TY - GEN
T1 - Increasing accuracy of medical CNN applying optimization algorithms
T2 - 8th Brazilian Conference on Intelligent Systems, BRACIS 2019
AU - Marconi Ramos, Rafael
AU - Ghedini Ralha, Celia
AU - Kurc, Tahsin M.
AU - Saltz, Joel H.
AU - Teodoro, George
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Convolutional Neural Networks (CNN) for medical image classification involves particular features: big images, expensive training, complex architecture with several layers and hyperparameters, etc. Thus, increasing the accuracy or adjusting medical CNN is a challenging task that requires many resources, much time, and specialized knowledge. In this work, we proposed and tested an efficient approach to increase accuracy of a biomedical CNN using optimization algorithms. Our approach starts with a known deep network architecture and tunes it, together with its hyperparameters, to generate a final adjusted one. We have reached improvements in the quality of the results of about 40% when starting from a simple architecture and 12% from a manually adjusted architecture, with only 40 tries in a biomedical image classification case.
AB - Convolutional Neural Networks (CNN) for medical image classification involves particular features: big images, expensive training, complex architecture with several layers and hyperparameters, etc. Thus, increasing the accuracy or adjusting medical CNN is a challenging task that requires many resources, much time, and specialized knowledge. In this work, we proposed and tested an efficient approach to increase accuracy of a biomedical CNN using optimization algorithms. Our approach starts with a known deep network architecture and tunes it, together with its hyperparameters, to generate a final adjusted one. We have reached improvements in the quality of the results of about 40% when starting from a simple architecture and 12% from a manually adjusted architecture, with only 40 tries in a biomedical image classification case.
KW - CNN
KW - Deep architecture
KW - Hyperparameters
KW - Medical CNN
KW - Optimization algorithms
KW - Tuning
UR - https://www.scopus.com/pages/publications/85077027388
U2 - 10.1109/BRACIS.2019.00049
DO - 10.1109/BRACIS.2019.00049
M3 - Conference contribution
AN - SCOPUS:85077027388
T3 - Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019
SP - 233
EP - 238
BT - Proceedings - 2019 Brazilian Conference on Intelligent Systems, BRACIS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 15 October 2019 through 18 October 2019
ER -