2022 Fiscal Year Final Research Report
Development of artificial intelligence assisted Raman microscopy for reliable and automated examination of urine sediment
| Project/Area Number |
21K18081
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 90130:Medical systems-related
|
|---|
| Research Institution | Shimane University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2021-04-01 – 2023-03-31
|
| Keywords | Raman Spectroscopy / Single cell analysis / Disease diagnostics / Molecular imaging / Artificial Intelligence / Machine learning / Explainable AI |
|---|
| Outline of Final Research Achievements |
Urine is a rich body fluid with over 3,000 metabolites. Determining exact composition of urine, its collection and storage are difficult and expensive. During the development of new modalities of urinalysis, therefore, artificial urine has many advantages as it is both practical and fast to obtain over human urine for research and educational purposes. In this work, we investigated several formulations and examined suitability of artificial urine for the development of AI assisted Raman spectroscopy based urinalysis. Raman spectra were measured using both portable Raman spectrometer and a Raman micro-spectrometer under liquid or air-dried conditions. By optimizing several experimental parameters, we realized artificial urine spectra that matched well with standard human urine. We believe this formulation of AU can be used to replace human urine during development of Raman spectroscopy based urinalysis successfully.
|
| Free Research Field |
Bioanalytical Chemistry
|
| Academic Significance and Societal Importance of the Research Achievements |
Human urine flows through kidneys, ureters, bladder, urethra etc. and it accurately reflects change in all the organs. Separate screening tests are done for each disease. Proposed urinalysis by Raman microscopy helps to screen multiple conditions in one step, reduce cost/time and contribute to SDG3
|
