ABSTRACT
Objective:To explore the feasibility of extracting the key plane of the normal fetal palate on the 11-13 + 6 week from tomography ultrasonography imaging based on artificial intelligence. Methods:The fetal volume datas of 235 cases of 11-13 + 6 week normal fetal were collected from the Department of Ultrasound in the Luohu District People′s Hospital of Shenzhen and Huazhong University of Science and Technology Union Shenzhen Hospital from May 2020 to April 2021. The data acquisition was completed by sonographers A and B by using the GE Voluson E10 color Doppler ultrasound diagnostic instrument. All datas were marked offline by sonographer C. Tomographic imaging was performed on all included data by sonographer D, the tomographic images were saved and the time-consuming was recorded, and the datas of the sonographer group were obtained. The labeled data were randomly divided into the training set and test set for model transfer learning and testing.The 4-fold cross-validation was adopted to record the test set image output by the model and the time consumption to obtain the intelligent group data. A senior sonographer performed image analysis on the two groups of data images. The feasibility of the intelligent model was verified by comparing the score of the plane of retronasal triangle(RTP), the acquisition rate of RTP, the acquisition rate of the fault, and the time-consuming difference between the sonographer group and the intelligent group. Results:①There was no significant difference in the overall distribution of RTP scores between the sonographer group and intelligent group [5 (5, 6) points vs 5 (5, 6) points, Z=0.355, P=0.722]. The RTP acquisition rate of the sonographer group and intelligent group was not statistically significant (78.72% vs 76.60%, χ 2=0.55, P=0.458). The consistency and correlation of RTP obtained by the two groups were high (Kappa=0.645, φ=0.646, both P<0.001). ②The effective layers of the sonographer group were 9 (8, 9) and the intelligent group was 8 (7, 9). The fault acquisition rate of the doctor group was higher than that of the intelligent group (78.72% vs 68.51%, χ 2=12.52, P=0.001). The consistency and correlation of the two groups in obtaining faults were media (Kappa=0.503, φ=0.521, both P<0.001). ③The time-consuming of the intelligent group was significantly lower than that of the sonographer group [1.50 (1.23, 1.75)s vs 26.94 (22.28, 30.48)s, Z=11.440, P<0.001]. Conclusions:This research model can quickly and accurately realize the extraction and tomography of the key plane of the normal fetal palate on the 11-13 + 6 week.
ABSTRACT
Objective:To explore the accuracy and clinical application value of a Multi-Agent Reinforcement Learning framework (MARL framework) in three-dimensional ultrasound to automatically locate the coronal plane of the uterus.Methods:A total of 144 female patients who underwent routine gynecological examinations in Luohu People′s Hospital during May 2020 were selected as the experimental subjects. The three-dimensional volume data of the uterus of all the experimental subjects were collected by using the Resona-8 high-end color Doppler ultrasound system. A sonographer with more than 5 years of clinical experience manually locate the coronal plane of the uterus in all collected data, and at the same time automatically locate the coronal plane of the uterus MARL framework. The coronal plane images of the uterus obtained by the two methods were saved, and the operation time of the two methods was recorded. The coronal plane uterine images obtained by the two methods were mixed together, and the images were scored 0-1 by two senior ultrasound experts in a double-blind manner. The average score greater than or equal to 0.6 points was considered qualified.Results:①In 144 volunteers, among the coronal planes of the uterus located by the two methods, 131 were qualified by the manual method, and 137 were qualified by the automatic method.There was no statistical difference between the manual and automatic coronal plane images of the uterus (χ 2=1.934, P=0.164) by the chi-square test. ②Using interquartile range analysis, the median and interquartile range of the image score of the automatic group was 0.80(0.75, 0.90), while the median and interquartile range of the image score of the manual group was 0.80(0.75, 0.90). The Wilcoxon signed rank test was used to analyze the quality of the coronal plane images obtained by manual and automatic methods, and the difference was not statistically significant ( Z=1.241, P=0.215). ③The paired t test was used to compare the time required to locate the coronal surface of the uterus, by manual method (63.65±10.182)s, by automatic method (3.25±0.294)s, the difference between the two methods was statistically significant ( t=19.52, P<0.001). Conclusions:The method based on MARL framework has a high correlation with the manual locating of the coronal plane of uterus in three-dimensional ultrasound, and greatly reduces the operation time. It can be effectively applied in clinical practice and lays a foundation for the automatic diagnosis of uterine related diseases.
ABSTRACT
Objective:To explore the imaging rate and diagnostic rate of positioning the fetal conus medullaris by three-dimensional ultrasound method to detect atlantoaxial intervertebral space, comparing it with the traditional two-dimensional and three-dimensional ultrasound methods.Methods:Consecutively 318 singleton fetuses received routine ultrasound screening during the second trimester were enrolled from November 2017 to December 2018 in Shenzhen Luohu People′s Hospital and Shenzhen People′s Hospital. These fetuses included 276 normal cases and 42 abnormal cases. The abnormal group contained 11 cases tethered cords fetuses(tethered cords group) and 31 cases non-tethered fetuses(non-tethered group). A new ultrasound method named detecting atlanto-axial intervertebral space with three-dimensional ultrasound and traditional two-dimensional and three-dimensional ultrasound methods were used to acquire and store the images. The positions of the fetal conus medullaris were analyzed blindly and recorded by three experienced physicians using three different methods with off-line software.Results:①The χ 2 test comparing multiple sample rates was used to compare the imaging acquisition success rate of fetal conus medullaris by three ultrasound methods. The test level was adjusted to be α′=0.05/4=0.0125, the results showed that there were no statistically significant differences between the three methods in the normal group (χ 2=7.39, P=0.025) and the abnormal group (χ 2=5.32, P=0.070). ②The χ 2 test comparing multiple sample rates was used to compare the diagnostic accuracy of fetal conus medullaris position in normal group by three methods, it showed there was no significant difference in the correct rate of conus medullaris position in the normal group (χ 2=2.52, P=0.284). ③The χ 2 test comparing multiple sample rates was used to compare the diagnostic accuracy of the fetal conus medullaris in tethered cord group and non-tethered group using 3 methods, the difference was not statistically significant in tethered cord group (χ 2=1.22, P=0.543), while the difference was statistically significant in non-tethered group(χ 2=9.69, P=0.008). Conclusions:The method of detecting atlanto-axial intervertebral space with three-dimensional ultrasound has a high imaging rate and diagnostic accuracy in positioning the fetal conus medullaris. Positioning of fetal conus medullaris by detecting atlanto-axial intervertebral space with three-dimensional ultrasound is better than traditional two-dimensional and three-dimensional ultrasound in the abnormal non-tethered fetuses, which can provide more valuable information for prenatal diagnosis consultation and prenatal and postnatal care.
ABSTRACT
Objective To explore the accuracy of ultrasonic diagnosis using the tele-ultrasound robot system . Methods During the period from May to June 2018 ,42 volunteers were consecutive selected to participate in this study ,and their digestive system and urinary system were examined using the robot method manufactured by GI Tech Co . ,Ltd ,Shenzhen and the traditional method . The results including the ultrasound diagnosis and the inspection time of two methods in each patient were compared . The ultrasonographic diagnosis of each volunteer was obtained by two methods and the time was recorded . The ultrasound images of the two methods were mixed together ,and the quality of the images was evaluated double-blindly by two senior doctors . Results There were actually 25 positive lesions in 42 volunteers . In the ultrasonic diagnosis of the two methods ,22 lesions were positive detected by robot method ,with 5 lesions misdiagnosed . In the traditional method , 24 lesions were positive detected , with 1 lesions misdiagnosed . Using the Wilcoxon signed rank test of paired sample comparison ,the score obtained by the robot method was 4 .79 ± 0 .57 ,and the score obtained by the traditional method was 4 .81 ± 0 .54 ( Z =0 .775 ,P= 0 .439) ,the difference was not statistically significant . There was no statistically significant difference in the images'qulity between the robot method and the traditional method using the chi-square test of the four-grid data( P >0 .05) . The check time for volunteers with negative result was ( 8 .64 ± 2 .95) min in robotic method and ( 2 .55 ± 0 .74 ) min in the traditional method ,the difference was statistically significant ( t =15 .161 , P =0 .000) . Conclusions The robot method has high value in common disease diagnosis and high quality in image acquisition ,and can be used in real-time diagnosis of the remote areas or community medical .