Image Based Detection of Craniofacial Abnormalities using Feature Extraction by Classical Convolutional Neural Network

Saloni Agarwal, Rami R. Hallac, Rashika Mishra, Chao Li, Ovidiu Daescu, Alex A. Kane

2018 · 19 citations · 7 references

Concepts

Abstract

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.

References

7