TY - GEN
T1 - Human Bone Localization in Ultrasound Image Using YOLOv3 CNN Architecture
AU - Arif Firdaus Lazuardi, R.
AU - Karlita, Tita
AU - Yuniarno, Eko Mulyanto
AU - Ketut Eddy Purnama, I.
AU - Purnomo, Mauridhi Hery
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Localization of human long bones in ultrasound images has quite complex challenges. This is due to a representation of the reflection of a sound wave emitted by a B-scan sensor. The ultrasound scan does not only display bone specimens, but also contains muscles, soft tissue, and other parts under the skin tissue Therefore we need a system that can automatically recognize bone specimens in ultrasound images. This study implements deep learning based learning systems using the convolutional neural network (CNN) method with YOLOv3. The training results from the network detector with IoU threshold 0.5 can recognize bone objects in mAP@50, mAP@75 and mAP@50:95 with values of 99.98, 97.68 and 85.67 respectively. And for the results of training the network detector with IoU threshold 0.75 can recognize bone objects in mAP@50, mAP@75 and mAP@50:95 with values of 99.96, 97.46 and 86.35 respectively.
AB - Localization of human long bones in ultrasound images has quite complex challenges. This is due to a representation of the reflection of a sound wave emitted by a B-scan sensor. The ultrasound scan does not only display bone specimens, but also contains muscles, soft tissue, and other parts under the skin tissue Therefore we need a system that can automatically recognize bone specimens in ultrasound images. This study implements deep learning based learning systems using the convolutional neural network (CNN) method with YOLOv3. The training results from the network detector with IoU threshold 0.5 can recognize bone objects in mAP@50, mAP@75 and mAP@50:95 with values of 99.98, 97.68 and 85.67 respectively. And for the results of training the network detector with IoU threshold 0.75 can recognize bone objects in mAP@50, mAP@75 and mAP@50:95 with values of 99.96, 97.46 and 86.35 respectively.
KW - CNN
KW - YOLOv3
KW - bone USG
UR - http://www.scopus.com/inward/record.url?scp=85084472630&partnerID=8YFLogxK
U2 - 10.1109/CENIM48368.2019.8973372
DO - 10.1109/CENIM48368.2019.8973372
M3 - Conference contribution
AN - SCOPUS:85084472630
T3 - 2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding
BT - 2019 International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019 - Proceeding
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Computer Engineering, Network, and Intelligent Multimedia, CENIM 2019
Y2 - 19 November 2019 through 20 November 2019
ER -