Related Experiment Video
Updated: Aug 4, 2025
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
In situ Raman spectroscopy and machine learning unveil biomolecular alterations in invasive breast cancer
Sandryne David1,2, Trang Tran1,2, Frédérick Dallaire1,2
1Polytechnique Montréal, Department of Engineering Physics, Montreal, Quebec, Canada.
Significance:
As many as 60% of patients with early stage breast cancer undergo breast-conserving surgery. Of those, 20% to 35% need a second surgery because of incomplete resection of the lesions. A technology allowing in situ detection of cancer could reduce re-excision procedure rates and improve patient survival.
Aim:
Raman spectroscopy was used to measure the spectral fingerprint of normal breast and cancer tissue ex-vivo. The aim was to build a machine learning model and to identify the biomolecular bands that allow one to detect invasive breast cancer.
Approach:
The system was used to interrogate specimens from 20 patients undergoing lumpectomy, mastectomy, or breast reduction surgery. This resulted in 238 ex-vivo measurements spatially registered with standard histology classifying tissue as cancer, normal, or fat. A technique based on support vector machines led to the development of predictive models, and their performance was quantified using a receiver-operating-characteristic analysis.
Results:
Raman spectroscopy combined with machine learning detected normal breast from ductal or lobular invasive cancer with a sensitivity of 93% and a specificity of 95%. This was achieved using a model based on only two spectral bands, including the peaks associated with C-C stretching of proteins around and the symmetric ring breathing at associated with phenylalanine.
Conclusions:
Detection of cancer on the margins of surgically resected breast specimen is feasible with Raman spectroscopy.
Insights
Raman spectroscopy and machine learning can detect invasive breast cancer in surgical specimens with high accuracy. This technology shows promise for reducing repeat surgeries and improving outcomes for breast cancer patients.
Area of Science:
- Biomedical Optics
- Medical Spectroscopy
- Computational Biology
Background:
- Breast-conserving surgery is common for early-stage breast cancer, but incomplete resection necessitates re-excision in 20-35% of cases.
- Improving intraoperative cancer detection can reduce re-operation rates and enhance patient survival.
Purpose of the Study:
- To develop a machine learning model using Raman spectroscopy for ex-vivo detection of invasive breast cancer.
- To identify specific biomolecular spectral bands indicative of cancerous tissue.
Main Methods:
- Raman spectroscopy was employed to analyze 238 ex-vivo breast tissue specimens from 20 patients.
- Support vector machine models were developed and validated using receiver-operating-characteristic analysis.
- Spectra were spatially registered with histological classifications (cancer, normal, fat).
Main Results:
- The combined Raman spectroscopy and machine learning approach achieved 93% sensitivity and 95% specificity in distinguishing normal breast tissue from invasive ductal or lobular carcinoma.
- The model effectively utilized two key spectral bands related to protein C-C stretching and phenylalanine.
Conclusions:
- Raman spectroscopy is a feasible technology for detecting cancer margins in surgically resected breast specimens.
- This technique has the potential to significantly decrease the need for repeat surgeries in breast cancer treatment.
More Related Videos
13:48Non-contact, Label-free Monitoring of Cells and Extracellular Matrix using Raman Spectroscopy
Published on: May 29, 2012
07:54Surface-enhanced Resonance Raman Scattering Nanoprobe Ratiometry for Detecting Microscopic Ovarian Cancer via Folate Receptor Targeting
Published on: March 25, 2019