Apply Machine Learning to the Interpretation of Urinary Crystal Morphology.

Yi-Shiou Tseng

Status: Not yet enrolling

Conditions: Kidney Calculi

Study type: Observational

Funder types: Other

Identifiers

NCT06178575

112183-E

Details and patient eligibility

About

The goal of this observational study is to developing an image-based artificial intelligence software that can automatically interpret the types and sizes of crystals in urine. The main question[s] it aims to answer are:

• Allowing healthcare professionals to input urine images and receive real-time reading results on crystal types and sizes.
• This aims to provide a faster, more objective, and accurate analysis of crystals.

We anticipate delivering an image AI software suitable for practical applications, promoting the automation and accuracy of urine crystal analysis.

Full description

Kidney stones are primarily formed due to the supersaturation of ions in urine, leading to the formation of crystals. An assessment of the risk of kidney stones is based on a patient's medical history, biochemical urine tests, and various laboratory examinations. Combining these with imaging studies such as CT scans, ultrasound, and X-rays helps in diagnosing the type of kidney stones, though imaging results for smaller stones may be less accurate. Stone formation is common with a high recurrence rate, and there is a strong correlation between urine crystals and stone composition. Therefore, the analysis of urine crystals is meaningful for the diagnosis, evaluation of treatment strategies, and prevention of stone recurrence in kidney stone disease.

Microscopic analysis of urine crystals allows the observation of smaller crystals. However, manual urine microscopy is slow and time-consuming. To address this, we aim to develop artificial intelligence software to assist in the interpretation of urine crystals, providing a faster analysis. We will retrospectively analyze urine crystal images stored from previous research (Chang Gung Memorial Hospital Internal Project Research No. 107123-E) to identify crystal types. Subsequent image preprocessing and category labeling will be done to train and infer machine software. The results will be compared with manual interpretation to establish the accuracy of the software.

Enrollment: 200 estimated patients

Sex: All

Ages: 20+ years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Retrospectively analyze the urine crystal images preserved from the previous study 107123-E for crystal type analysis. Subsequently, conduct image preprocessing and label categorization for machine software learning and inference. The interpreted results will then be assessed for accuracy using statistical analysis software.

Exclusion criteria

• Not applicable

Trial design

200 participants in 2 patient groups

Manual microscopic observation

Description:

Control Group: Manual analysis of urine crystal images, distinguishing crystal types, recording accuracy, and analyzing the time consumed.

Machine interpretation

Description:

The urine crystal images undergo analysis for crystal types, followed by image preprocessing and category labeling for machine software learning and inference. Subsequently, the interpreted results will be subjected to statistical analysis software to assess accuracy.