The use of artificial intelligence for the classification of craniofacial deformities
Positional cranial deformities are a common finding in toddlers, yet differentiation from craniosynostosis can be challenging. The aim of this study was to train convolutional neural networks (CNNs) to classify craniofacial deformities based on 2D images generated using photogrammetry as a radiation...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
14 November 2023
|
| In: |
Journal of Clinical Medicine
Year: 2023, Volume: 12, Issue: 22, Pages: 1-12 |
| ISSN: | 2077-0383 |
| DOI: | 10.3390/jcm12227082 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.3390/jcm12227082 Verlag, kostenfrei, Volltext: https://www.mdpi.com/2077-0383/12/22/7082 
|
| Author Notes: | Reinald Kuehle, Friedemann Ringwald, Frederic Bouffleur, Niclas Hagen, Matthias Schaufelberger, Werner Nahm, Jürgen Hoffmann, Christian Freudlsperger, Michael Engel and Urs Eisenmann |
| Summary: | Positional cranial deformities are a common finding in toddlers, yet differentiation from craniosynostosis can be challenging. The aim of this study was to train convolutional neural networks (CNNs) to classify craniofacial deformities based on 2D images generated using photogrammetry as a radiation-free imaging technique. A total of 487 patients with photogrammetry scans were included in this retrospective cohort study: children with craniosynostosis (n = 227), positional deformities (n = 206), and healthy children (n = 54). Three two-dimensional images were extracted from each photogrammetry scan. The datasets were divided into training, validation, and test sets. During the training, fine-tuned ResNet-152s were utilized. The performance was quantified using tenfold cross-validation. For the detection of craniosynostosis, sensitivity was at 0.94 with a specificity of 0.85. Regarding the differentiation of the five existing classes (trigonocephaly, scaphocephaly, positional plagiocephaly left, positional plagiocephaly right, and healthy), sensitivity ranged from 0.45 (positional plagiocephaly left) to 0.95 (scaphocephaly) and specificity ranged from 0.87 (positional plagiocephaly right) to 0.97 (scaphocephaly). We present a CNN-based approach to classify craniofacial deformities on two-dimensional images with promising results. A larger dataset would be required to identify rarer forms of craniosynostosis as well. The chosen 2D approach enables future applications for digital cameras or smartphones. |
|---|---|
| Item Description: | Gesehen am 23.01.2024 |
| Physical Description: | Online Resource |
| ISSN: | 2077-0383 |
| DOI: | 10.3390/jcm12227082 |