Publications

BibTex format

@article{Nan:2022:10.1016/j.patcog.2022.108648,
author = {Nan, Y and Li, F and Tang, P and Zhang, G and Zeng, C and Xie, G and Liu, Z and Yang, G},
doi = {10.1016/j.patcog.2022.108648},
journal = {Pattern Recognition},
title = {Automatic fine-grained glomerular lesion recognition in kidney pathology},
url = {http://dx.doi.org/10.1016/j.patcog.2022.108648},
volume = {127},
year = {2022}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Recognition of glomeruli lesions is the key for diagnosis and treatment planning in kidney pathology; however, the coexisting glomerular structures such as mesangial regions exacerbate the difficulties of this task. In this paper, we introduce a scheme to recognize fine-grained glomeruli lesions from whole slide images. First, a focal instance structural similarity loss is proposed to drive the model to locate all types of glomeruli precisely. Then an Uncertainty Aided Apportionment Network is designed to carry out the fine-grained visual classification without bounding-box annotations. This double branch-shaped structure extracts common features of the child class from the parent class and produces the uncertainty factor for reconstituting the training dataset. Results of slide-wise evaluation illustrate the effectiveness of the entire scheme, with an 8–22% improvement of the mean Average Precision compared with remarkable detection methods. The comprehensive results clearly demonstrate the effectiveness of the proposed method.
AU  - Nan,Y
AU  - Li,F
AU  - Tang,P
AU  - Zhang,G
AU  - Zeng,C
AU  - Xie,G
AU  - Liu,Z
AU  - Yang,G
DO  - 10.1016/j.patcog.2022.108648
PY  - 2022///
SN  - 0031-3203
TI  - Automatic fine-grained glomerular lesion recognition in kidney pathology
T2  - Pattern Recognition
UR  - http://dx.doi.org/10.1016/j.patcog.2022.108648
UR  - http://hdl.handle.net/10044/1/96144
VL  - 127
ER  -

Download

DrGuangYang

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)