segment is converted into a surface, the gradient features of the ST surface are extracted, and the morphological features are formed into a feature vector. Finally, the support vector machine is used to classify the ST segment, and then the ST segment morphology is multi-classified. The MIT-Beth Israel Hospital Database (MITDB) and the European ST-T database (EDB) were used as data sources to validate the algorithm in this paper, and the results showed that the algorithm in this paper achieved an average recognition rate of 97.79% and 95.60%, respectively, in the process of ST segment recognition. Based on the results of this paper, it is expected that this method can be introduced in the clinical setting in the future to provide morphological guidance for the diagnosis of cardiovascular diseases in the clinic and improve the diagnostic efficiency.
Algorithms ; Arrhythmias, Cardiac ; Databases, Factual ; Electrocardiography/methods* ; Humans ; Support Vector Machine

Objective:To investigate the value of contrast-enhanced ultrasound (CEUS) in the diagnosis of malignant endometrial lesions.Methods:A total of 142 patients with endometrial lesions who underwent contrast-enhanced ultrasound examination in Beijing Tiantan Hospital, Capital Medical University from January 2019 to September 2021 were selected. The endometrial lesions were divided into benign group (including endometrial hyperplasia and endometrial polyps) and malignant group (endometrial cancer) according to the pathological results of surgery, and the differences of contrast enhancement patterns between benign group and malignant group were compared. The sensitivity, specificity of CEUS in the diagnosis of endometrial cancer were calculated, and the Kappa value was calculated with the initial enhancement time earlier than or equal to the muscularity or the peak time earlier than the muscularity as the diagnostic index for the diagnosis of endometrial malignant lesions. The sensitivity, specificity, and Kappa value of CEUS in the diagnosis of endometrial cancer and endometrial cancer with thickness ≥10 mm were calculated.Results:A total of 108 patients underwent surgery with clear pathological results, including 66 patients in the benign lesion group and 42 patients in the malignant lesion group. The thickness of malignant lesions was significantly larger than that of benign lesions, and the difference was statistically significant( t=4.039, P<0.05), but there was no significant difference of hemodynamic parameters between the two groups ( P>0.05). The initial enhancement time, peak time and peak intensity of benign lesions were significantly different from those of malignant lesions(all P<0.05). The sensitivity, specificity, and Kappa value of CEUS in the diagnosis of endometrial cancer were 64.3%, 100% and 0.668, respectively. The sensitivity, specificity and Kappa value of CEUS in the diagnosis of endometrial carcinoma with lesion thickness ≥10 mm were 75.0%, 100% and 0.795, respectively. Conclusions:For the diagnosis of endometrial lesions, especially the malignant endometrial lesions with thickness and diameter greater than or equal to 10mm, there is a high diagnostic coincidence rate between CEUS and pathological diagnosis, and endometrial malignant lesions have more specific CEUS manifestations.

Objective: To analyze the ultrasound examination and computed tomography angiography (CTA) features of carotid web(CAW), and compare with the pathology after carotid endarterectomy, and then compare diagnostic efficacies of the two methods. Methods: From June 2018 to July 2019, 159 patients underwent carotid endarterectomy(CEA) in Beijing Tian Tan Hospital were collected, ultrasound examination and CTA were performed preoperatively. The presence or absence of CAW and whether there were thrombosis or atherosclerotic plaques associated with it were identified. The location length, thickness, direction in the lumen, echo characteristics of CAW, and complicated with or without thrombosis or atherosclerotic plaques were recorded. The postoperative specimens were observed, and the pathological analysis was performed. Results: Among the 159 cases of CEA, 22 cases were confirmed to have CAW structure by pathology, and HE staining showed extensive intimal fibrohyperplasia and mucoid degeneration, among which 18 cases had plaque formation at the bottom of the carotid web, and 4 cases associated with thrombosis. There were 17 cases of CAW structure diagnosed by ultrasound, 5 cases were misdiagnosed or missed, the sensitivity and specificity of ultrasound in the diagnosis of CAW were 77% (17/22) and 98% (135/137), and the accuracy was 75%. Eleven cases of CAW were diagnosed by preoperative CTA, and 11 cases were misdiagnosed and missed diagnosis, the sensitivity and specificity of CTA in the diagnosis of CAW were 50%(11/22) and 97%(134/137), and the accuracy was 47%. Conclusions The sensitivity of ultrasound in the diagnosis of CAW is higher than that of CTA, which can better display the structure of CAW and whether it is associated with plaque or thrombosis.