Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation

by   Hao Zheng, et al.

Automated airway segmentation is a prerequisite for pre-operative diagnosis and intra-operative navigation for pulmonary intervention. Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways. In this paper, we demonstrate that this problem is arisen by gradient erosion and dilation of the neighborhood voxels. During back-propagation, if the ratio of the foreground gradient to background gradient is small while the class imbalance is local, the foreground gradients can be eroded by their neighborhoods. This process cumulatively increases the noise information included in the gradient flow from top layers to the bottom ones, limiting the learning of small structures in CNNs. To alleviate this problem, we use group supervision and the corresponding WingsNet to provide complementary gradient flows to enhance the training of shallow layers. To further address the intra-class imbalance between large and small airways, we design a General Union loss function which obviates the impact of airway size by distance-based weights and adaptively tunes the gradient ratio based on the learning process. Extensive experiments on public datasets demonstrate that the proposed method can predict the airway structures with higher accuracy and better morphological completeness.


page 1

page 7

page 8

page 12


A systematic study of the foreground-background imbalance problem in deep learning for object detection

The class imbalance problem in deep learning has been explored in severa...

Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation

Class imbalance poses a challenge for developing unbiased, accurate pred...

Harmonizing Output Imbalance for semantic segmentation on extremely-imbalanced input data

Semantic segmentation is a high level computer vision task that assigns ...

Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery

Geospatial object segmentation, as a particular semantic segmentation ta...

Ensembled ResUnet for Anatomical Brain Barriers Segmentation

Accuracy segmentation of brain structures could be helpful for glioma an...

Characterizing the Effect of Class Imbalance on the Learning Dynamics

Data imbalance is a common problem in the machine learning literature th...

On Class Imbalance and Background Filtering in Visual Relationship Detection

In this paper we investigate the problems of class imbalance and irrelev...

Please sign up or login with your details

Forgot password? Click here to reset