Algorithms for lung segmentation
Real-time and code-free evaluation of different convolutional neural network architectures trained for lung segmentation
Evaluation of the GSC convolutional neural network, specifically trained for lung segmentation and formulated in:
Promising crack segmentation method based on gated skip connection. M. Jabreel and M. Abdel-Nasser, in Electronic Letters, Volume 56, Pages 493-495, 2020.
Evaluation of the UNet convolutional neural network, specifically trained for lung segmentation and formulated in:
U-Net: Convolutional Networks for Biomedical Image Segmentation. O. Ronneberger, P. Fisher and T. Brox, in Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015.
Evaluation of the ESNet convolutional neural network, specifically trained for lung segmentation and formulated in:
ESNet: An Efficient Symmetric Network for Real-Time Semantic Segmentation. Y. Wang, Q. Zhou, X. Wu, X. Jin, in Pattern Recognition and Computer Vision (PRCV 2019), Volume 11858, Springer, 2019.
Evaluation of the UnetPre convolutional neural network, specifically trained for lung segmentation and formulated in:
Automatic lung segmentation in chest X-ray images using improved UNet. W. Liu, J. Luo, Y. Yang, W.Wang, J. Deng and L. Yu, in Scientific Reports, Volume 12, Page 8649, 2022.
Evaluation of the ERFNet convolutional neural network, specifically trained for lung segmentation and formulated in:
ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation. E. Romera, J.M. Álvarez, L.M. Bergasa, and R. Arroyo, in IEEE Transactions on Intelligent Transportation Systems, Volume 19, Pages 263-272, 2018.
Evaluation of the CGNet convolutional neural network, specifically trained for lung segmentation and formulated in:
CGNet: A Light-Weight Context Guided Network for Semantic Segmentation. T. Wu, S. Tang, R. Zhang, J. Cao and Y. Zhang in IEEE Transactions on Image Processing, Volume 30, Pages 1169-1179, 2021.
Evaluation of the LinkNet convolutional neural network, specifically trained for lung segmentation and formulated in:
LinkNet: Exploiting encoder representations for efficient semantic segmentation. A. Chaurasia and E. Culurciello, in IEEE Visual Communications and Image Processing (VCIP 2017), Pages 1-4, 2017.
Evaluation of the MIA4Lung-Aggregation method, implemented by the MIA4Lung team and based on the aggregation of the partial segmentations of several CNNs, using a Weighted Ordered Weighted Averaging (WOWA) as aggregation function. The aggregation is performed on the following architectures: UNet, GSC, ESNet, UNetPre, ERFNet, CGNet and LinkNet. For more information on WOWA and related operators, see:
Aggregation Functions: A Guide for Practitioners. G. Beliakov, A. Pradera and T. Calvo. Springer, 2007.