1
|
Sun L, Yu J, Yao J, Cao Y, Sun N, Chen K, Lin Y, Ji C, Zhang J, Ling C, Yang Z, Pan Q, Yang R, Yang X, Ni D, Yin L, Deng X. A novel artificial intelligence model for measuring fetal intracranial markers during the first trimester based on two-dimensional ultrasound image. Int J Gynaecol Obstet 2024. [PMID: 38944698 DOI: 10.1002/ijgo.15762] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Revised: 05/30/2024] [Accepted: 06/17/2024] [Indexed: 07/01/2024]
Abstract
OBJECTIVE To establish reference ranges of fetal intracranial markers during the first trimester and develop the first novel artificial intelligence (AI) model to measure key markers automatically. METHODS This retrospective study used two-dimensional (2D) ultrasound images from 4233 singleton normal fetuses scanned at 11+0-13+6 weeks of gestation at the Affiliated Suzhou Hospital of Nanjing Medical University from January 2018 to July 2022. We analyzed 10 key markers in three important planes of the fetal head. Based on these, reference ranges of 10 fetal intracranial markers were established and an AI model was developed for automated marker measurement. AI and manual measurements were compared to evaluate differences, correlations, consistency, and time consumption based on mean error, Pearson correlation analysis, intraclass correlation coefficients (ICCs), and average measurement time. RESULTS The results of AI and manual methods had strong consistency and correlation (all ICC values >0.75, all r values >0.75, and all P values <0.001). The average absolute error of both only ranged from 0.124 to 0.178 mm. AI achieved a 100% detection rate for abnormal cases. Additionally, the average measurement time of AI was only 0.49 s, which was more than 65 times faster than the manual measurement method. CONCLUSION The present study first established the normal standard reference ranges of fetal intracranial markers based on a large Chinese population data set. Furthermore, the proposed AI model demonstrated its capability to measure multiple fetal intracranial markers automatically, serving as a highly effective tool to streamline sonographer tasks and mitigate manual measurement errors, which can be generalized to first-trimester scanning.
Collapse
Affiliation(s)
- Lingling Sun
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Junxuan Yu
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China
| | - Jiezhi Yao
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China
| | - Yan Cao
- Shenzhen RayShape Medical Technology Co., Ltd, Shenzhen, Guangdong, China
| | - Naimin Sun
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Keqi Chen
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Yujia Lin
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China
| | - Chunya Ji
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Jun Zhang
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Chen Ling
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Zhong Yang
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Qi Pan
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Ronghao Yang
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China
| | - Xin Yang
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China
| | - Dong Ni
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, Guangdong, China
| | - Linliang Yin
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| | - Xuedong Deng
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China
| |
Collapse
|
2
|
Hu Y, Sun L, Feng L, Wang J, Zhu Y, Wu Q. The role of routine first-trimester ultrasound screening for central nervous system abnormalities: a longitudinal single-center study using an unselected cohort with 3-year experience. BMC Pregnancy Childbirth 2023; 23:312. [PMID: 37138220 PMCID: PMC10157940 DOI: 10.1186/s12884-023-05644-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Accepted: 04/25/2023] [Indexed: 05/05/2023] Open
Abstract
BACKGROUND To evaluate the role of a standardized first-trimester scan in screening different kinds of central nervous system malformations and to report a 3-year experience from a tertiary center using an unselected cohort. METHODS This was a retrospective analysis of prospectively collected data from a single center evaluating first-trimester scans with predesigned standardized protocols performed between 1 May 2017 and 1 May 2020, involving 39,526 pregnancies. All pregnant women underwent a series of prenatal ultrasound scans at 11-14, 20-24, 28-34 and 34-38 weeks of gestation. Abnormalities were confirmed by magnetic resonance imaging, postmortem examination or trained ultrasound professionals. Pregnancy outcomes and some postnatal follow-up were obtained from maternity medical records and telephone calls. RESULTS A total of 38,586 pregnancies included in the study. The detection rates of CNS anomalies by ultrasound in the first, second, third and late third trimester were 32%, 22%, 25%, and 16%, respectively. And there were 5% of CNS anomalies missed by prenatal ultrasound. In the first-trimester scan, we diagnosed all cases of exencephaly, anencephaly, alobar holoprosencephaly and meningoencephalocele, and some cases of posterior cranial fossa anomalies (20%), open spina bifida (67%), semilobar holoprosencephaly (75%) and severe ventriculomegaly (8%). Vein of Galen aneurysmal malformation, closed spina bifida, lobar holoprosencephaly, intracranial infection, arachnoid cyst, agenesis of the corpus callosum, cysts of the septum pellucidum and isolated absence of the septum pellucidum were never detected during the first trimester. The abortion rates of fetal CNS anomalies detected by first-trimester scan, second-trimester scan, and third- trimester scan were 96%, 84% and 14%, respectively. CONCLUSIONS The study showed that almost 1/3 of central nervous system anomalies were detected by the standard first-trimester scan and these cases were associated with a high rate of abortion. Early screening for fetal abnormalities gives parents more time for medical advice and safer abortion if needed. It is therefore recommended that some major CNS anomalies should be screened in the first trimester. The standardized anatomical protocol, consisting of four fetal brain planes, were recommended for routine first trimester ultrasound screening.
Collapse
Affiliation(s)
- Yu Hu
- Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing, P. R. China
- Beijing Maternal and Child Health Care Hospital, Beijing, P. R. China
| | - Lijuan Sun
- Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing, P. R. China
- Beijing Maternal and Child Health Care Hospital, Beijing, P. R. China
| | - Li Feng
- Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing, P. R. China
- Beijing Maternal and Child Health Care Hospital, Beijing, P. R. China
| | - Jingjing Wang
- Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing, P. R. China
- Beijing Maternal and Child Health Care Hospital, Beijing, P. R. China
| | - Yantong Zhu
- Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing, P. R. China
- Beijing Maternal and Child Health Care Hospital, Beijing, P. R. China
| | - Qingqing Wu
- Beijing Obstetrics and Gynecology Hospital, Capital Medical University, Beijing, P. R. China.
- Beijing Maternal and Child Health Care Hospital, Beijing, P. R. China.
- Department Ultrasound, Beijing Obstetrics and Gynecology Hospital, Capital Medical University, No.251 Yaojiayuan Road, Beijing, Chaoyang District, 100026, P. R. China.
| |
Collapse
|
3
|
Altmann R, Scharnreitner I, Auer C, Hirtler L, Springer C, Falschlehner S, Arzt W. Visualization of the Third Ventricle, the Future Cavum Septi Pellucidi, and the Cavum Veli Interpositi at 11+3 to 13+6 Gestational Weeks on 3D Transvaginal Ultrasound Including Normative Data. ULTRASCHALL IN DER MEDIZIN (STUTTGART, GERMANY : 1980) 2023; 44:e72-e82. [PMID: 35213924 DOI: 10.1055/a-1683-6141] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
OBJECTIVES To show the development of the third ventricle, commissural plate, future cavum septi pellucidi, and cavum veli interpositi in weeks 12-14 by transvaginal 3D ultrasound. METHODS This is a prospective transvaginal 3D study carried out to define the third ventricle and the diencephalic midline structures surrounding it. 93 of 387 fetuses in which the commissural plate with the future cavum septi pellucidi, cavum veli interpositi, and the roof of the third ventricle could be well visualized, were selected with the choroid plexus of the third ventricle and the pituitary gland serving as leading structures. In a small number of fetuses, the optic chiasm could also be displayed. In addition, the following measurements were performed: third ventricle craniocaudal and anteroposterior, roof of the third ventricle/cavum veli interpositi, and fcsp. RESULTS The sonomorphologic characteristics of the commissural plate, the future cavum septi pellucidi, and the cavum veli interpositi are described IN 9% OF THE FETUSES examined. Measurements of the third ventricle, cavum veli interpositi, and the roof of the third ventricle show the following results: 3rd V cc = 3.895 + 0.091*CRL mm; 3rd V ap = 4.175 + 0.036*CRL mm; CVI ap = 2.223 + 0.029*CRL mm; CVI cc = 0.139 + 0.02*CRL mm. CONCLUSION Transvaginal neurosonography enables visualization and measurement of the normal fetal third ventricle at 12-14 weeks of gestation including visualization of the future cavum septi pellucidi and the cavum veli interpositi. BEFORE USE IN PATIENTS CAN BE CONSIDERED, FURTHER SCIENTIFIC WORK IS REQUIRED.
Collapse
Affiliation(s)
- Reinhard Altmann
- Prenatal Medicine, Kepler University Hospital Med Campus IV, Linz, Austria
| | - Iris Scharnreitner
- Prenatal Medicine, Kepler University Hospital Med Campus IV, Linz, Austria
| | - Christian Auer
- Department of Neurosurgery, Kepler University Hospital, Linz, Austria
| | - Lena Hirtler
- Center for Anatomy and Cell Biology, Medical University of Vienna, Wien, Austria
| | - Claudia Springer
- Prenatal Medicine, Kepler University Hospital Med Campus IV, Linz, Austria
| | - Stephanie Falschlehner
- Department of Gynecology and Obstetrics, Kepler University Hospital Med Campus IV, Linz, Austria
| | - Wolfgang Arzt
- Prenatal Medicine, Kepler University Hospital Med Campus IV, Linz, Austria
| |
Collapse
|
4
|
Vasciaveo L, Rizzo G, Khalil A, Alameddine S, Di Girolamo R, Candia M, De Lucia G, Mappa I, Liberati M, Nappi L, D'Antonio F. Assessment of pericallosal artery at 11-14 weeks of gestation: Cohort study and meta-analysis. JOURNAL OF CLINICAL ULTRASOUND 2022; 50:984-988. [PMID: 35315936 DOI: 10.1002/jcu.23191] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Revised: 02/24/2022] [Accepted: 03/02/2022] [Indexed: 02/05/2023]
Abstract
OBJECTIVES To report the rate of visualization of the pericallosal artery (PCA) in the first trimester of pregnancy (11-14 weeks). METHODS Prospective observational study of consecutive fetuses undergoing first trimester risk assessment for chromosomal anomalies. The presence of PCA was assessed in a midsagittal view of fetal brain using high-definition power Color Doppler. A normal course of the PCA was defined as the visualization of an artery emerging from the anterior cerebral artery running parallel the corpus callosum (CC). The reference standard was the visualization of CC and PCA between the 20 and 22 weeks of gestation. We also performed a systematic review and meta-analysis of the published literature. Multivariate logistic regression and random-effect meta-analyses of proportion were used to analyze the data. RESULTS Cohort study: Five-hundred women were included. PCA was identified trans-abdominally or transvaginally at 11-14 weeks of gestation in 98.8% (95% CI 97.4-99.6: 494/500); of the four cases of PCA not identified one had a diagnosis of complete agenesis of the corpus callosum during the anomaly scan which was confirmed at birth. Systematic review of the published literature: Six studies (1093 fetuses, including the present series) were included. The PCA was detected at the 11-14 weeks scan and confirmed to co-exist with a normal CC at time of the anomaly scan in 96.9% (95% CI 93.8-99.0); 20.6% (95% CI 5.7-41.7) of fetuses with no clear identification of the PCA at the 11-14 weeks scan had a normal appearance of the CC at the time of anomaly scan. CONCLUSION Prenatal ultrasonography has a high diagnostic accuracy in detecting PCA in the first trimester. Visualization of the PCA at the time of 11-14 scan is highly specific for the presence of a normal CC later in pregnancy.
Collapse
Affiliation(s)
- Lorenzo Vasciaveo
- Fetal Medicine Unit, Department of Obstetrics and Gynaecology, University of Foggia, Foggia, Italy
| | - Giuseppe Rizzo
- Department of Obstetrics and Gynaecology, Fondazione Policlinico Tor Vergata Università Roma Tor Vergata Roma, Rome, Italy
- Fetal Medicine Unit, Saint George's Hospital, London, UK
| | - Asma Khalil
- Fetal Medicine Unit, Saint George's Hospital, London, UK
| | - Sara Alameddine
- Centre for High-Risk Pregnancy and Fetal Care, Department of Obstetrics and Gynaecology, University of Chieti, Chieti, Italy
| | - Raffaella Di Girolamo
- Centre for High-Risk Pregnancy and Fetal Care, Department of Obstetrics and Gynaecology, University of Chieti, Chieti, Italy
| | - Mariangela Candia
- Fetal Medicine Unit, Department of Obstetrics and Gynaecology, University of Foggia, Foggia, Italy
| | - Graziana De Lucia
- Fetal Medicine Unit, Department of Obstetrics and Gynaecology, University of Foggia, Foggia, Italy
| | - Ilenia Mappa
- Department of Obstetrics and Gynaecology, Fondazione Policlinico Tor Vergata Università Roma Tor Vergata Roma, Rome, Italy
| | - Marco Liberati
- Centre for High-Risk Pregnancy and Fetal Care, Department of Obstetrics and Gynaecology, University of Chieti, Chieti, Italy
| | - Luigi Nappi
- Fetal Medicine Unit, Department of Obstetrics and Gynaecology, University of Foggia, Foggia, Italy
| | - Francesco D'Antonio
- Centre for High-Risk Pregnancy and Fetal Care, Department of Obstetrics and Gynaecology, University of Chieti, Chieti, Italy
| |
Collapse
|
5
|
Scoping Review of the Prenatal Diagnosis of Agenesis of the Corpus Callosum. J Obstet Gynecol Neonatal Nurs 2020; 49:423-436. [PMID: 32687791 DOI: 10.1016/j.jogn.2020.06.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/01/2020] [Indexed: 11/22/2022] Open
Abstract
OBJECTIVE To map and summarize the literature related to the prenatal diagnosis of agenesis of the corpus callosum (ACC) to inform nursing practice. DATA SOURCES We searched MEDLINE, CINAHL, PyscINFO, and Academic Search Complete with the use of strings of curated terms to cover the broad ACC nomenclature. Documents were published in English between 2009 and June 1, 2020. We also hand searched the reference lists of included documents. STUDY SELECTION We screened 582 abstracts and retrieved the full texts of primary research articles, reviews, discussion papers, and peer-reviewed book chapters if the abstracts specifically mentioned ACC and the prenatal period. We excluded case reports, conference and poster abstracts, papers on broader anomalies, and animal studies. We reviewed 84 full-text documents and identified 61 for inclusion. DATA EXTRACTION We charted the data through an iterative process under headings for location, article type, study design, participant age, ACC type, recruitment, method, tools/assessments, results, key recommendations, gestational age at diagnosis, termination of pregnancy rate, the definition of isolated ACC, and our notes of critique of the document. DATA SYNTHESIS We constructed a narrative synthesis from thematically arranged data. In the included documents, ACC was diagnosed between 17 and 38 weeks gestation and was frequently described as heterogeneous because of different causes, presentations, and outcomes. Whether the ACC was isolated as the only anomaly or present with other anomalies was considered the key factor for prenatal counseling. However, the definition of isolated ACC was inconsistent. CONCLUSION The inconsistent nomenclature and definitions of an isolated presentation of ACC increase the ambiguity in the prenatal diagnosis and must be considered when the outcome and diagnostic efficacy studies are interpreted. There is an absence of research on parents' experiences of prenatal diagnoses of ACC to inform holistic nursing interventions and the provision of psychosocial support.
Collapse
|