1
|
Tang J, Han J, Xie B, Xue J, Zhou H, Jiang Y, Hu L, Chen C, Zhang K, Zhu F, Lu L. The Two-Stage Ensemble Learning Model Based on Aggregated Facial Features in Screening for Fetal Genetic Diseases. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:2377. [PMID: 36767743 PMCID: PMC9914999 DOI: 10.3390/ijerph20032377] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Revised: 01/18/2023] [Accepted: 01/25/2023] [Indexed: 06/18/2023]
Abstract
With the advancement of medicine, more and more researchers have turned their attention to the study of fetal genetic diseases in recent years. However, it is still a challenge to detect genetic diseases in the fetus, especially in an area lacking access to healthcare. The existing research primarily focuses on using teenagers' or adults' face information to screen for genetic diseases, but there are no relevant directions on disease detection using fetal facial information. To fill the vacancy, we designed a two-stage ensemble learning model based on sonography, Fgds-EL, to identify genetic diseases with 932 images. Concretely speaking, we use aggregated information of facial regions to detect anomalies, such as the jaw, frontal bone, and nasal bone areas. Our experiments show that our model yields a sensitivity of 0.92 and a specificity of 0.97 in the test set, on par with the senior sonographer, and outperforming other popular deep learning algorithms. Moreover, our model has the potential to be an effective noninvasive screening tool for the early screening of genetic diseases in the fetus.
Collapse
Affiliation(s)
- Jiajie Tang
- School of Information Management, Wuhan University, Wuhan 430072, China
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
| | - Jin Han
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
- Graduate School, Guangzhou Medical University, Guangzhou 511436, China
| | - Bingbing Xie
- School of Information Management, Wuhan University, Wuhan 430072, China
| | - Jiaxin Xue
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
- Graduate School, Guangzhou Medical University, Guangzhou 511436, China
| | - Hang Zhou
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
- Graduate School, Guangzhou Medical University, Guangzhou 511436, China
| | - Yuxuan Jiang
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
| | - Lianting Hu
- Medical Big Data Center, Guangdong Provincial People’s Hospital, Guangzhou 510080, China
- Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangzhou 510080, China
| | - Caiyuan Chen
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
- Graduate School, Guangzhou Medical University, Guangzhou 511436, China
| | - Kanghui Zhang
- School of Information Management, Wuhan University, Wuhan 430072, China
| | - Fanfan Zhu
- School of Information Management, Wuhan University, Wuhan 430072, China
| | - Long Lu
- School of Information Management, Wuhan University, Wuhan 430072, China
- Institute of Pediatrics, Prenatal Diagnostic Center, Guangzhou Women and Children’s Medical Center, Guangzhou Medical University, Guangzhou 510180, China
- Center for Healthcare Big Data Research, The Big Data Institute, Wuhan University, Wuhan 430072, China
- School of Public Health, Wuhan University, Wuhan 430072, China
| |
Collapse
|
2
|
Pranpanus S, Keatkongkaew K, Suksai M. Utility of fetal facial markers on a second trimester genetic sonogram in screening for Down syndrome in a high-risk Thai population. BMC Pregnancy Childbirth 2022; 22:27. [PMID: 35016623 PMCID: PMC8751369 DOI: 10.1186/s12884-021-04332-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2021] [Accepted: 12/03/2021] [Indexed: 11/28/2022] Open
Abstract
Background To establish the reference ranges and evaluate the efficacy of the fetal facial sonomarkers prenasal thickness (PT), nasal bone length (NBL), PT/NBL ratio and NBL/PT ratio for Down syndrome screening in the second trimester of high-risk pregnancies using two-dimensional (2D) ultrasound. Methods A prospective study was done in Thai pregnant women at high risk for structural and chromosomal abnormalities between May 2018 and May 2019. The main exclusion criteria were any fetal anatomical anomaly detected on ultrasonography or postpartum examination, abnormal chromosome or syndrome other than Down syndrome. Ultrasounds were performed in 375 pregnant women at 14 to 22 weeks’ gestation and the fetal facial parameters were analyzed. Down syndrome results were confirmed by karyotyping. The reference ranges of these facial ultrasound markers were constructed based on the data of our population. The Down syndrome screening performance using these facial ultrasound markers was evaluated. Results In total, 340 euploid fetuses and 11 fetuses with Down syndrome met the inclusion criteria. The PT, NBL, and PT/NBL ratios in the euploid fetuses gradually increased with gestation progression while the NBL/PT ratio gradually decreased between 14–22 weeks’ gestation. The NBL, PT/NBL ratio, and NBL/PT ratio all had 100% sensitivity and PT had 91% sensitivity. These facial markers had 100% negative predictive value for Down syndrome screening in the second trimester. The Bland–Altman analysis showed the intra- and inter-observer variations of PT and NBL had high intraclass correlation coefficients (ICC) in both operators, with ICCs of 0.98 and 0.99 and inter-observer ICCs of 0.99 for both operators. Conclusion The facial ultrasound markers are very useful for second trimester Down syndrome screening in our population. These facial ultrasound markers were easily identifiable and highly consistent either intra- or inter-operator by using widely-available 2D ultrasound. However, the reference ranges for these markers need to be constructed based on individual populations. Trial registration Registration number: REC 61–029-12–3. Date of registration: 18 May 2018.
Collapse
|
3
|
Du Y, Ren Y, Yan Y, Cao L. Absent fetal nasal bone in the second trimester and risk of abnormal karyotype in a prescreened population of Chinese women. Acta Obstet Gynecol Scand 2017; 97:180-186. [PMID: 29164604 PMCID: PMC5814939 DOI: 10.1111/aogs.13263] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2017] [Accepted: 11/11/2017] [Indexed: 12/19/2022]
Abstract
INTRODUCTION The aim of this study was to evaluate the value of absent fetal nasal bone in the prediction of fetal chromosomal abnormalities, according to whether it was associated with other soft markers or structural abnormalities in a prescreened population of Chinese pregnant women. MATERIAL AND METHODS In this retrospective cohort study, women whose fetuses had absent nasal bone detected during the second trimester ultrasound scan were followed. Fetal karyotyping was performed and pregnancy outcomes were recorded. The association between absent fetal nasal bone with abnormal karyotype was evaluated according to whether soft markers or structural abnormalities were also observed. RESULTS Fetal nasal bone was assessed in 56 707 singleton pregnancies. After exclusion of unqualified cases, 71 (71/56 707, 0.13%) fetuses were included in the final analyses, of which 16 (16/71, 22.54%) were detected to have chromosomal abnormalities, including 12 cases of trisomy-21, three of trisomy-18, and one of micro-deletion (in 7q). Among the 42 cases with isolated absence of nasal bone, two had trisomy-21 and one had a micro-deletion. Absence of nasal bone in association with other structural abnormalities had a higher rate of abnormal karyotypes compared with isolated absence of nasal bone [83.33% (10/12) vs. 7.14% (3/42), Fisher's exact test χ2 = 25.620, p < 0.001]. CONCLUSION Absent fetal nasal bone is a highly specific ultrasonographic soft marker that should be included in the routine second trimester ultrasound scan.
Collapse
Affiliation(s)
- Yan Du
- Office of Clinical Epidemiology, Obstetrics and Gynecology Hospital of Fudan University, Shanghai, China
| | - Yunyun Ren
- Ultrasound Department, Obstetrics and Gynecology Hospital of Fudan University, Shanghai, China
| | - Yingliu Yan
- Ultrasound Department, Obstetrics and Gynecology Hospital of Fudan University, Shanghai, China
| | - Li Cao
- Ultrasound Department, Obstetrics and Gynecology Hospital of Fudan University, Shanghai, China
| |
Collapse
|