Improved mask R-CNN for lung nodule segmentation

Huanlan Yan, Huijuan Lu, Minchao Ye, Ke Yan, Yige Xu, Qun Jin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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%.

Original languageEnglish
Title of host publicationProceedings - 10th International Conference on Information Technology in Medicine and Education, ITME 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages137-141
Number of pages5
ISBN (Electronic)9781728139173
DOIs
Publication statusPublished - 2019 Aug
Event10th International Conference on Information Technology in Medicine and Education, ITME 2019 - Qingdao, Shandong, China
Duration: 2019 Aug 232019 Aug 25

Publication series

NameProceedings - 10th International Conference on Information Technology in Medicine and Education, ITME 2019

Conference

Conference10th International Conference on Information Technology in Medicine and Education, ITME 2019
CountryChina
CityQingdao, Shandong
Period19/8/2319/8/25

Keywords

  • Focal Loss
  • Lung nodule segmentation
  • Mask R-CNN

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Health Informatics
  • Education

Fingerprint Dive into the research topics of 'Improved mask R-CNN for lung nodule segmentation'. Together they form a unique fingerprint.

  • Cite this

    Yan, H., Lu, H., Ye, M., Yan, K., Xu, Y., & Jin, Q. (2019). Improved mask R-CNN for lung nodule segmentation. In Proceedings - 10th International Conference on Information Technology in Medicine and Education, ITME 2019 (pp. 137-141). [8964832] (Proceedings - 10th International Conference on Information Technology in Medicine and Education, ITME 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITME.2019.00041