ABSTRACT
Objective To determine the consistency of urogenital hiatus ( U H ) data between the semi‐automatic measurement and manual measurement using transperineal pelvic floor ultrasonography . Methods Total of 286 three‐dimensional images of minimal U H dimension were obtained . And they were divided into study group ( 100 images) and test group ( 186 images) randomly . T hree experts traced and created the w hole profile of the U H of those images in the study group by M AT LAB . T hen the semi‐automatic software was obtained through machine learning algorithms . In the test group , 6 parameters of U H ( including anterioposterior diameter , transverse diameter ,circumference , area ,left and right levator urethral gap distance) were measured by two experts ( D 1 and D2 ) both manually and semi‐automatically . T he time experts spent on measuring was also recorded and compared . Results T he time used for semi‐automatic measurement was significantly shorter than that for manual measurement [ ( 7 .49 ± 1 .51 ) s vs ( 42 .42 ± 11 .08) s ,( 7 .52 ± 1 .37) s vs ( 43 .45 ± 9 .09) s for D1 and D2 , t ＝ －12 .09 ,－13 .64 ,all P＝0 .00] . T he Pearson correlation coefficients between semi‐automatic and manual measurements of 6 parameters were 0 .857 －0 .985 ( P ＜ 0 .01) ,0 .853 －0 .979 ( P ＜ 0 .01 ) in D1 and D2 ,respectively . T he interclass correlation coefficients ( ICC) of six parameters were ranged from 0 .846 －0 .985 for D1 and 0 .843～0 .979 for D2 ( all P ＜ 0 .01 ) . T he Bland Altman plot also showed good agreement between two methods . Conclusions Intellectual recognition and semi‐automatic measurement has simplified the process for U H measurement ,and it is proved to be a reliable and timesaving method that is practical for clinical use .
ABSTRACT
Objective We aim to evaluate and discuss the feasibility of Hyaline imaging of three-dimension sonography in observation of paravaginal support structure in normal nonporous women.Methods Total of 45 normal infertile women were chosen.Three-dimensional volume datasets were collected at rest by transperineal ultrasound.The three-dimensional Hyaline images were acquired off-line.We observed the morphologic features of paravaginal support structure on the axial plane in middle vagina and measured the anteroposterior and lateral horizontal distances between bilateral paravaginal support structure and ureter.The consistency between two sonographers were analyzed by intraclass correlation coefficient (ICC).Results In three-dimensional Hyaline imaging sonogram,paravaginal support structure was appeared as typically tenting-like shaped.The anteroposterior distances between paravaginal support structure and center of ureter were listed as followed:left (-0.31 ± 1.29) mm,right (0.47 ± O.99) mm.While the lateral horizontal distances were left (12.67 ± 6.70) mm,right (13.01 ± 5.75) mm.There were no statistical differences between bilateral both anteroposterior and lateral horizontal distances.The consistency between two sonographers for distinguishing paravaginal support structure on the middle-vaginal plane and measuring distances between paravaginal support structure and center of ureter was remarkably high (ICC is 0.87 and 0.82).Conclusions Hyaline imaging technology of three-dimensional pelvic floor sonography could be used to observe paravaginal support structure in women.The normal paravaginal support structure is typically showed as bilateral symmetrical tenting-like structure,which is on the same level as the center of ureter.It provides normal anatomic radiological evidence and helps study defect of paravaginal support structure caused by pregnancy or delivery.
ABSTRACT
Objective To investigate the feasibility of the automatic cystocele severity grading software for quantitative evaluation of prolapse of bladder posterior wall by transperineal ultrasound . Methods One hundred and seventy transperineal ultrasound video clips were recorded when the female patients performing the Valsalva maneuver and those clips were divided into training group ( 85 cases) and test group ( 85 cases) randomly ,then the ralated structures of the images from the training group offline were marked . Through machine learning algorithm ,the computer had learned and was able to analyzed the marking information ,then the automatic cystocele severity grading software was obtained . And later the software was ran to mark the structures and get the cystocele severity grading in the images from the test group . Meanwhile , the same structures of the same images manually were marked and after an interval of more than two weeks the process were repeated by 3 doctors . Finally the grading results obtained from the software and the measurers of the 3 doctors were compared . Results The intelligent identification and automatic measurement software obtained from the machine learning algorithm was able to identify the related structures . The grading results of each measurer were of good consistency ( κ :0 .72 －0 .78 ;ICC :0 .980－0 .990) . The grading results between different measurers were of good consistency ( κ :0 .65－0 .75 ;ICC :0 .985－0 .992) . The grading results between automatic software and three different measurers were of good consistency ( κ :0 .63－0 .67 ;ICC :0 .967－0 .969 ; r ＝0 .936 ,0 .943 ,0 .936 ,all P ＜0 .01) . Conclusions The automatic cystocele severity grading software is able to identify the related structures in the images and reliable to apply the software in pelvic floor ultrasound .
ABSTRACT
Objective To assess the recovery of contraction function ofpuborectalis (PR) in women at different periods after delivery with different delivery modes,and to discuss the effect of delivery mode on PR contraction.Methods Between September 2016 and December 2016,168 primiparas who underwent ultrasound examination at the First Affiliated Hospital of Shenzhen University were enrolled.All participants were able to accomplish Valsalva maneuver.Participants were divided into two groups according to delivery modes:the vaginal delivery group and the cesarean section group.This two groups were further divided into three groups according to their periods after delivery:42-60 days after delivery (group l),61-90 days after delivery (group 2) and more than 90 days after delivery (group 3).Two dimensional translabial ultrasound examination were performed in all participants both at rest and in maximal contraction status.Thickness of anterior,middle and posterior parts of PR were measured and thickening rate was calculated.Data were evaluated by t-test and comparisons were made between the vaginal delivery groups and cesarean section groups,respectively.Results In the vaginal delivery group 1,the thickening rate of the anterior,middle and posterior parts of right-side PR were (35.57 ± 19.80)％,(31.46 ± 20.96)％ and (24.18 ± 21.51)％,while the thickening rate of left-side PR were (25.23 ± 14.36)％,(21.25 ± 13.79)％ and (20.60± 11.58)％,respectively.In the cesarean section group 1,the thickening rate of the anterior,middle and posterior parts of right-side PR were (30.27± 19.22)％,(29.50± 17.21)％ and (28.25± 14.92)％,while the thickening rate of left-side PR were (33.02± 20.65)％,(30.56± 20.11)％ and (28.64± 14.84)％,respectively.In the vaginal delivery group 2,the thickening rate of the anterior,middle and posterior parts of right-side PR were (29.62t 16.93)％,(24.94± 14.56)％ and (19.26± 11.12)％,while the thickening rate of left-side PR were (20.17±15.70)％,(19.95± 13.07)％ and (22.19± 14.50)％,respectively.In the cesarean section group 2,the thickening rate of the anterior,middle and posterior parts of right-side PR were (30.82± 15.65)％,(17.70± 10.34)％and (19.30± 7.02)％,while the thickening rate of left-side PR were (18.33± 1 1.61)％,(16.46 ± 10.51)％and (16.62± 1 1.69)％,respectively.In the vaginal delivery group 3,the thickening rate of the anterior,middle and posterior parts of right-side PR were (33.56 ±19.79)％,(25.18 ±11.80)％ and (17.44± 11.41)％,while the thickening rate of left-side PR were (28.06± 10.93)％,(22.25 ± 11.82)％ and (22.15 ± 12.69)％,respectively.In the cesarean section group 3,the thickening rate of the anterior,middle and posterior parts of right-side PR were (46.36± 20.65)％,(17.00 ± 10.34)％ and (10.86±3.40)％,while the thickening rate of left-side PR were (22.54± 13.81)％,(13.90± 10.51)％ and (18.24± 11.17)％,respectively.There were no statistically difference of the thickening rate of PR in both side between the vaginal delivery subgroups and the cesarean section subgroups (For group 1,right side:t=0.87,P=0.34;t=0.32,P=0.75;t=0.68,P=0.50;left side:t=1.48,P=0.15;t=1.82,P=0.08;t=1.36,P=0.12.For group 2,right side:t=0.22,P=0.83;t=1.64,P=0.11;t=0.01,P=0.99;left side:t=0.43,P=0.67;t=0.79,P=0.44;t=1.13,P=0.27.For group 3,right side:t=0.73,P=0.48;t=1.22,P=0.23;t=0.868,P=0.40.left side:t=0.89,P=0.41;t=1.79,P=0.89;t=0.79,P=0.44).Conclusion There was no significant differences between the impact of two delivery modes on the contraction function of the PR,and the protective effect of caesarean section on the contraction function of the PR was limited.