Automatic classification of kidney stone components based on smartphone microscopy and the GoogLeNet model
This study successfully developed a kidney stone composition classification system integrating a smartphone-based microscope with a deep learning model, achieving an overall classification accuracy of 85.7%. The system exhibited strong performance in classifying uric acid and magnesium ammonium phosphate hexahydrate stones. With its low cost, efficiency, and portability, this system offers an economical and practical diagnostic solution for resource-limited regions.
Authors
- Yuxuan Du (ORCID: https://orcid.org/0000-0002-0568-3838)
- Dehui Lai
- Jiaqi Chen (ORCID: https://orcid.org/0000-0003-3936-009X)
- Yaochuan Guo
- Yangang Xu
- Ping Li
- Yanbing Liang
- Jun Bian
- Yifei Zhan
- Xingshu Zhen
- Zichi Wu
- Chenyu Zhou
- Guanyang Li
- Chan Hiu Fung Anson
- Kaiyue Tang
- Zhiyuan Guo
- Mei Huang
- Ayizeba Aimaierjiang
- Liuqiang Li
Institutions
- Jiamusi University (CN)
- Sun Yat-sen University (CN)
- The Fourth People's Hospital (CN)
- Sixth Affiliated Hospital of Sun Yat-sen University (CN)
- Integrated Chinese Medicine (China) (HK)
- Foshan Second People's Hospital (CN)
- Ninth Hospital of Nanchang (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- BMC Urology
- Published
- 2026-02-12
- DOI
- https://doi.org/10.1186/s12894-026-02080-x
- Primary Topic
- Kidney Stones and Urolithiasis Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00