1
|
He S, Zou Y, Li B, Peng F, Lu X, Guo H, Tan X, Chen Y. An image inpainting-based data augmentation method for improved sclerosed glomerular identification performance with the segmentation model EfficientNetB3-Unet. Sci Rep 2024; 14:1033. [PMID: 38200109 PMCID: PMC10781987 DOI: 10.1038/s41598-024-51651-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Accepted: 01/08/2024] [Indexed: 01/12/2024] Open
Abstract
The percent global glomerulosclerosis is a key factor in determining the outcome of renal transfer surgery. At present, the rate is typically computed by pathologists, which is labour intensive and nonstandardized. With the development of Deep Learning (DL), DL-based segmentation models can be used to better identify and segment normal and sclerosed glomeruli. Based on this, we can better quantify percent global glomerulosclerosis to reduce the discard rate of donor kidneys. We used 51 whole slide images (WSIs) from different institutions that are publicly available on the internet. However, the number of sclerosed glomeruli is much smaller than that of normal glomeruli in different WSIs, which can reduce the effectiveness of Deep Learning. For better sclerosed glomerular identification and segmentation performance, we modified and trained a GAN (generative adversarial network)-based image inpainting model to obtain more synthetic sclerosed glomeruli. Our proposed inpainting method achieved an average SSIM (Structural Similarity) of 0.8086 and an average PSNR (Peak Signal-to-Noise Ratio) of 22.8943 dB in the area of generated sclerosed glomeruli. We obtained sclerosed glomerular segmentation performance improvement by adding synthetic sclerosed glomerular images and achieved the best Dice of glomerular segmentation in different test sets based on the modified Unet model.
Collapse
Affiliation(s)
- Songping He
- Digital Manufacturing Equipment National Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Yi Zou
- National NC System Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Bin Li
- Digital Manufacturing Equipment National Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Fangyu Peng
- National NC System Engineering Research Center, Huazhong University of Science and Technology, Wuhan, China
| | - Xia Lu
- Key Laboratory of Organ Transplantation of Ministry of Education, Institute of Organ Transplantation, Tongji Hospital, Tongji Medical College, National Health Commission and Chinese Academy of Medical Sciences, Huazhong University of Science and Technology, Wuhan, China
| | - Hui Guo
- Key Laboratory of Organ Transplantation of Ministry of Education, Institute of Organ Transplantation, Tongji Hospital, Tongji Medical College, National Health Commission and Chinese Academy of Medical Sciences, Huazhong University of Science and Technology, Wuhan, China
| | - Xin Tan
- Wuhan Intelligent Equipment Industrial Institute Co Ltd, Wuhan, China
| | - Yanyan Chen
- Department of Information Management, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
| |
Collapse
|