Name
Abstract | ||
|---|---|---|
Urine casts is a particularly important examination item in clinical urinalysis, especially for the diagnosis of nephritis. Therefore, it is of great significance to identify the cast precisely in clinical urinalysis. However, due to subjectivity, time-consuming artificial microscopy, and the accuracy of various recognition algorithms, previous research is not considered to be sufficient. In this paper, an efficient approach to cast detection and recognition in urine sediment images is proposed. We used urine casts in urine microscopy as the detection target and then passed it to the ResNet50 network; in the last few layers of networks (FPN), we can obtain feature maps of different sizes. Finally, we input target area feature maps into the classification sub-network and the regression sub-network separately for classification and localization, and obtain detection results. The data shows that the mean average precision of the recognition result is 89.4%, while taking only 0.2s per image on the NVIDA Titan X GPU. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/IWSSIP.2019.8787296 | 2019 International Conference on Systems, Signals and Image Processing (IWSSIP) |
Keywords | Field | DocType |
deep learning,FPN,urine cast recognition | Computer vision,Urine,Pattern recognition,Urinalysis,Computer science,Feature extraction,Artificial intelligence,Deep learning,Recognition algorithm,Statistical classification,Urine sediment,Urine Casts | Conference |
ISSN | ISBN | Citations |
2157-8672 | 978-1-7281-3228-0 | 0 |
PageRank | References | Authors |
0.34 | 1 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qiaoliang Li | 1 | 0 | 0.68 |
| Zhigang Yu | 2 | 0 | 0.34 |
| Suwen Qi | 3 | 11 | 2.40 |
| Zhuoying He | 4 | 0 | 0.68 |
| Shiyu Li | 5 | 0 | 0.34 |
| Huimin Guan | 6 | 0 | 0.34 |