|
1
|
Hennocq Q, Willems M, Amiel J, Arpin S, Attie-Bitach T, Bongibault T, Bouygues T, Cormier-Daire V, Corre P, Dieterich K, Douillet M, Feydy J, Galliani E, Giuliano F, Lyonnet S, Picard A, Porntaveetus T, Rio M, Rouxel F, Shotelersuk V, Toutain A, Yauy K, Geneviève D, Khonsari RH, Garcelon N. Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome. Sci Rep 2024; 14:2330. [PMID: 38282012 PMCID: PMC10822856 DOI: 10.1038/s41598-024-52691-3] [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: 12/20/2023] [Accepted: 01/22/2024] [Indexed: 01/30/2024] Open
Abstract
The field of dysmorphology has been changed by the use Artificial Intelligence (AI) and the development of Next Generation Phenotyping (NGP). The aim of this study was to propose a new NGP model for predicting KS (Kabuki Syndrome) on 2D facial photographs and distinguish KS1 (KS type 1, KMT2D-related) from KS2 (KS type 2, KDM6A-related). We included retrospectively and prospectively, from 1998 to 2023, all frontal and lateral pictures of patients with a molecular confirmation of KS. After automatic preprocessing, we extracted geometric and textural features. After incorporation of age, gender, and ethnicity, we used XGboost (eXtreme Gradient Boosting), a supervised machine learning classifier. The model was tested on an independent validation set. Finally, we compared the performances of our model with DeepGestalt (Face2Gene). The study included 1448 frontal and lateral facial photographs from 6 centers, corresponding to 634 patients (527 controls, 107 KS); 82 (78%) of KS patients had a variation in the KMT2D gene (KS1) and 23 (22%) in the KDM6A gene (KS2). We were able to distinguish KS from controls in the independent validation group with an accuracy of 95.8% (78.9-99.9%, p < 0.001) and distinguish KS1 from KS2 with an empirical Area Under the Curve (AUC) of 0.805 (0.729-0.880, p < 0.001). We report an automatic detection model for KS with high performances (AUC 0.993 and accuracy 95.8%). We were able to distinguish patients with KS1 from KS2, with an AUC of 0.805. These results outperform the current commercial AI-based solutions and expert clinicians.
Collapse
Affiliation(s)
- Quentin Hennocq
- Imagine Institute, INSERM UMR1163, 75015, Paris, France.
- Service de chirurgie maxillo-faciale et chirurgie plastique, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France.
- Centre de Référence des Malformations Rares de la Face et de la Cavité Buccale MAFACE, Filière Maladies Rares TeteCou, Paris, France.
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France.
- Laboratoire 'Forme et Croissance du Crâne', Faculté de Médecine, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Université Paris Cité, Paris, France.
- Hôpital Necker-Enfants Malades, 149 rue de Sèvres, 75015, Paris, France.
| | - Marjolaine Willems
- Département de Génétique Médicale, Maladies Rares et Médecine Personnalisée, Génétique clinique, CHU Montpellier, Centre de référence anomalies du développement SOOR, INSERM U1183, Montpellier University, Montpellier, France
| | - Jeanne Amiel
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
- Service de médecine génomique des maladies rares, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Stéphanie Arpin
- Service de Génétique, CHU Tours, UMR 1253, iBrain, Université de Tours, Inserm, Tours, France
| | - Tania Attie-Bitach
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
- Service de médecine génomique des maladies rares, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Thomas Bongibault
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Laboratoire 'Forme et Croissance du Crâne', Faculté de Médecine, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Université Paris Cité, Paris, France
| | - Thomas Bouygues
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Laboratoire 'Forme et Croissance du Crâne', Faculté de Médecine, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Université Paris Cité, Paris, France
| | - Valérie Cormier-Daire
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
- Service de médecine génomique des maladies rares, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Pierre Corre
- Nantes Université, CHU Nantes, Service de chirurgie maxillo-faciale et stomatologie, 44000, Nantes, France
- Nantes Université, Oniris, UnivAngers, CHU Nantes, INSERM, Regenerative Medicine and Skeleton, RMeS, UMR 1229, 44000, Nantes, France
| | - Klaus Dieterich
- Univ. Grenoble Alpes, Inserm, U1209, IAB, CHU Grenoble Alpes, 38000, Grenoble, France
| | | | | | - Eva Galliani
- Service de chirurgie maxillo-faciale et chirurgie plastique, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
- Centre de Référence des Malformations Rares de la Face et de la Cavité Buccale MAFACE, Filière Maladies Rares TeteCou, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
| | | | - Stanislas Lyonnet
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
- Service de médecine génomique des maladies rares, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Arnaud Picard
- Service de chirurgie maxillo-faciale et chirurgie plastique, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
- Centre de Référence des Malformations Rares de la Face et de la Cavité Buccale MAFACE, Filière Maladies Rares TeteCou, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
| | - Thantrira Porntaveetus
- Center of Excellence in Genomics and Precision Dentistry, Department of Physiology, Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand
| | - Marlène Rio
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
- Service de médecine génomique des maladies rares, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
| | - Flavien Rouxel
- Département de Génétique Médicale, Maladies Rares et Médecine Personnalisée, Génétique clinique, CHU Montpellier, Centre de référence anomalies du développement SOOR, INSERM U1183, Montpellier University, Montpellier, France
| | - Vorasuk Shotelersuk
- Center of Excellence for Medical Genomics, Department of Pediatrics, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand
| | - Annick Toutain
- Service de Génétique, CHU Tours, UMR 1253, iBrain, Université de Tours, Inserm, Tours, France
| | - Kevin Yauy
- Département de Génétique Médicale, Maladies Rares et Médecine Personnalisée, Génétique clinique, CHU Montpellier, Centre de référence anomalies du développement SOOR, INSERM U1183, Montpellier University, Montpellier, France
| | - David Geneviève
- Département de Génétique Médicale, Maladies Rares et Médecine Personnalisée, Génétique clinique, CHU Montpellier, Centre de référence anomalies du développement SOOR, INSERM U1183, Montpellier University, Montpellier, France
| | - Roman H Khonsari
- Imagine Institute, INSERM UMR1163, 75015, Paris, France
- Service de chirurgie maxillo-faciale et chirurgie plastique, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Paris, France
- Centre de Référence des Malformations Rares de la Face et de la Cavité Buccale MAFACE, Filière Maladies Rares TeteCou, Paris, France
- Faculté de Médecine, Université de Paris Cité, 75015, Paris, France
- Laboratoire 'Forme et Croissance du Crâne', Faculté de Médecine, Hôpital Necker-Enfants Malades, Assistance Publique-Hôpitaux de Paris, Université Paris Cité, Paris, France
| | | |
Collapse
|
|
2
|
Mundt P, Hertel A, Tharmaseelan H, Nörenberg D, Papavassiliu T, Schoenberg SO, Froelich MF, Ayx I. Analysis of Epicardial Adipose Tissue Texture in Relation to Coronary Artery Calcification in PCCT: The EAT Signature! Diagnostics (Basel) 2024; 14:277. [PMID: 38337793 PMCID: PMC10854976 DOI: 10.3390/diagnostics14030277] [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: 01/03/2024] [Revised: 01/25/2024] [Accepted: 01/25/2024] [Indexed: 02/12/2024] Open
Abstract
(1) Background: Epicardial adipose tissue influences cardiac biology in physiological and pathological terms. As it is suspected to be linked to coronary artery calcification, identifying improved methods of diagnostics for these patients is important. The use of radiomics and the new Photon-Counting computed tomography (PCCT) may offer a feasible step toward improved diagnostics in these patients. (2) Methods: In this retrospective single-centre study epicardial adipose tissue was segmented manually on axial unenhanced images. Patients were divided into three groups, depending on the severity of coronary artery calcification. Features were extracted using pyradiomics. Mean and standard deviation were calculated with the Pearson correlation coefficient for feature correlation. Random Forest classification was applied for feature selection and ANOVA was performed for group comparison. (3) Results: A total of 53 patients (32 male, 21 female, mean age 57, range from 21 to 80 years) were enrolled in this study and scanned on the novel PCCT. "Original_glrlm_LongRunEmphasis", "original_glrlm_RunVariance", "original_glszm_HighGrayLevelZoneEmphasis", and "original_glszm_SizeZoneNonUniformity" were found to show significant differences between patients with coronary artery calcification (Agatston score 1-99/≥100) and those without. (4) Conclusions: Four texture features of epicardial adipose tissue are associated with coronary artery calcification and may reflect inflammatory reactions of epicardial adipose tissue, offering a potential imaging biomarker for atherosclerosis detection.
Collapse
Affiliation(s)
- Peter Mundt
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| | - Alexander Hertel
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| | - Hishan Tharmaseelan
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| | - Dominik Nörenberg
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| | - Theano Papavassiliu
- First Department of Internal Medicine-Cardiology, University Medical Centre Mannheim, and DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, 68167 Mannheim, Germany
| | - Stefan O. Schoenberg
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| | - Matthias F. Froelich
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| | - Isabelle Ayx
- Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, 68167 Mannheim, Germany; (P.M.); (A.H.); (H.T.); (D.N.); (S.O.S.); (M.F.F.)
| |
Collapse
|