1
|
Specktor-Fadida B, Link-Sourani D, Rabinowich A, Miller E, Levchakov A, Avisdris N, Ben-Sira L, Hiersch L, Joskowicz L, Ben-Bashat D. Deep learning-based segmentation of whole-body fetal MRI and fetal weight estimation: assessing performance, repeatability, and reproducibility. Eur Radiol 2024; 34:2072-2083. [PMID: 37658890 DOI: 10.1007/s00330-023-10038-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2023] [Revised: 06/13/2023] [Accepted: 06/19/2023] [Indexed: 09/05/2023]
Abstract
OBJECTIVES To develop a deep-learning method for whole-body fetal segmentation based on MRI; to assess the method's repeatability, reproducibility, and accuracy; to create an MRI-based normal fetal weight growth chart; and to assess the sensitivity to detect fetuses with growth restriction (FGR). METHODS Retrospective data of 348 fetuses with gestational age (GA) of 19-39 weeks were included: 249 normal appropriate for GA (AGA), 19 FGR, and 80 Other (having various imaging abnormalities). A fetal whole-body segmentation model with a quality estimation module was developed and evaluated in 169 cases. The method was evaluated for its repeatability (repeated scans within the same scanner, n = 22), reproducibility (different scanners, n = 6), and accuracy (compared with birth weight, n = 7). A normal MRI-based growth chart was derived. RESULTS The method achieved a Dice = 0.973, absolute volume difference ratio (VDR) = 1.8% and VDR mean difference = 0.75% ([Formula: see text]: - 3.95%, 5.46), and high agreement with the gold standard. The method achieved a repeatability coefficient = 4.01%, ICC = 0.99, high reproducibility with a mean difference = 2.21% ([Formula: see text]: - 1.92%, 6.35%), and high accuracy with a mean difference between estimated fetal weight (EFW) and birth weight of - 0.39% ([Formula: see text]: - 8.23%, 7.45%). A normal growth chart (n = 246) was consistent with four ultrasound charts. EFW based on MRI correctly predicted birth-weight percentiles for all 18 fetuses ≤ 10thpercentile and for 14 out of 17 FGR fetuses below the 3rd percentile. Six fetuses referred to MRI as AGA were found to be < 3rd percentile. CONCLUSIONS The proposed method for automatic MRI-based EFW demonstrated high performance and sensitivity to identify FGR fetuses. CLINICAL RELEVANCE STATEMENT Results from this study support the use of the automatic fetal weight estimation method based on MRI for the assessment of fetal development and to detect fetuses at risk for growth restriction. KEY POINTS • An AI-based segmentation method with a quality assessment module for fetal weight estimation based on MRI was developed, achieving high repeatability, reproducibility, and accuracy. • An MRI-based fetal weight growth chart constructed from a large cohort of normal and appropriate gestational-age fetuses is proposed. • The method showed a high sensitivity for the diagnosis of small fetuses suspected of growth restriction.
Collapse
Affiliation(s)
- Bella Specktor-Fadida
- School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel.
| | | | - Aviad Rabinowich
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
- Department of Radiology, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
| | - Elka Miller
- Department of Medical Imaging, The Hospital for Sick Children, University of Toronto, Toronto, Canada
- Department of Medical Imaging, CHEO, University of Ottawa, Ottawa, Canada
| | - Anna Levchakov
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
| | - Netanell Avisdris
- School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
| | - Liat Ben-Sira
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
- Department of Radiology, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel
| | - Liran Hiersch
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
- Department of Obstetrics and Gynecology, Lis Hospital for Women's Health, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
| | - Leo Joskowicz
- School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, Israel
- Edmond and Lily Safra Center for Brain Sciences, The Hebrew University of Jerusalem, Jerusalem, Israel
| | - Dafna Ben-Bashat
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel.
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel.
| |
Collapse
|
2
|
Predicting fetal weight by three-dimensional limb volume ultrasound (AVol/TVol) and abdominal circumference. Chin Med J (Engl) 2021; 134:1070-1078. [PMID: 33883411 PMCID: PMC8116021 DOI: 10.1097/cm9.0000000000001413] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
Abstract
BACKGROUND Fetal weight is an important parameter to ensure maternal and child safety. The purpose of this study was to use three-dimensional (3D) limb volume ultrasound combined with fetal abdominal circumference (AC) measurement to establish a model to predict fetal weight and evaluate its efficiency. METHODS A total of 211 participants with single pregnancy (28-42 weeks) were selected between September 2017 and December 2018 in the Beijing Obstetrics and Gynecology Hospital of Capital Medical University. The upper arm (AVol)/thigh volume (TVol) of fetuses was measured by the 3D limb volume technique. Fetal AC was measured by two-dimensional ultrasound. Nine cases were excluded due to incomplete information or the interval between examination and delivery >7 days. The enrolled 202 participants were divided into a model group (134 cases, 70%) and a verification group (68 cases, 30%) by mechanical sampling method. The linear relationship between limb volume and fetal weight was evaluated using Pearson Chi-squared test. The prediction model formula was established by multivariate regression with data from the model group. Accuracy of the model formula was evaluated with verification group data and compared with traditional formulas (Hadlock, Lee2009, and INTERGROWTH-21st) by paired t-test and residual analysis. Receiver operating characteristic curves were generated to predict macrosomia. RESULTS AC, AVol, and TVol were linearly related to fetal weight. Pearson correlation coefficient was 0.866, 0.862, and 0.910, respectively. The prediction model based on AVol/TVol and AC was established as follows: Y = -481.965 + 12.194TVol + 15.358AVol + 67.998AC, R2adj = 0.868. The scatter plot showed that when birth weight fluctuated by 5% (i.e., 95% to 105%), the difference between the predicted fetal weight by the model and the actual weight was small. A paired t-test showed that there was no significant difference between the predicted fetal weight and the actual birth weight (t = -1.015, P = 0.314). Moreover, the residual analysis showed that the model formula's prediction efficiency was better than the traditional formulas with a mean residual of 35,360.170. The combined model of AVol/TVol and AC was superior to the Lee2009 and INTERGROWTH-21st formulas in the diagnosis of macrosomia. Its predictive sensitivity and specificity were 87.5% and 91.7%, respectively. CONCLUSION Fetal weight prediction model established by semi-automatic 3D limb volume combined with AC is of high accuracy, sensitivity, and specificity. The prediction model formula shows higher predictive efficiency, especially for the diagnosis of macrosomia. TRIAL REGISTRATION ClinicalTrials.gov, NCT03002246; https://clinicaltrials.gov/ct2/show/NCT03002246?recrs=e&cond=fetal&draw=8&rank=67.
Collapse
|
3
|
Carlin A, Kadji C, Cannie MM, Resta S, Kang X, Jani JC. The use of magnetic resonance imaging in the prediction of birthweight. Prenat Diagn 2019; 40:125-135. [PMID: 31319434 DOI: 10.1002/pd.5530] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2019] [Revised: 06/05/2019] [Accepted: 07/08/2019] [Indexed: 01/11/2023]
Abstract
Extremes of fetal growth can increase adverse pregnancy outcomes, and this is equally applicable to single and multiple gestations. Traditionally, these cases have been identified using simple two-dimensional ultrasound which is quite limited by its low precision. Magnetic resonance imaging (MRI) has now been used for many years in obstetrics, mainly as an adjunct to ultrasound for congenital abnormalities and increasingly as part of the post-mortem examination. However, MRI can also be used to accurately assess fetal weight as first demonstrated by Baker et al in 1994, using body volumes rather than standard biometric measurements. This publication was followed by several others, all of which confirmed the superiority of MRI; however, despite this initial promise, the technique has never been successfully integrated into clinical practice. In this review, we provide an overview of the literature, detail the various techniques and formulas currently available, discuss the applicability to specific high-risk groups and present our vision for the future of MRI within clinical obstetrics.
Collapse
Affiliation(s)
- Andrew Carlin
- Department of Obstetrics and Gynaecology, University Hospital Brugmann, Université Libre de Bruxelles, Brussels, Belgium
| | - Caroline Kadji
- Department of Obstetrics and Gynaecology, University Hospital Brugmann, Université Libre de Bruxelles, Brussels, Belgium
| | - Mieke M Cannie
- Department of Radiology, University Hospital Brugmann, Brussels, Belgium.,Department of Radiology, UZ Brussel, Vrije Universiteit Brussel, Brussels, Belgium
| | - Serena Resta
- Department of Obstetrics and Gynaecology, University Hospital Brugmann, Université Libre de Bruxelles, Brussels, Belgium
| | - Xin Kang
- Department of Obstetrics and Gynaecology, University Hospital Brugmann, Université Libre de Bruxelles, Brussels, Belgium
| | - Jacques C Jani
- Department of Obstetrics and Gynaecology, University Hospital Brugmann, Université Libre de Bruxelles, Brussels, Belgium
| |
Collapse
|
4
|
Liao K, Tang L, Peng C, Chen L, Chen R, Huang L, Liu P, Chen C. Two new models for the estimation of foetal weight more than a week before delivery: An MRI study. Eur J Radiol 2019; 121:108596. [PMID: 31623899 DOI: 10.1016/j.ejrad.2019.06.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2019] [Accepted: 06/27/2019] [Indexed: 10/26/2022]
Abstract
PURPOSE To develop and evaluate new formulas to determine the magnetic resonance imaging (MRI)-based estimated foetal weight (EFW) more than a week before delivery. METHODS The study included 153 women with singleton pregnancies who gave birth to live, normal neonates within 15-21 days of the MRI examination for whom foetal body volume biometry data were available at term. All foetuses were randomly divided into a testing group (102) and a validation group (51). Regression analysis was used to determine the single volume or the combination of volume and MRI-to-delivery interval that determined the EFW. The accuracy of the two new models and the primary existing model developed by Baker et al. were evaluated in validation group. RESULTS The two new models had similar mean percentage errors (MPEs) (3.9% vs 3.9%) and proportions of pregnancies with an MPE < 10% (92.2% vs 90.2%); the model incorporating volume and MRI-to-delivery had relatively higher proportions of pregnancies with an MPE < 5% (72.5% vs 64.7%) and EFWs in agreement with the birth weights. The error in the Baker model was almost twice that in the new models. CONCLUSION The accuracy of foetal weight estimation more than one week before delivery using the model developed by Baker et al. was poor and was significantly improved by the new models. A combination of the foetal body volume and MRI-to-delivery interval will enable the more accurate determination of the EFWs.
Collapse
Affiliation(s)
- Kedan Liao
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China
| | - Lian Tang
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China
| | - Cheng Peng
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China
| | - Lan Chen
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China
| | - Ruiying Chen
- Department of Radiology, NanFang Hospital, Southern Medical University, Guangzhou, China
| | - Lu Huang
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China
| | - Ping Liu
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China.
| | - Chunlin Chen
- Department of Obstetrics and Gynaecology, NanFang Hospital, Southern Medical University, Guangzhou, China.
| |
Collapse
|