Related Experiment Video
Updated: Jun 3, 2025
07:54
Surface-enhanced Resonance Raman Scattering Nanoprobe Ratiometry for Detecting Microscopic Ovarian Cancer via Folate Receptor Targeting
Published on: March 25, 2019
8.1K
Differential Diagnosis of Urinary Cancers by Surface-Enhanced Raman Spectroscopy and Machine Learning.
Li Song1,2, Fei Xue3, Tingmiao Li3
1National Engineering Laboratory for AIDS Vaccine, School of Life Sciences, Jilin University, Changchun 130012, P. R. China.
Analytical Chemistry
|January 6, 2025
Summary
This study introduces a novel SERS-based method combined with deep learning for noninvasive early detection of bladder, kidney, and prostate cancers using serum samples. The approach offers high sensitivity and accuracy for diagnosing these prevalent urinary cancers.
Area of Science:
- Analytical Chemistry
- Biomedical Engineering
- Oncology
Background:
- Urinary cancers (bladder, kidney, prostate) are common, necessitating improved early diagnostic methods.
- Traditional detection techniques face challenges in noninvasive, sensitive cancer diagnosis.
- Early detection is crucial for effective treatment and improved patient outcomes.
Purpose of the Study:
- To develop a sensitive, noninvasive method for detecting multiple urinary cancers.
- To utilize Surface-Enhanced Raman Spectroscopy (SERS) and machine learning for serum sample analysis.
- To establish a SERS-machine learning strategy for discriminating bladder, kidney, and prostate cancers.
Main Methods:
- Developed a SERS-based assay using cleaned and aggregated silver nanoparticles for serum analysis.
- Employed a long short-term memory (LSTM) deep learning algorithm to analyze serum spectral data.
- Evaluated model performance using accuracy, sensitivity, specificity, and ROC curves.
Main Results:
- Achieved rapid, label-free, and highly sensitive detection of human sera.
- Successfully classified three types of urinary cancers (bladder, kidney, prostate) with high discrimination.
- Demonstrated the effectiveness of combining SERS sensitivity with machine learning data processing.
Conclusions:
- The SERS-machine learning strategy shows significant potential for the early diagnosis and screening of urinary cancers.
- This study represents the first application of SERS-machine learning for discriminating multiple urinary cancers from clinical serum samples.
- The developed method offers a promising noninvasive approach for cancer detection.
