Image Based Detection of Craniofacial Abnormalities using Feature Extraction by Classical Convolutional Neural Network
- Resource Type
- Conference
- Authors
- Agarwal, Saloni; Hallac, Rami R; Mishra, Rashika; Li, Chao; Daescu, Ovidiu; Kane, Alex
- Source
- 2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS) Computational Advances in Bio and Medical Sciences (ICCABS), 2018 IEEE 8th International Conference on. :1-6 Oct, 2018
- Subject
- Bioengineering
Computing and Processing
Signal Processing and Analysis
Lips
Feature extraction
Training
Pediatrics
Mouth
Medical diagnostic imaging
Craniosynostosis
Pediatric Cleft
Craniofacial
Transfer Learning
AlexNet
multiclass SVM
- Language
- ISSN
- 2473-4659
The ubiquitous approach of transfer learning for feature extraction is harnessed for image based detection of two types of craniofacial abnormalities: pediatric cleft and craniosynostosis. In the current study, using features extracted from pre-trained AlexNet activations, we train a multi class support vector machine (SVM) for cleft lip abnormality and developed a multi-view classifier using max voting for craniosynostosis anomaly detection. We achieved Area under the ROC curve (AUC) value of 0.95 for cleft abnormality and 0.84 for craniosynostosis.