Name
Title | ||
|---|---|---|
A Coarse-to-fine Cascading Model for Cataract Nuclear Segmentation in Slit-lamp Photographs |
Abstract | ||
|---|---|---|
A nuclear cataract is an age-related chronic and priority ophthalmic disease in which a clouding of the lens in the human eye affects vision. Automatic segmentation of nuclear region based on slit-lamp photographs is a basic step for computer-aided diagnosis such as nuclear cataract grading. However, slit-lamp photographs collected from a clinic scenario often have complex background containing the eyelids, sclera and cornea with spectral highlights. The existing efforts using traditional image processing that have unsatisfactory results, and the deep learning method using standard Faster R-CNN tends to obtain a bigger nuclear contour. In this paper, we propose a coarse-to-fine deep learning solution to localize nuclear regions by cascading the Faster R-CNN in a two-stage framework. First, a nuclear ROI (region of interest) predictor is pre-trained to localize a rough position and remove complex backgrounds. Then, a fine nuclear locator is applied to predict a more compact nuclear bounding box. Finally, an ellipse-like nuclear contour is fitted based on its bounding box. Evaluated on a clinical dataset of 884 slit-lamp photographs, the proposed method outperforms the state-of-the-art, improving the overlapping rate (IoU) by 0.33% from 67.98% to 68.31%, and increasing the success rate by 2.55% from 85.71% to 88.26%. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/VCIP47243.2019.8965714 | 2019 IEEE Visual Communications and Image Processing (VCIP) |
Keywords | Field | DocType |
coarse-to-fine cascading model,cataract nuclear segmentation,age-related chronic,priority ophthalmic disease,nuclear region,nuclear cataract grading,complex background,bigger nuclear contour,coarse-to-fine deep learning solution,nuclear ROI,fine nuclear locator,compact nuclear bounding box,ellipse-like nuclear contour,slit-lamp photographs | Human eye,Computer vision,Computer science,Segmentation,Image processing,Nuclear cataract,Artificial intelligence,Deep learning,Region of interest,Slit lamp,Minimum bounding box | Conference |
ISSN | ISBN | Citations |
1018-8770 | 978-1-7281-3724-7 | 0 |
PageRank | References | Authors |
0.34 | 7 | 14 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun Wu | 1 | 0 | 0.34 |
| Xianfang Rong | 2 | 0 | 0.34 |
| Zhennan Zhao | 3 | 1 | 0.72 |
| Lei Cai | 4 | 53 | 19.97 |
| Dayong Ding | 5 | 0 | 0.34 |
| Xirong Li | 6 | 1191 | 68.62 |
| Zongjiang Shang | 7 | 1 | 1.39 |
| Kaiwei Wang | 8 | 0 | 0.34 |
| Xixi He | 9 | 2 | 1.09 |
| Xiangjia Zhu | 10 | 1 | 0.72 |
| Wenwen He | 11 | 1 | 0.72 |
| Yi Lu | 12 | 0 | 0.34 |
| Keke Zhang | 13 | 1 | 0.72 |
| Yinglei Zhang | 14 | 1 | 0.72 |