TY - GEN
T1 - 2ST-UNet
T2 - 2020 International Joint Conference on Neural Networks, IJCNN 2020
AU - Abedalla, Ayat
AU - Abdullah, Malak
AU - Al-Ayyoub, Mahmoud
AU - Benkhelifa, Elhadj
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - Pneumothorax, also called a collapsed lung, is the presence of the air outside of the lung in the space between the lung and chest wall. It is generally diagnosed using a chest X-ray. However, for some cases, the diagnosis can be difficult as other medical conditions appear similarly. Machine Learning algorithms have been providing great assistance in detecting and locating pneumothorax lately. In this paper, we propose a 2-Stage Training system to segment images with pneumothorax. This system has been built based on U-Net, the state-of-the-art Fully Convolutional Network (FCN) architecture, with a backbone Residual Networks (ResNet-34) that is pre-trained on the ImageNet dataset. In the beginning, we train the network at a lower resolution. Then, we load the trained model weights to retrain the network with a higher resolution. Moreover, we utilize different techniques including Stochastic Weight Averaging (SWA), data augmentation, and Test-Time Augmentation (TTA). We use the chest X-ray dataset that is provided by the 2019 SIIM-ACR Pneumothorax Segmentation Challenge, which contains 12047 training images and 3205 testing images. Our experiments show that 2-Stage Training leads to better and faster network convergence. Our method achieves 0.8356 mean Dice coefficient placing it among the top 9% of competitors with a rank of 124 out of 1475.
AB - Pneumothorax, also called a collapsed lung, is the presence of the air outside of the lung in the space between the lung and chest wall. It is generally diagnosed using a chest X-ray. However, for some cases, the diagnosis can be difficult as other medical conditions appear similarly. Machine Learning algorithms have been providing great assistance in detecting and locating pneumothorax lately. In this paper, we propose a 2-Stage Training system to segment images with pneumothorax. This system has been built based on U-Net, the state-of-the-art Fully Convolutional Network (FCN) architecture, with a backbone Residual Networks (ResNet-34) that is pre-trained on the ImageNet dataset. In the beginning, we train the network at a lower resolution. Then, we load the trained model weights to retrain the network with a higher resolution. Moreover, we utilize different techniques including Stochastic Weight Averaging (SWA), data augmentation, and Test-Time Augmentation (TTA). We use the chest X-ray dataset that is provided by the 2019 SIIM-ACR Pneumothorax Segmentation Challenge, which contains 12047 training images and 3205 testing images. Our experiments show that 2-Stage Training leads to better and faster network convergence. Our method achieves 0.8356 mean Dice coefficient placing it among the top 9% of competitors with a rank of 124 out of 1475.
KW - 2-Stage Training
KW - Chest X-ray
KW - Data Augmentation
KW - Pneumothorax Segmentation
KW - ResNet-34
KW - Test-Time Augmentation
KW - Transfer Learning
KW - U-Net
UR - https://www.scopus.com/pages/publications/85093852254
U2 - 10.1109/IJCNN48605.2020.9207268
DO - 10.1109/IJCNN48605.2020.9207268
M3 - Conference contribution
AN - SCOPUS:85093852254
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 July 2020 through 24 July 2020
ER -