Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video analyses.There is a growing...Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video analyses.There is a growing interest in applying this technology to diverse applications in medical image analysis.Automated three dimensional Breast Ultrasound is a vital tool for detecting breast cancer,and computer-assisted diagnosis software,developed based on deep learning,can effectively assist radiologists in diagnosis.However,the network model is prone to overfitting during training,owing to challenges such as insufficient training data.This study attempts to solve the problem caused by small datasets and improve model detection performance.Methods We propose a breast cancer detection framework based on deep learning(a transfer learning method based on cross-organ cancer detection)and a contrastive learning method based on breast imaging reporting and data systems(BI-RADS).Results When using cross organ transfer learning and BIRADS based contrastive learning,the average sensitivity of the model increased by a maximum of 16.05%.Conclusion Our experiments have demonstrated that the parameters and experiences of cross-organ cancer detection can be mutually referenced,and contrastive learning method based on BI-RADS can improve the detection performance of the model.展开更多
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
Purpose: This review examines the diagnostic value of transvaginal 3D ultrasound image texture analysis for the diagnosis of uterine adhesions. Materials and Methods: The total clinical data of 53 patients with uterin...Purpose: This review examines the diagnostic value of transvaginal 3D ultrasound image texture analysis for the diagnosis of uterine adhesions. Materials and Methods: The total clinical data of 53 patients with uterine adhesions diagnosed by hysteroscopy and the imaging data of transvaginal three-dimensional ultrasound from the Second Affiliated Hospital of Chongqing Medical University from June 2022 to August 2023 were retrospectively analysed. Based on hysteroscopic surgical records, patients were divided into two independent groups: normal endometrium and uterine adhesion sites. The samples were divided into a training set and a test set, and the transvaginal 3D ultrasound was used to outline the region of interest (ROI) and extract texture features for normal endometrium and uterine adhesions based on hysteroscopic surgical recordings, the training set data were feature screened and modelled using lasso regression and cross-validation, and the diagnostic efficacy of the model was assessed by applying the subjects’ operating characteristic (ROC) curves. Results: For each group, 290 texture feature parameters were extracted and three higher values were screened out, and the area under the curve of the constructed ultrasonographic scoring model was 0.658 and 0.720 in the training and test sets, respectively. Conclusion Relative clinical value of transvaginal three-dimensional ultrasound image texture analysis for the diagnosis of uterine adhesions.展开更多
Objectives: This study focused on evaluating the value of transvaginal 3D ultrasound for the diagnosis and prognostic assessment of post-cesarean section uterine diverticulum. Materials and Methods: We retrospectively...Objectives: This study focused on evaluating the value of transvaginal 3D ultrasound for the diagnosis and prognostic assessment of post-cesarean section uterine diverticulum. Materials and Methods: We retrospectively analyzed the data from 32 patients with post-cesarean section uterine diverticulum over three recent years. In all patients, transvaginal 3D ultrasound was used to measure the size of the uterine diverticulum and the thickness of the lower uterine segment (LUS) and myometrium. Patients with a LUS with a myometrial thickness under 4 mm underwent resection and repair surgery;those with a LUS with a myometrial thickness over 4 mm underwent hysteroscopic resection. The postoperative sonograms were compared with preoperative images to evaluate the efficacy of various treatments. Results: The mean length, width and depth of the uterine diverticula were 18.30 ± 2.80 mm, 9.14 ± 3.20 mm and 11.49 ± 2.71 mm, respectively. The average LUS myometrial thickness was 3.40 ± 0.80 mm (with a range of 1.6 mm - 6.3 mm). After surgery, two patients’ sonograms still showed diverticula at the post-cesarean section scar, measuring 6 mm × 7 mm × 6 mm and 6 mm × 8 mm × 4 mm. There were significant differences in the size of uterine diverticula between preoperative and postoperative sonograms (P < 0.05) and the effective rate of surgery was 93.75% (30/32). Conclusions: Transvaginal 3D ultrasound is an accurate method for detecting post-cesarean section uterine diverticulum and is helpful for assessing surgical options and prognosis. The LUS myometrial thickness, which is considered as an optional index of post-cesarean section uterine diverticulum, should be measured routinely.展开更多
Coumarins occupy an important place in the realm of natural products and synthetic organic chemistry. A fast and highly efficient green method for synthesizing 3-aryl coumarin derivatives from salicylaldehyde and phen...Coumarins occupy an important place in the realm of natural products and synthetic organic chemistry. A fast and highly efficient green method for synthesizing 3-aryl coumarin derivatives from salicylaldehyde and phenyl acetyl chloride in the presence of tetrahydrofuran and K2CO3 using ultrasound irradiation is reported. Ultrasound assisted reactions have resulted in better yields and faster reaction time of the desired products than when prepared under conventional conditions. The resulting coumarin derivatives were characterized by IR spectrum.展开更多
Photoacoustic microscopy(PAM),due to its deep penetration depth and high contrast,is playing an increasingly important role in biomedical imaging.PAM imaging systems equipped with conventional ultrasound transducers h...Photoacoustic microscopy(PAM),due to its deep penetration depth and high contrast,is playing an increasingly important role in biomedical imaging.PAM imaging systems equipped with conventional ultrasound transducers have demonstrated excellent imaging performance.However,these opaque ultrasonic transducers bring some constraints to the further development and application of PAM,such as complex optical path,bulky size,and difficult to integrate with other modalities.To overcome these problems,ultrasonic transducers with high optical transparency have appeared.At present,transparent ultrasonic transducers are divided into optical-based and acoustic-based sensors.In this paper,we mainly describe the acoustic-based piezoelectric transparent transducers in detail,of which the research advances in PAM applications are reviewed.In addition,the potential challenges and developments of transparent transducers in PAM are also demonstrated.展开更多
基金Macao Polytechnic University Grant(RP/FCSD-01/2022RP/FCA-05/2022)Science and Technology Development Fund of Macao(0105/2022/A).
文摘Background Deep convolutional neural networks have garnered considerable attention in numerous machine learning applications,particularly in visual recognition tasks such as image and video analyses.There is a growing interest in applying this technology to diverse applications in medical image analysis.Automated three dimensional Breast Ultrasound is a vital tool for detecting breast cancer,and computer-assisted diagnosis software,developed based on deep learning,can effectively assist radiologists in diagnosis.However,the network model is prone to overfitting during training,owing to challenges such as insufficient training data.This study attempts to solve the problem caused by small datasets and improve model detection performance.Methods We propose a breast cancer detection framework based on deep learning(a transfer learning method based on cross-organ cancer detection)and a contrastive learning method based on breast imaging reporting and data systems(BI-RADS).Results When using cross organ transfer learning and BIRADS based contrastive learning,the average sensitivity of the model increased by a maximum of 16.05%.Conclusion Our experiments have demonstrated that the parameters and experiences of cross-organ cancer detection can be mutually referenced,and contrastive learning method based on BI-RADS can improve the detection performance of the model.
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Purpose: This review examines the diagnostic value of transvaginal 3D ultrasound image texture analysis for the diagnosis of uterine adhesions. Materials and Methods: The total clinical data of 53 patients with uterine adhesions diagnosed by hysteroscopy and the imaging data of transvaginal three-dimensional ultrasound from the Second Affiliated Hospital of Chongqing Medical University from June 2022 to August 2023 were retrospectively analysed. Based on hysteroscopic surgical records, patients were divided into two independent groups: normal endometrium and uterine adhesion sites. The samples were divided into a training set and a test set, and the transvaginal 3D ultrasound was used to outline the region of interest (ROI) and extract texture features for normal endometrium and uterine adhesions based on hysteroscopic surgical recordings, the training set data were feature screened and modelled using lasso regression and cross-validation, and the diagnostic efficacy of the model was assessed by applying the subjects’ operating characteristic (ROC) curves. Results: For each group, 290 texture feature parameters were extracted and three higher values were screened out, and the area under the curve of the constructed ultrasonographic scoring model was 0.658 and 0.720 in the training and test sets, respectively. Conclusion Relative clinical value of transvaginal three-dimensional ultrasound image texture analysis for the diagnosis of uterine adhesions.
文摘Objectives: This study focused on evaluating the value of transvaginal 3D ultrasound for the diagnosis and prognostic assessment of post-cesarean section uterine diverticulum. Materials and Methods: We retrospectively analyzed the data from 32 patients with post-cesarean section uterine diverticulum over three recent years. In all patients, transvaginal 3D ultrasound was used to measure the size of the uterine diverticulum and the thickness of the lower uterine segment (LUS) and myometrium. Patients with a LUS with a myometrial thickness under 4 mm underwent resection and repair surgery;those with a LUS with a myometrial thickness over 4 mm underwent hysteroscopic resection. The postoperative sonograms were compared with preoperative images to evaluate the efficacy of various treatments. Results: The mean length, width and depth of the uterine diverticula were 18.30 ± 2.80 mm, 9.14 ± 3.20 mm and 11.49 ± 2.71 mm, respectively. The average LUS myometrial thickness was 3.40 ± 0.80 mm (with a range of 1.6 mm - 6.3 mm). After surgery, two patients’ sonograms still showed diverticula at the post-cesarean section scar, measuring 6 mm × 7 mm × 6 mm and 6 mm × 8 mm × 4 mm. There were significant differences in the size of uterine diverticula between preoperative and postoperative sonograms (P < 0.05) and the effective rate of surgery was 93.75% (30/32). Conclusions: Transvaginal 3D ultrasound is an accurate method for detecting post-cesarean section uterine diverticulum and is helpful for assessing surgical options and prognosis. The LUS myometrial thickness, which is considered as an optional index of post-cesarean section uterine diverticulum, should be measured routinely.
文摘Coumarins occupy an important place in the realm of natural products and synthetic organic chemistry. A fast and highly efficient green method for synthesizing 3-aryl coumarin derivatives from salicylaldehyde and phenyl acetyl chloride in the presence of tetrahydrofuran and K2CO3 using ultrasound irradiation is reported. Ultrasound assisted reactions have resulted in better yields and faster reaction time of the desired products than when prepared under conventional conditions. The resulting coumarin derivatives were characterized by IR spectrum.
基金supported by Guangdong Province Introduction of Innovative R&D Team(2016ZT06G375)National Natural Science Foundation of China(11804059,62205070 and 11664011).
文摘Photoacoustic microscopy(PAM),due to its deep penetration depth and high contrast,is playing an increasingly important role in biomedical imaging.PAM imaging systems equipped with conventional ultrasound transducers have demonstrated excellent imaging performance.However,these opaque ultrasonic transducers bring some constraints to the further development and application of PAM,such as complex optical path,bulky size,and difficult to integrate with other modalities.To overcome these problems,ultrasonic transducers with high optical transparency have appeared.At present,transparent ultrasonic transducers are divided into optical-based and acoustic-based sensors.In this paper,we mainly describe the acoustic-based piezoelectric transparent transducers in detail,of which the research advances in PAM applications are reviewed.In addition,the potential challenges and developments of transparent transducers in PAM are also demonstrated.
