An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy
Abstract Mandibular retrognathia (C2Rm) is one of the most common oral pathologies. Acquiring a better understanding of the points of impact of C2Rm on the entire skull is of major interest in the diagnosis, treatment, and management of this dysmorphism, but also permits us to contribute to the deba...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-45314-w |
| _version_ | 1827710952041086976 |
|---|---|
| author | Masrour Makaremi Alireza Vafaei Sadr Benoit Marcy Ikram Chraibi Kaadoud Ali Mohammad-Djafari Salomé Sadoun François De Brondeau Bernard N’kaoua |
| author_facet | Masrour Makaremi Alireza Vafaei Sadr Benoit Marcy Ikram Chraibi Kaadoud Ali Mohammad-Djafari Salomé Sadoun François De Brondeau Bernard N’kaoua |
| author_sort | Masrour Makaremi |
| collection | DOAJ |
| description | Abstract Mandibular retrognathia (C2Rm) is one of the most common oral pathologies. Acquiring a better understanding of the points of impact of C2Rm on the entire skull is of major interest in the diagnosis, treatment, and management of this dysmorphism, but also permits us to contribute to the debate on the changes undergone by the shape of the skull during human evolution. However, conventional methods have some limits in meeting these challenges, insofar as they require defining in advance the structures to be studied, and identifying them using landmarks. In this context, our work aims to answer these questions using AI tools and, in particular, machine learning, with the objective of relaying these treatments automatically. We propose an innovative methodology coupling convolutional neural networks (CNNs) and interpretability algorithms. Applied to a set of radiographs classified into physiological versus pathological categories, our methodology made it possible to: discuss the structures impacted by retrognathia and already identified in literature; identify new structures of potential interest in medical terms; highlight the dynamic evolution of impacted structures according to the level of gravity of C2Rm; provide for insights into the evolution of human anatomy. Results were discussed in terms of the major interest of this approach in the field of orthodontics and, more generally, in the field of automated processing of medical images. |
| first_indexed | 2024-03-10T17:47:02Z |
| format | Article |
| id | doaj.art-8f2262b094c24acabf59a2f65b548ec9 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-10T17:47:02Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-8f2262b094c24acabf59a2f65b548ec92023-11-20T09:29:54ZengNature PortfolioScientific Reports2045-23222023-10-0113111410.1038/s41598-023-45314-wAn interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomyMasrour Makaremi0Alireza Vafaei Sadr1Benoit Marcy2Ikram Chraibi Kaadoud3Ali Mohammad-Djafari4Salomé Sadoun5François De Brondeau6Bernard N’kaoua7Dentofacial Orthopedics Department (UFR de Sciences Odontologiques), University of BordeauxDepartment of Public Health Sciences, College of Medicine, The Pennsylvania State UniversityUniversity of ToulouseLUSSI Department, IMT AtlantiqueLSS, Centrale SupelecDentofacial Orthopedics Department (UFR de Sciences Odontologiques), University of BordeauxDentofacial Orthopedics Department (UFR de Sciences Odontologiques), University of BordeauxBordeaux Population Health (Team ACTIVE), INSERM U1219, University of BordeauxAbstract Mandibular retrognathia (C2Rm) is one of the most common oral pathologies. Acquiring a better understanding of the points of impact of C2Rm on the entire skull is of major interest in the diagnosis, treatment, and management of this dysmorphism, but also permits us to contribute to the debate on the changes undergone by the shape of the skull during human evolution. However, conventional methods have some limits in meeting these challenges, insofar as they require defining in advance the structures to be studied, and identifying them using landmarks. In this context, our work aims to answer these questions using AI tools and, in particular, machine learning, with the objective of relaying these treatments automatically. We propose an innovative methodology coupling convolutional neural networks (CNNs) and interpretability algorithms. Applied to a set of radiographs classified into physiological versus pathological categories, our methodology made it possible to: discuss the structures impacted by retrognathia and already identified in literature; identify new structures of potential interest in medical terms; highlight the dynamic evolution of impacted structures according to the level of gravity of C2Rm; provide for insights into the evolution of human anatomy. Results were discussed in terms of the major interest of this approach in the field of orthodontics and, more generally, in the field of automated processing of medical images.https://doi.org/10.1038/s41598-023-45314-w |
| spellingShingle | Masrour Makaremi Alireza Vafaei Sadr Benoit Marcy Ikram Chraibi Kaadoud Ali Mohammad-Djafari Salomé Sadoun François De Brondeau Bernard N’kaoua An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy Scientific Reports |
| title | An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy |
| title_full | An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy |
| title_fullStr | An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy |
| title_full_unstemmed | An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy |
| title_short | An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy |
| title_sort | interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy |
| url | https://doi.org/10.1038/s41598-023-45314-w |
| work_keys_str_mv | AT masrourmakaremi aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT alirezavafaeisadr aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT benoitmarcy aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT ikramchraibikaadoud aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT alimohammaddjafari aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT salomesadoun aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT francoisdebrondeau aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT bernardnkaoua aninterpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT masrourmakaremi interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT alirezavafaeisadr interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT benoitmarcy interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT ikramchraibikaadoud interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT alimohammaddjafari interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT salomesadoun interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT francoisdebrondeau interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy AT bernardnkaoua interpretablemachinelearningapproachtostudytherelationshipbeetwenretrognathiaandskullanatomy |