CVJan 11, 2019

Residual Pyramid FCN for Robust Follicle Segmentation

arXiv:1901.03760v16 citations
Originality Synthesis-oriented
AI Analysis

This work addresses a domain-specific problem in medical image analysis for thyroid follicle labeling, with incremental improvements to existing FCN-based methods.

The paper tackled the problem of segmenting thyroid follicles in histology images by proposing a pyramid network structure with residual modules, resulting in improved accuracy and robustness in segmentation.

In this paper, we propose a pyramid network structure to improve the FCN-based segmentation solutions and apply it to label thyroid follicles in histology images. Our design is based on the notion that a hierarchical updating scheme, if properly implemented, can help FCNs capture the major objects, as well as structure details in an image. To this end, we devise a residual module to be mounted on consecutive network layers, through which pixel labels would be propagated from the coarsest layer towards the finest layer in a bottom-up fashion. We add five residual units along the decoding path of a modified U-Net to make our segmentation network, Res-Seg-Net. Experiments demonstrate that the multi-resolution set-up in our model is effective in producing segmentations with improved accuracy and robustness.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes