Identifying Tumor Tissue in Thin Pathological Samples using Femtosecond Laser-Induced Breakdown Spectroscopy and Machine Learning

Researchers have developed a new technique that can help identify cancerous tissue in thin pathological samples. The technique involves the use of ultrashort laser pulses and machine learning algorithms. The aim is to differentiate cancerous tissue from healthy surrounding tissue, which can be critical in ensuring the complete removal of the tumor without affecting much of the neighboring healthy tissue. The researchers tested femtosecond Laser-Induced Breakdown Spectroscopy (LIBS) on fixed liver and breast postoperative samples. The team recorded the emission spectra following the ablation on the thin samples and compared them to adjacent stained sections to identify the tissue type based on classical pathological analysis. The technique achieved a high level of discrimination and a very high Classification Accuracy of around 0.95, according to the researchers. The technique has the potential to be used in clinical applications for rapid identification of tissue type during surgery. By using ultrashort laser pulses and a high-purity quartz substrate, researchers performed ablation with a high spatial resolution and low collateral damage.