Artificial intelligence-based diagnosis in fetal pathology using external ear shapes.
Journal
Prenatal diagnosis
ISSN: 1097-0223
Titre abrégé: Prenat Diagn
Pays: England
ID NLM: 8106540
Informations de publication
Date de publication:
18 Apr 2024
18 Apr 2024
Historique:
revised:
28
03
2024
received:
22
10
2023
accepted:
07
04
2024
medline:
18
4
2024
pubmed:
18
4
2024
entrez:
18
4
2024
Statut:
aheadofprint
Résumé
Here we trained an automatic phenotype assessment tool to recognize syndromic ears in two syndromes in fetuses-=CHARGE and Mandibulo-Facial Dysostosis Guion Almeida type (MFDGA)-versus controls. We trained an automatic model on all profile pictures of children diagnosed with genetically confirmed MFDGA and CHARGE syndromes, and a cohort of control patients, collected from 1981 to 2023 in Necker Hospital (Paris) with a visible external ear. The model consisted in extracting landmarks from photographs of external ears, in applying geometric morphometry methods, and in a classification step using machine learning. The approach was then tested on photographs of two groups of fetuses: controls and fetuses with CHARGE and MFDGA syndromes. The training set contained a total of 1489 ear photographs from 526 children. The validation set contained a total of 51 ear photographs from 51 fetuses. The overall accuracy was 72.6% (58.3%-84.1%, p < 0.001), and 76.4%, 74.9%, and 86.2% respectively for CHARGE, control and MFDGA fetuses. The area under the curves were 86.8%, 87.5%, and 90.3% respectively for CHARGE, controls, and MFDGA fetuses. We report the first automatic fetal ear phenotyping model, with satisfactory classification performances. Further validations are required before using this approach as a diagnostic tool.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : Agence Nationale de la Recherche
ID : ANR-10-IAHU-01
Organisme : Agence Nationale de la Recherche
ID : ANR-21-PMRB-0004
Organisme : National University of Singapore
ID : 2021-05-R/UP-NUS
Informations de copyright
© 2024 The Authors. Prenatal Diagnosis published by John Wiley & Sons Ltd.
Références
Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347‐1358. https://doi.org/10.1056/NEJMra1814259
Choy G, Khalilzadeh O, Michalski M, et al. Current applications and future impact of machine learning in radiology. Radiology. 2018;288(2):318‐328. https://doi.org/10.1148/radiol.2018171820
Novoa RA, Gevaert O, Ko JM. Marking the path toward artificial intelligence‐based image classification in dermatology. JAMA Dermatol. 2019;155(10):1105‐1106. https://doi.org/10.1001/jamadermatol.2019.1633
Loftus TJ, Tighe PJ, Filiberto AC, et al. Artificial intelligence and surgical decision‐making. JAMA Surg. 2020;155(2):148‐158. https://doi.org/10.1001/jamasurg.2019.4917
Gurovich Y, Hanani Y, Bar O, et al. Identifying facial phenotypes of genetic disorders using deep learning. Nat Med. 2019;25(1):60‐64. https://doi.org/10.1038/s41591‐018‐0279‐0
Zhang Q, Ding Y, Feng B, et al. Molecular and phenotypic expansion of Alström syndrome in Chinese patients. Front Genet. 2022;13:808919. https://doi.org/10.3389/fgene.2022.808919
Javitt MJ, Vanner EA, Grajewski AL, Chang TC. Evaluation of a computer‐based facial dysmorphology analysis algorithm (Face2Gene) using standardized textbook photos. Eye. 2022;36(4):859‐861. https://doi.org/10.1038/s41433‐021‐01563‐5
Latorre‐Pellicer A, Ascaso Á, Trujillano L, et al. Evaluating Face2Gene as a tool to identify Cornelia de Lange Syndrome by facial phenotypes. Int J Mol Sci. 2020;21(3):E1042. https://doi.org/10.3390/ijms21031042
Mishima H, Suzuki H, Doi M, et al. Evaluation of Face2Gene using facial images of patients with congenital dysmorphic syndromes recruited in Japan. J Hum Genet. 2019;64(8):789‐794. https://doi.org/10.1038/s10038‐019‐0619‐z
Rooijers W, Tio PaE, van der Schroeff MP, et al. Hearing impairment and ear anomalies in craniofacial microsomia: a systematic review. Int J Oral Maxillofac Surg. 2022;51(22):S0901‐S5027. Published online February 3. https://doi.org/10.1016/j.ijom.2022.01.005
Rymer K, Shiang R, Hsiung A, et al. Expanding the phenotype for the recurrent p.Ala391Glu variant in FGFR3: beyond Crouzon syndrome and acanthosis nigricans. Mol Genet Genomic Med. 2019;7(6):e656. https://doi.org/10.1002/mgg3.656
Peart LS, Gonzalez J, Bivona S, et al. Bilateral choanal stenosis in auriculocondylar syndrome caused by a PLCB4 variant. Am J Med Genet. 2022;188(4):1307‐1310. https://doi.org/10.1002/ajmg.a.62634
Andresen C, Matias A, Merz E. Fetal face: the whole picture. Ultraschall Med. 2012;33(5):431‐440. https://doi.org/10.1055/s‐0031‐1299482
Bartel‐Friedrich S, Wulke C. Classification and diagnosis of ear malformations. GMS Curr Top Otorhinolaryngol Head Neck Surg. 2008;6:Doc05.
Dudarewicz L, Kałuzewski B. Prenatal screening for fetal chromosomal abnormalities using ear length and shape as an ultrasound marker. Med Sci Monit. 2000;6(4):801‐806.
Nuñez‐Castruita A, López‐Serna N. Low‐set ears and associated anomalies in human foetuses. Int J Pediatr Otorhinolaryngol. 2018;104:126‐133. https://doi.org/10.1016/j.ijporl.2017.11.008
Sacchini C, El‐Sheikhah A, Cicero S, Rembouskos G, Nicolaides KH. Ear length in trisomy 21 fetuses at 11–14 weeks of gestation. Ultrasound Obstet Gynecol. 2003;22(5):460‐463. https://doi.org/10.1002/uog.903
Lehalle D, Gordon CT, Oufadem M, et al. Delineation of EFTUD2 haploinsufficiency‐related phenotypes through a series of 36 patients. Hum Mutat. 2014;35(4):478‐485. https://doi.org/10.1002/humu.22517
Sanlaville D, Etchevers HC, Gonzales M, et al. Phenotypic spectrum of CHARGE syndrome in fetuses with CHD7 truncating mutations correlates with expression during human development. J Med Genet. 2006;43(3):211‐217. https://doi.org/10.1136/jmg.2005.036160
Garcelon N, Neuraz A, Salomon R, et al. A clinician friendly data warehouse oriented toward narrative reports: Dr. Warehouse. J Biomed Inf. 2018;80:52‐63. https://doi.org/10.1016/j.jbi.2018.02.019
Zhou Y, Zaferiou S. Deformable models of ears in‐the‐wild for alignment and recognition. In: 2017 12th IEEE International Conference on Automatic Face Gesture Recognition (FG 2017); 2017:626‐633. https://doi.org/10.1109/FG.2017.79
Baken EK, Collyer ML, Kaliontzopoulou A, Adams DC. Geomorph v4.0 and gmShiny: enhanced analytics and a new graphical interface for a comprehensive morphometric experience. Methods Ecol Evol. 2021;12(12):2355‐2363. https://doi.org/10.1111/2041‐210X.13723
Hennocq Q, Bongibault T, Bizière M, et al. An automatic facial landmarking for children with rare diseases. Am J Med Genet. 2023;191(5):1210‐1221. https://doi.org/10.1002/ajmg.a.63126
landmarker.io. The Menpo Project. Accessed March 20, 2022. https://www.menpo.org/landmarkerio/
Bartko JJ. The intraclass correlation coefficient as a measure of reliability. Psychol Rep. 1966;19(1):3‐11. https://doi.org/10.2466/pr0.1966.19.1.3
Rohlf FJ, Slice D. Extensions of the Procrustes method for the optimal superimposition of landmarks. Syst Zool. 1990;39(1):40‐59. https://doi.org/10.2307/2992207
McInnes L, Healy J, Melville J. UMAP: uniform manifold approximation and projection for dimension reduction. Published online September 17, 2020. https://doi.org/10.48550/arXiv.1802.03426
R Core Team. European environment agency. 2020. Accessed January 18, 2023. https://www.eea.europa.eu/data‐and‐maps/indicators/oxygen‐consuming‐substances‐in‐rivers/r‐development‐core‐team‐2006
Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’16. Association for Computing Machinery; 2016:785‐794. https://doi.org/10.1145/2939672.2939785
Sachs MC. plotROC: a tool for plotting ROC curves. J Stat Softw. 2017;79:2. https://doi.org/10.18637/jss.v079.c02
Protocole Type D’examen Autopsique Foetal ou Néonatal. Haute Autorité de Santé. Accessed August 11, 2023. https://www.has‐sante.fr/jcms/c_1747470/fr/protocole‐type‐d‐examen‐autopsique‐foetal‐ou‐neonatal
Blake KD, Prasad C. CHARGE syndrome. Orphanet J Rare Dis. 2006;1:34. https://doi.org/10.1186/1750‐1172‐1‐34
Sondern K, Kreitz K, Hammer K, et al. 3D ultrasound evaluation of the fetal outer ear: novel biometry ratio and comparison of different surface display modes. Fetal Diagn Ther. 2019;46(3):200‐206. https://doi.org/10.1159/000497145
Biard JM, Payrat S, Clapuyt P, et al. Antenatal diagnosis of CHARGE syndrome: prenatal ultrasound findings and crucial role of fetal dysmorphic signs. About a series of 10 cases and review of literature. Eur J Med Genet. 2021;64(4):104189. https://doi.org/10.1016/j.ejmg.2021.104189
Legendre M, Gonzales M, Goudefroye G, et al. Antenatal spectrum of CHARGE syndrome in 40 fetuses with CHD7 mutations. J Med Genet. 2012;49(11):698‐707. https://doi.org/10.1136/jmedgenet‐2012‐100926
Busa T, Legendre M, Bauge M, et al. Prenatal findings in children with early postnatal diagnosis of CHARGE syndrome. Prenat Diagn. 2016;36(6):561‐567. https://doi.org/10.1002/pd.4825
Millischer AE, Sonigo P, Attie T, et al. Fetal MRI findings in a retrospective cohort of 26 cases of prenatally diagnosed CHARGE syndrome individuals. Prenat Diagn. 2019;39(9):781‐791. https://doi.org/10.1002/pd.5429
Batool S. The developing human‐clinically oriented embryology by Keith L. Moore. Accessed 24 June 2023. https://www.academia.edu/44502808/The_Developing_Human_Clinically_Oriented_Embryology_by_Keith_L_Moore
Chang CH, Chang FM, Yu CH, Liang RI, Ko HC, Chen HY. Fetal ear assessment and prenatal detection of aneuploidy by the quantitative three‐dimensional ultrasonography. Ultrasound Med Biol. 2000;26(5):743‐749. https://doi.org/10.1016/s0301‐5629(00)00206‐4
Hatanaka AR, Rolo LC, Mattar R, Araujo Júnior E, Nardozza LMM, Moron AF. Reference intervals for fetal ear length between 19 and 24 weeks of pregnancy on 3‐dimensional sonography. J Ultrasound Med. 2011;30(9):1185‐1190. https://doi.org/10.7863/jum.2011.30.9.1185
Chitkara U, Lee L, Oehlert JW, et al. Fetal ear length measurement: a useful predictor of aneuploidy? Ultrasound Obstet Gynecol. 2002;19(2):131‐135. https://doi.org/10.1046/j.0960‐7692.2001.00558.x
Merz E, Welter C. 2D and 3D ultrasound in the evaluation of normal and abnormal fetal anatomy in the second and third trimesters in a level III center. Ultraschall Med. 2005;26(1):9‐16. https://doi.org/10.1055/s‐2004‐813947
Shih JC, Shyu MK, Lee CN, Wu CH, Lin GJ, Hsieh FJ. Antenatal depiction of the fetal ear with three‐dimensional ultrasonography. Obstet Gynecol. 1998;91(4):500‐505. https://doi.org/10.1016/s0029‐7844(98)00021‐0
Rollnick BR, Kaye CI, Nagatoshi K, Hauck W, Martin AO, Reynolds JF. Oculoauriculovertebral dysplasia and variants: phenotypic characteristics of 294 patients. Am J Med Genet. 1987;26(2):361‐375. https://doi.org/10.1002/ajmg.1320260215