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.
| Original language | English (US) |
|---|---|
| Title of host publication | 2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2018 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Volume | 2018-October |
| ISBN (Electronic) | 9781538685204 |
| DOIs | |
| State | Published - Nov 20 2018 |
| Event | 8th IEEE International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2018 - Las Vegas, United States Duration: Oct 18 2018 → Oct 20 2018 |
Other
| Other | 8th IEEE International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2018 |
|---|---|
| Country | United States |
| City | Las Vegas |
| Period | 10/18/18 → 10/20/18 |
Fingerprint
Keywords
- AlexNet
- Craniofacial
- Craniosynostosis
- multiclass SVM
- Pediatric Cleft
- Transfer Learning
ASJC Scopus subject areas
- Biomedical Engineering
- Computational Theory and Mathematics
Cite this
Image Based Detection of Craniofacial Abnormalities using Feature Extraction by Classical Convolutional Neural Network. / Agarwal, Saloni; Hallac, Rami Robert; Mishra, Rashika; Li, Chao; Daescu, Ovidiu; Kane, Alex A.
2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2018. Vol. 2018-October Institute of Electrical and Electronics Engineers Inc., 2018. 8541948.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Image Based Detection of Craniofacial Abnormalities using Feature Extraction by Classical Convolutional Neural Network
AU - Agarwal, Saloni
AU - Hallac, Rami Robert
AU - Mishra, Rashika
AU - Li, Chao
AU - Daescu, Ovidiu
AU - Kane, Alex A
PY - 2018/11/20
Y1 - 2018/11/20
N2 - 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.
AB - 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.
KW - AlexNet
KW - Craniofacial
KW - Craniosynostosis
KW - multiclass SVM
KW - Pediatric Cleft
KW - Transfer Learning
UR - http://www.scopus.com/inward/record.url?scp=85059766175&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059766175&partnerID=8YFLogxK
U2 - 10.1109/ICCABS.2018.8541948
DO - 10.1109/ICCABS.2018.8541948
M3 - Conference contribution
AN - SCOPUS:85059766175
VL - 2018-October
BT - 2018 IEEE 8th International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
ER -