1
|
Automated ultrasound assessment of amniotic fluid index using deep learning. Med Image Anal 2021; 69:101951. [PMID: 33515982 DOI: 10.1016/j.media.2020.101951] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2020] [Revised: 12/13/2020] [Accepted: 12/21/2020] [Indexed: 12/19/2022]
Abstract
The estimation of antenatal amniotic fluid (AF) volume (AFV) is important as it offers crucial information about fetal development, fetal well-being, and perinatal prognosis. However, AFV measurement is cumbersome and patient specific. Moreover, it is heavily sonographer-dependent, with measurement accuracy varying greatly depending on the sonographer's experience. Therefore, the development of accurate, robust, and adoptable methods to evaluate AFV is highly desirable. In this regard, automation is expected to reduce user-based variability and workload of sonographers. However, automating AFV measurement is very challenging, because accurate detection of AF pockets is difficult owing to various confusing factors, such as reverberation artifact, AF mimicking region and floating matter. Furthermore, AF pocket exhibits an unspecified variety of shapes and sizes, and ultrasound images often show missing or incomplete structural boundaries. To overcome the abovementioned difficulties, we develop a hierarchical deep-learning-based method, which consider clinicians' anatomical-knowledge-based approaches. The key step is the segmentation of the AF pocket using our proposed deep learning network, AF-net. AF-net is a variation of U-net combined with three complementary concepts - atrous convolution, multi-scale side-input layer, and side-output layer. The experimental results demonstrate that the proposed method provides a measurement of the amniotic fluid index (AFI) that is as robust and precise as the results from clinicians. The proposed method achieved a Dice similarity of 0.877±0.086 for AF segmentation and achieved a mean absolute error of 2.666±2.986 and mean relative error of 0.018±0.023 for AFI value. To the best of our knowledge, our method, for the first time, provides an automated measurement of AFI.
Collapse
|
2
|
Sekhon S, Rosenbloom JI, Doering M, Conner SN, Macones GA, Colditz GA, Tuuli MG, Carter EB. Diagnostic utility of maximum vertical pocket versus amniotic fluid index in assessing amniotic fluid volume for the prediction of adverse maternal and fetal outcomes: a systematic review and meta-analysis. J Matern Fetal Neonatal Med 2019; 34:3730-3739. [PMID: 31709861 DOI: 10.1080/14767058.2019.1691988] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Abstract
Objective: To compare the utility of maximum vertical pocket versus amniotic fluid index for predicting adverse perinatal outcomes.Methods: Systematic review of randomized clinical studies comparing these two ultrasound techniques and random-effects meta-analysis to quantify a range of perinatal outcomes.Result: Six studies with 4278 women were eligible. Use of the maximum vertical pocket reduced the rate of diagnosis of oligohydramnios (pooled relative risk 0.38; 95% confidence interval 0.27, 0.53). Use of the maximum vertical pocket was associated with significantly lower rates of non-reassuring fetal heart tracing, cesarean delivery for fetal distress, and induction of labor for oligohydramnios. There were no differences in the rates of cesarean delivery, presence of meconium, umbilical artery pH <7.1, 5-minute Apgar score <7, or admission to the neonatal intensive care unit.Conclusion: The use of maximum vertical pocket is associated with a lower rate of pregnancy intervention without any worsening of adverse pregnancy outcomes.
Collapse
Affiliation(s)
- Subhjit Sekhon
- Department of Surgery, Division of Public Health Sciences, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Joshua I Rosenbloom
- Department of Obstetrics and Gynecology, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Michelle Doering
- Bernard Becker Medical Library, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Shayna N Conner
- Department of Obstetrics and Gynecology, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - George A Macones
- Department of Obstetrics and Gynecology, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Graham A Colditz
- Department of Surgery, Division of Public Health Sciences, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Methodius G Tuuli
- Department of Obstetrics and Gynecology, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Ebony B Carter
- Department of Obstetrics and Gynecology, Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| |
Collapse
|
3
|
Rosati P, Guariglia L, Cavaliere AF, Ciliberti P, Buongiorno S, Ciardulli A, Cianci S, Vitale SG, Cignini P, Mappa I. A comparison between amniotic fluid index and the single deepest vertical pocket technique in predicting adverse outcome in prolonged pregnancy. J Prenat Med 2016; 9:12-5. [PMID: 26918093 DOI: 10.11138/jpm/2015.9.1.012] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
OBJECTIVE to compare perinatal outcome in induced postterm pregnancies with normal amniotic volume and in patients with prolonged pregnancy undergone induction for oligohydramnios, evaluated by two different ultrasonographic methods. METHODS amniotic fluid volume was measured, using Single Deepest Vertical Pocket (SDVP) and Amniotic Fluid Index (AFI), in 961 singleton uncomplicated prolonged pregnancies. In 109 of these patients, hospitalization was planned for induction of labor, during or after 42 weeks of gestation, for oligohydramnios, postterm pregnancy and other indications in 47, 51 and 11 cases, respectively. Perinatal outcome included: rate of caesarean section, fetal distress, non reassuring fetal heart tracing, presence of meconium, umbilical artery pH < 7.1, Apgar score at 5 minutes < 7, admission to neonatal intensive care unit (NICU). RESULTS oligohydramnios was diagnosed in 4.89% of cases, when at least one of the two methods was used. A reduced AFI and SDVP value identified 4.47% and 3.75% of cases, respectively, even if without statistical difference. No statistical differences were reported in perinatal outcomes in postterm versus prolonged pregnancies with oligohydramnios, also in relation to the two different ultrasonographic methods. CONCLUSIONS oligohydramnios is more frequently diagnosed using AFI than SDVP, consequently determining a higher rate of induction of labor. Moreover, perinatal outcome in prolonged induced pregnancies is not affected by oligohydramnios.
Collapse
Affiliation(s)
- Paolo Rosati
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| | - Lorenzo Guariglia
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| | - Anna Franca Cavaliere
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| | - Paola Ciliberti
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| | - Silvia Buongiorno
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| | - Andrea Ciardulli
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| | - Stefano Cianci
- Department of General Surgery and Medical Surgical Specialties, University of Catania, Catania, Italy
| | - Salvatore Giovanni Vitale
- Department of General Surgery and Medical Surgical Specialties, University of Catania, Catania, Italy
| | - Pietro Cignini
- Department of Prenatal Diagnosis, Altamedica Fetal Maternal Medical Centre, Rome, Italy
| | - Ilenia Mappa
- Department of Obstetrics and Gynecology, Catholic University of the Sacred Heart, Rome, Italy
| |
Collapse
|
4
|
Abele H, Starz S, Hoopmann M, Yazdi B, Rall K, Kagan KO. Idiopathic Polyhydramnios and Postnatal Abnormalities. Fetal Diagn Ther 2012; 32:251-5. [PMID: 22760013 DOI: 10.1159/000338659] [Citation(s) in RCA: 41] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2012] [Accepted: 04/05/2012] [Indexed: 01/06/2023]
Affiliation(s)
- Harald Abele
- Department of Obstetrics and Gynaecology, University of Tübingen, Tübingen, Germany
| | | | | | | | | | | |
Collapse
|
5
|
Abstract
PURPOSE OF REVIEW Recognition of the fetus at risk for death or damage in utero, quantifying the risk, balancing fetal risk against the risk of neonatal complications from immaturity and determining optimal time and mode of intervention, is a cornerstone of modern perinatal medicine. Antepartum fetal testing is essential in making these crucial decisions. The art and science of fetal assessment is fluid. In this treatise, the evolution of testing is reviewed, test accuracy results examined and suggestions for future applications are considered. RECENT FINDINGS Composite testing of a range of fetal biophysical variables is an excellent predictor of fetal acidemia and risk of death or damage. Confusion regarding the optimal means of measuring one of these variables, amniotic fluid volume, has been addressed in the literature and contemporary studies from several independent sources indicate that the amniotic fluid index method should be abandoned in favor of the maximal vertical pocket method. It is becoming increasingly more evident that a spectrum of fetal testing modalities based on interrogation of different aspects of fetal adaptive responses to adversity is preferable in fetal testing. Further it is evident that in some fetal diseases, such as intrauterine growth restriction, fetal condition may change acutely and accordingly best outcome is achieved by much more frequent testing. The question of whether intervention for fetal compromise can prevent subsequent neurological sequelae remains open. SUMMARY There has been remarkable advancement in identifying the fetus at risk. The concept of multispectral combined fetal testing including acute biophysical variables, amniotic fluid volume and arterial and venous Doppler flow velocity waveforms is established.
Collapse
Affiliation(s)
- Frank A Manning
- Department of Obstetrics and Gynecology, Division of Maternal-Fetal Medicine, New York Medical College, Valhalla, New York, USA.
| |
Collapse
|
6
|
Nabhan AF, Abdelmoula YA. Amniotic fluid index versus single deepest vertical pocket: a meta-analysis of randomized controlled trials. Int J Gynaecol Obstet 2008; 104:184-8. [PMID: 19046586 DOI: 10.1016/j.ijgo.2008.10.018] [Citation(s) in RCA: 37] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2008] [Revised: 10/07/2008] [Accepted: 10/21/2008] [Indexed: 10/21/2022]
Abstract
OBJECTIVE To compare the use of the amniotic fluid index with the single deepest vertical pocket measurement, during antepartum fetal surveillance, in preventing adverse pregnancy outcome. SEARCH STRATEGY We searched the Cochrane Pregnancy and Childbirth Group's Trials Register (January 2008), the Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library 2008, Issue 2), MEDLINE (1966 to May 2008), and the metaRegister of Controlled Trials (May 2008). We handsearched the citation lists of relevant publications, review articles, and included studies. SELECTION CRITERIA Randomized controlled trials involving women with a singleton pregnancy, whether at low or high risk, undergoing ultrasound measurement of amniotic fluid volume as part of antepartum assessment of fetal well-being that compared the amniotic fluid index and the single deepest vertical pocket measurement. DATA COLLECTION AND ANALYSIS Both authors independently assessed eligibility and quality, and extracted the data. RESULTS Four trials (3125 women) met the inclusion criteria. When the amniotic fluid index was used, significantly more cases of oligohydramnios were diagnosed (risk ratio (RR) 2.33, 95% CI 1.67-3.24), and more women had inductions of labor (RR 2.10, 95% CI 1.60-2.76) and cesarean delivery for fetal distress (RR 1.45, 95% CI 1.07-1.97). There is no evidence that one method is superior to the other in the prevention of poor peripartum outcomes, including: admission to a neonatal intensive care unit; an umbilical artery pH of less than 7.1; the presence of meconium; an Apgar score of less than 7 at 5 minutes; or cesarean delivery. CONCLUSION Single deepest vertical pocket measurement is the method of choice for the assessment of amniotic fluid volume.
Collapse
|
7
|
Liu H, Zheng Z, Wintour E. Aquaporins and Fetal Fluid Balance. Placenta 2008; 29:840-7. [DOI: 10.1016/j.placenta.2008.07.010] [Citation(s) in RCA: 32] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/10/2008] [Revised: 07/20/2008] [Accepted: 07/24/2008] [Indexed: 01/01/2023]
|
8
|
Nabhan AF, Abdelmoula YA. Amniotic fluid index versus single deepest vertical pocket as a screening test for preventing adverse pregnancy outcome. Cochrane Database Syst Rev 2008; 2008:CD006593. [PMID: 18646160 PMCID: PMC6464731 DOI: 10.1002/14651858.cd006593.pub2] [Citation(s) in RCA: 45] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
BACKGROUND Amniotic fluid volume is an important parameter in the assessment of fetal well-being. Oligohydramnios occurs in many high-risk conditions and is associated with poor perinatal outcomes. Many caregivers practice planned delivery by induction of labor or caesarean section after diagnosis of decreased amniotic fluid volume at term. There is no clear consensus on the best method to assess amniotic fluid adequacy. OBJECTIVES To compare the use of the amniotic fluid index with the single deepest vertical pocket measurement as a screening tool for decreased amniotic fluid volume in preventing adverse pregnancy outcome. SEARCH STRATEGY We searched the Cochrane Pregnancy and Childbirth Group's Trials Register (January 2008), the Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library 2007, Issue 2), MEDLINE (1966 to May 2007) and the metaRegister of Controlled Trials (May 2007). We handsearched the citation lists of relevant publications, review articles, and included studies. SELECTION CRITERIA Randomised controlled trials involving women with a singleton pregnancy, whether at low or high risk, undergoing ultrasound measurement of amniotic fluid volume as part of antepartum assessment of fetal well-being that compared the amniotic fluid index and the single deepest vertical pocket measurement. DATA COLLECTION AND ANALYSIS Both authors independently assessed eligibility and quality, and extracted the data. MAIN RESULTS Four trials (3125 women) met the inclusion criteria. There is no evidence that one method is superior to the other in the prevention of poor peripartum outcomes, including: admission to a neonatal intensive care unit; an umbilical artery pH of less than 7.1; the presence of meconium; an Apgar score of less than 7 at five minutes; or caesarean delivery. When the amniotic fluid index was used, significantly more cases of oligohydramnios were diagnosed (risk ratio (RR, random) 2.33, 95% CI 1.67 to 3.24), and more women had inductions of labor (RR (fixed) 2.10, 95% CI 1.60 to 2.76) and caesarean delivery for fetal distress (RR (fixed) 1.45, 95% CI 1.07 to 1.97). AUTHORS' CONCLUSIONS The single deepest vertical pocket measurement in the assessment of amniotic fluid volume during fetal surveillance seems a better choice since the use of the amniotic fluid index increases the rate of diagnosis of oligohydramnios and the rate of induction of labor without improvement in peripartum outcomes. A systematic review of the diagnostic accuracy of both methods in detecting decreased amniotic fluid volume is required.
Collapse
Affiliation(s)
- Ashraf F Nabhan
- Department of Obstetrics and Gynecology, Ain Shams University, 16 Ali Fahmi Kamel Street, Heliopolis, Cairo, Egypt, 11351.
| | | |
Collapse
|
9
|
Peixoto-Filho FM, Sá RAM, Lopes LM, Velarde LGC, Marchiori E, Ville Y. Three-dimensional ultrasound fetal urinary bladder volume measurement: reliability of rotational (VOCALTM) technique using different steps of rotation. Arch Gynecol Obstet 2007; 276:345-9. [PMID: 17431648 DOI: 10.1007/s00404-007-0360-2] [Citation(s) in RCA: 30] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2006] [Accepted: 03/16/2007] [Indexed: 11/25/2022]
Abstract
OBJECTIVE The aim of the study was to investigate the inter- and intraobserver reliability in measuring the fetal bladder volume by 3d ultrasound imaging by VOCAL. In addition a comparison of 15 degrees and 30 degrees rotation steps calculation had been performed. METHODS Measurements (n = 240) of FB volume were performed in 30 low-risk patients with gestation times ranging from 22 to 39 weeks by two independent observers blind to each other. All fetuses were examined and no ultrasound detectable malformation was found. The volume for each FB was measured twice by the observers who used the Virtual Organ Computed-aided Analysis (VOCAL) technique. Distinct sets of 12 and 6 planes were obtained after sequential rotations of 15 degrees and 30 degrees, respectively. The internal contour of fetal bladder was determined manually and carefully as to exclude adjacent structures from volume calculation. Wilcoxon signed-rank test was used for the comparison of paired samples in the cases of replication within and between observers. Spearman's rank correlation was used to study the relationship among angles. Bland and Altman's graphical approach was used to investigate the agreement between observers. RESULTS Both techniques were shown to be highly reliable. No significant difference was found between the measurements of FB volume with the VOCAL technique by varying either the steps of rotation or the observers. CONCLUSION Excellent correlations were found for both observers in the use of rotation angles of 15 degrees and 30 degrees . Since a significantly faster evaluation was obtained by using a 30 degrees rotation step it must be preferred to assess the FB volume. Our results show that the VOCAL technique, with a plane rotation of 30 degrees , can be used in a simple way to estimate fetal urine production.
Collapse
Affiliation(s)
- F M Peixoto-Filho
- Centro Pré-natal de Diagnóstico e Tratamento - CPDT, Laranjeiras Clínica Perinatal, Rua das Laranjeiras, 445, Rio de Janeiro, RJ, Brazil.
| | | | | | | | | | | |
Collapse
|