TY - GEN
T1 - Improved mask R-CNN for lung nodule segmentation
AU - Yan, Huanlan
AU - Lu, Huijuan
AU - Ye, Minchao
AU - Yan, Ke
AU - Xu, Yige
AU - Jin, Qun
N1 - Funding Information:
This study is supported by National Natural Science Foundation of China (Nos. 61272315, 61602431, 61701468 and 61850410531) , International Cooperation Project of Zhejiang Provincial Science and Technology Department (Nos. 2017C34003), the Project of Zhejiang Provincial Natural Science Foundation (LY19F020016), and the Project of Zhejiang Provincial Science and Technology Innovation Activities for College Students University (Nos. 2019R409030).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/8
Y1 - 2019/8
N2 - With more and more people suffer from lung cancer, computer-aided diagnosis plays a more and more important role in lung cancer diagnosis. CNN has achieved state-of-the-art performance in image processing, and Mask R-CNN outperforms most other methods on instance segmentation. However, the target is extraordinarily small, and the background is very large in images, which results in a large number of negative examples and most of them are easy negatives. They will contribute a large part of the loss value in smooth loss function. The class imbalance problem leads to inefficient training, which makes model degenerated. In this paper, we propose a method based on Mask R-CNN to segment lung nodules. Due to the non-uniformity of CT values, we use the Laplacian operator to do feature dimensionality reduction for filtering out part of the noise. In our model, the novel function Focal Loss is used to suppress well-classified examples. The model is tested on LIDC-IDRI dataset and the results showed that the average precision of lung nodules reaches 78%. Compared with the smooth loss function in Mask R-CNN it improves by 7%.
AB - With more and more people suffer from lung cancer, computer-aided diagnosis plays a more and more important role in lung cancer diagnosis. CNN has achieved state-of-the-art performance in image processing, and Mask R-CNN outperforms most other methods on instance segmentation. However, the target is extraordinarily small, and the background is very large in images, which results in a large number of negative examples and most of them are easy negatives. They will contribute a large part of the loss value in smooth loss function. The class imbalance problem leads to inefficient training, which makes model degenerated. In this paper, we propose a method based on Mask R-CNN to segment lung nodules. Due to the non-uniformity of CT values, we use the Laplacian operator to do feature dimensionality reduction for filtering out part of the noise. In our model, the novel function Focal Loss is used to suppress well-classified examples. The model is tested on LIDC-IDRI dataset and the results showed that the average precision of lung nodules reaches 78%. Compared with the smooth loss function in Mask R-CNN it improves by 7%.
KW - Focal Loss
KW - Lung nodule segmentation
KW - Mask R-CNN
UR - http://www.scopus.com/inward/record.url?scp=85079328867&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079328867&partnerID=8YFLogxK
U2 - 10.1109/ITME.2019.00041
DO - 10.1109/ITME.2019.00041
M3 - Conference contribution
AN - SCOPUS:85079328867
T3 - Proceedings - 10th International Conference on Information Technology in Medicine and Education, ITME 2019
SP - 137
EP - 141
BT - Proceedings - 10th International Conference on Information Technology in Medicine and Education, ITME 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Information Technology in Medicine and Education, ITME 2019
Y2 - 23 August 2019 through 25 August 2019
ER -
