1
|
Vasung L, Xu J, Abaci-Turk E, Zhou C, Holland E, Barth WH, Barnewolt C, Connolly S, Estroff J, Golland P, Feldman HA, Adalsteinsson E, Grant PE. Cross-Sectional Observational Study of Typical in utero Fetal Movements Using Machine Learning. Dev Neurosci 2022; 45:105-114. [PMID: 36538911 PMCID: PMC10233700 DOI: 10.1159/000528757] [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: 08/09/2022] [Accepted: 11/14/2022] [Indexed: 12/24/2022] Open
Abstract
Early variations of fetal movements are the hallmark of a healthy developing central nervous system. However, there are no automatic methods to quantify the complex 3D motion of the developing fetus in utero. The aim of this prospective study was to use machine learning (ML) on in utero MRI to perform quantitative kinematic analysis of fetal limb movement, assessing the impact of maternal, placental, and fetal factors. In this cross-sectional, observational study, we used 76 sets of fetal (24-40 gestational weeks [GW]) blood oxygenation level-dependent (BOLD) MRI scans of 52 women (18-45 years old) during typical pregnancies. Pregnant women were scanned for 5-10 min while breathing room air (21% O2) and for 5-10 min while breathing 100% FiO2 in supine and/or lateral position. BOLD acquisition time was 20 min in total with effective temporal resolution approximately 3 s. To quantify upper and lower limb kinematics, we used a 3D convolutional neural network previously trained to track fetal key points (wrists, elbows, shoulders, ankles, knees, hips) on similar BOLD time series. Tracking was visually assessed, errors were manually corrected, and the absolute movement time (AMT) for each joint was calculated. To identify variables that had a significant association with AMT, we constructed a mixed-model ANOVA with interaction terms. Fetuses showed significantly longer duration of limb movements during maternal hyperoxia. We also found a significant centrifugal increase of AMT across limbs and significantly longer AMT of upper extremities <31 GW and longer AMT of lower extremities >35 GW. In conclusion, using ML we successfully quantified complex 3D fetal limb motion in utero and across gestation, showing maternal factors (hyperoxia) and fetal factors (gestational age, joint) that impact movement. Quantification of fetal motion on MRI is a potential new biomarker of fetal health and neuromuscular development.
Collapse
Affiliation(s)
- Lana Vasung
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Junshen Xu
- Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, USA
| | - Esra Abaci-Turk
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Cindy Zhou
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Elizabeth Holland
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - William H Barth
- Department of Obstetrics and Gynecology, Massachusetts General Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Carol Barnewolt
- Department of Radiology, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Susan Connolly
- Department of Radiology, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Judy Estroff
- Department of Radiology, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Polina Golland
- Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, USA
- Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts, USA
- Institute for Medical Engineering and Science, MIT, Cambridge, Massachusetts, USA
| | - Henry A Feldman
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
- Institutional Centers for Clinical and Translational Research, Boston Children's Hospital, Boston, Massachusetts, USA
| | - Elfar Adalsteinsson
- Department of Electrical Engineering and Computer Science, MIT, Cambridge, Massachusetts, USA
- Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts, USA
- Institute for Medical Engineering and Science, MIT, Cambridge, Massachusetts, USA
| | - P Ellen Grant
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
- Department of Radiology, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
2
|
Khatib N, Thaler I, Beloosesky R, Dabaja H, Ganem N, Abecassis P, Ginsberg Y, Weiner Z. The effect of maternal hyperoxygenation on fetal circulatory system in normal growth and IUGR fetuses. What we can learn from this impact. J Matern Fetal Neonatal Med 2017; 31:914-918. [DOI: 10.1080/14767058.2017.1301925] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
3
|
Fuchs T. Values of T/QRS ratio in pregnancies complicated by intrauterine growth restriction. J Perinat Med 2016; 44:751-757. [PMID: 26020551 DOI: 10.1515/jpm-2014-0305] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/23/2015] [Accepted: 04/17/2015] [Indexed: 11/15/2022]
Abstract
AIMS To evaluate values of T/QRS ratio in normal pregnancies and those complicated by intrauterine growth restriction (IUGR) using non-invasive method with transabdominal electrodes. Assessment of fetal well-being in IUGR pregnancies. METHODS Fetal electrocardiograms were recorded and analyzed by KOMPOREL software from ITAM (Zabrze, Poland) and T/QRS ratios were automatically calculated. Doppler velocimetry of the middle cerebral artery and umbilical artery was carried out. The study group consisted of IUGR pregnancies with normal cerebroplacental ratios (CPRs) (n=110), IUGR pregnancies with decreased CPRs (n=29), and healthy controls (n=549). Analyses were performed between the study groups and by gestational age. T/QRS ratio variables and CPRs were calculated. Analysis of variance and linear regression were performed. RESULTS Maximum values, maximum minimal value differences, and standard deviations of T/QRS ratio were significantly different between the IUGR group with reduced CPRs and normal CPRs (P=0.0009, P=0.0000, P=0.0034, respectively) as well as between the IUGR group with reduced CPRs and healthy controls (P=0.0000, P=0.0001, P=0.0009, respectively). Mean maximum values in the IUGR group with reduced CPRs exceeded normal values. CONCLUSIONS T/QRS ratio may be useful in assessing fetal well-being in IUGR pregnancies; however, future studies are needed to determine typical ranges of T/QRS ratio in pregnancies complicated by IUGR.
Collapse
|
4
|
Teppema LJ, Dahan A. The Ventilatory Response to Hypoxia in Mammals: Mechanisms, Measurement, and Analysis. Physiol Rev 2010; 90:675-754. [DOI: 10.1152/physrev.00012.2009] [Citation(s) in RCA: 257] [Impact Index Per Article: 18.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023] Open
Abstract
The respiratory response to hypoxia in mammals develops from an inhibition of breathing movements in utero into a sustained increase in ventilation in the adult. This ventilatory response to hypoxia (HVR) in mammals is the subject of this review. The period immediately after birth contains a critical time window in which environmental factors can cause long-term changes in the structural and functional properties of the respiratory system, resulting in an altered HVR phenotype. Both neonatal chronic and chronic intermittent hypoxia, but also chronic hyperoxia, can induce such plastic changes, the nature of which depends on the time pattern and duration of the exposure (acute or chronic, episodic or not, etc.). At adult age, exposure to chronic hypoxic paradigms induces adjustments in the HVR that seem reversible when the respiratory system is fully matured. These changes are orchestrated by transcription factors of which hypoxia-inducible factor 1 has been identified as the master regulator. We discuss the mechanisms underlying the HVR and its adaptations to chronic changes in ambient oxygen concentration, with emphasis on the carotid bodies that contain oxygen sensors and initiate the response, and on the contribution of central neurotransmitters and brain stem regions. We also briefly summarize the techniques used in small animals and in humans to measure the HVR and discuss the specific difficulties encountered in its measurement and analysis.
Collapse
Affiliation(s)
- Luc J. Teppema
- Department of Anesthesiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Albert Dahan
- Department of Anesthesiology, Leiden University Medical Center, Leiden, The Netherlands
| |
Collapse
|
6
|
Richardson BS, Bocking AD. Metabolic and circulatory adaptations to chronic hypoxia in the fetus. Comp Biochem Physiol A Mol Integr Physiol 1998; 119:717-23. [PMID: 9683411 DOI: 10.1016/s1095-6433(98)01010-1] [Citation(s) in RCA: 89] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
When oxygenation is compromised the fetus is capable of a number of adaptive responses, both protective and potentially pathologic, which can be categorized as those affecting fetal metabolism and those affecting fetal oxygen transport. However, both the extent and the duration of the impairment in oxygenation will bear on these adaptive responses. While fetal O2 extraction is increased when oxygenation is acutely compromised thus maintaining O2 consumption, with chronic hypoxemia there is a decrease in O2 consumption paralleling that in O2 delivery and contributed to by the resultant fall-off in growth and alterations in behavioural activity. While a redistribution of blood flow to vital organs continues to be evident, this will be less pronounced than that seen with acute hypoxemia reflecting diminished hormonal changes, underlying metabolic alterations, and the extent to which fetal blood gases are normalized. Much of this information is based on experimental data using unanesthetized fetal sheep with chronic catheterization; however, clinical outcome data and the use of investigative techniques including ultrasound scanning and cordocentesis have supported the relevance of this experimental data to the human situation.
Collapse
Affiliation(s)
- B S Richardson
- Department of OB/GYN, University of Western Ontario, London, Canada
| | | |
Collapse
|
9
|
Abstract
It has been suggested that the near full-term fetus in-utero has a sensori-neural hearing loss compared to the neonate due to the relative hypoxia resulting from placental oxygenation compared to pulmonary oxygenation. This hypothesis was tested by estimating the threshold of the fetus to vibrio-acoustic stimulation applied to the maternal abdomen while the mother was breathing room air and again when breathing oxygen. Fetal response was assessed by maternal perception of fetal movement and by objective demonstration of movement by ultrasound. It has been shown that the fetal responses are to the acoustic component of the stimulus, that the acoustic stimulus is not overly attenuated or masked, and that maternal oxygen inhalation enhances fetal oxygenation. The results showed that the threshold was lower and/or the response was stronger when the mother was breathing oxygen compared to when she was breathing room air. Thus it is confirmed that in-utero the fetus has an hypoxia-induced sensori-neural hearing loss. At birth, with the shift to more efficient pulmonary oxygenation, there is an improvement in auditory threshold.
Collapse
Affiliation(s)
- H Sohmer
- Department of Physiology, Hebrew University-Hadassah Medical School, Jerusalem, Israel
| | | | | |
Collapse
|
11
|
Bekedam DJ, Mulder EJ, Snijders RJ, Visser GH. The effects of maternal hyperoxia on fetal breathing movements, body movements and heart rate variation in growth retarded fetuses. Early Hum Dev 1991; 27:223-32. [PMID: 1802673 DOI: 10.1016/0378-3782(91)90196-a] [Citation(s) in RCA: 35] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
In hypoxemic intrauterine growth-retarded fetuses (IUGR) there is a reduction in the incidence of fetal movements and in fetal heart rate variation. A causal relationship with the impairment of fetal oxygenation has been suggested. In 16 IUGR fetuses and in 13 normally grown fetuses maternal hyperoxygenation was applied for 40 min to increase fetal PO2 levels. All IUGR fetuses had abnormal Doppler blood velocity waveforms of the umbilical artery suggesting an impaired uteroplacental exchange. The effect of hyperoxygenation on fetal breathing and body movements and on fetal heart rate was evaluated. In the IUGR fetuses there was a significant increase in fetal breathing and body movements and in heart rate variation during hyperoxygenation as compared to the preceding control period of 40 min. No significant changes in fetal breathing and body movements were found in the normally grown control fetuses. A surprising observation was the increase of the number of heart rate decelerations after discontinuation of the maternal hyperoxygenation. It is concluded that in IUGR fetuses the increase in fetal heart rate variation and the increase in the incidence of breathing and body movements during maternal hyperoxygenation substantiates the relationship between these variables and the oxygenation status of the fetus.
Collapse
Affiliation(s)
- D J Bekedam
- Department of Obstetrics and Gynaecology, University Hospital Groningen, The Netherlands
| | | | | | | |
Collapse
|