Related Experiment Video
Updated: Jul 14, 2025
08:08
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
69
Prostate cancer detection using e-nose and AI for high probability assessment.
J B Talens1,2, J Pelegri-Sebastia3, T Sogorb1
1Sensor and Magnetism Group, Institut de Recerca Per a La Gestió Integrada de Zones Costaneres (IGIC), Campus de Gandia, Universitat Politecnica de Valencia, Paranimf 1, Grao de Gandia, 46000, Valencia, Spain.
BMC Medical Informatics and Decision Making
|October 6, 2023
Summary
This study introduces an electronic nose and neural network tool for rapid prostate cancer detection using urine samples. The technology significantly reduces unnecessary biopsies, achieving a 91% cancer detection recall rate.
Area of Science:
- Biotechnology and Medical Diagnostics
- Artificial Intelligence in Healthcare
- Oncology and Urology
Background:
- Prostate cancer diagnosis often relies on invasive procedures like biopsies.
- Current diagnostic methods can lead to overdiagnosis and overtreatment.
- There is a need for rapid, non-invasive, and accurate diagnostic tools.
Purpose of the Study:
- To develop an electronic nose-based diagnostic tool for prostate cancer.
- To utilize artificial intelligence, specifically neural networks, for sample analysis.
- To improve diagnostic accuracy and reduce unnecessary invasive procedures.
Main Methods:
- Trained a neural network on urine sample data from prostate cancer and benign prostatic hyperplasia patients.
- Employed a unique data redundancy method for enhanced signal analysis.
- Utilized electronic nose technology to detect volatile organic compounds in urine.
Main Results:
- Achieved a 91% recall rate for prostate cancer detection.
- Demonstrated significant reduction in the number of unnecessary biopsies.
- Improved the overall classification accuracy of the diagnostic method.
Conclusions:
- The developed electronic nose and neural network tool offers a promising non-invasive method for prostate cancer detection.
- This technology has the potential to be implemented in primary care settings for early and rapid diagnosis.
- The approach effectively differentiates between prostate cancer and benign prostatic hyperplasia, aiding clinical decision-making.
