Przejdź do głównej treści

Widok zawartości stron Widok zawartości stron

News

Nawigacja okruszkowa Nawigacja okruszkowa

Widok zawartości stron Widok zawartości stron

JU research will speed up aesophageal cancer diagostics

JU research will speed up aesophageal cancer diagostics

Scientists from the SOLARIS National Synchrotron Radiation Centre at the Jagiellonian University, University of Exeter (UK), Beckman Institute (University of Illinois at Urbana-Champaign - USA), and the Institute of Nuclear Physics of the Polish Academy of Sciences (Kraków, Poland) carried out a research project that will facilitate rapid and automated diagnosis of aesophageal cancer.

Dr. Tomasz Wróbel's group focuses on cancer detection through a combination of Infrared Imaging (IR) and the use of Machine Learning (ML) algorithms. Thanks to this approach, it is possible to develop an effective model which will allow histopathologists to confirm the diseased area automatically and in a much shorter time period.

Infrared Imaging (IR), which will soon also be available at the newly built beamline at SOLARIS, has found widespread use in biomedical research over the last couple of decades and is currently being introduced into clinical diagnostics.

'The wealth of biochemical information provided by this method is contained in spectra, describing unique characteristics of a sample to absorb infrared light of different wavelengths. Part of IR spectrum is often called a 'molecular fingerprint'. It also allows us to identify hundreds of chemical compounds. Combining multidimensional data from IR Imaging with Machine Learning (ML) algorithms led to the development of a completely new field focused on cancer detection', explains Dr. Tomasz Wróbel.

Using samples coming from both healthy and sick patients (originally diagnosed by a trained histopathologist), the ML algorithm searches through spectra to find and extract features characteristic of a given tissue type and creates a model. This model will be applicable later in the identification of future unknown samples.

Such full automation, which does not require staining of samples, is a great support for histopathologists and allows them to detect inflammation and pathology in the body faster and much more effectively.

'To be suitable for clinical application, a potential method needs to fit into a specific timescale. In the case of IR Imaging, this issue can be aided by the Quantum Cascade Laser-based (QCL) infrared spectroscopic imaging, which provides a more rapid method (minutes per patient) than the conventional Fourier transform infrared imaging (FT-IR). However, apart from speed, there are plenty of other aspects, for example sample preparation, that need examination and further optimisation', adds Dr. Wróbel

This work considers a few factors having crucial impact on the final work-flow of the proposed diagnostic approach. The most important question is: how effective will the model translation be to a faster modality of QCL microscopes? FT-IR measurements provide full spectral information, which is not always fully needed for model creation. On the other hand, the QCL-based imaging allows focusing only on selected spectral regions. Defining a small subset of spectral frequencies, which is most important for tissue types discrimination, provides the basis to create a reliable classification model, at the same time saving precious time. The results show that even after a major reduction of spectral information, models achieve sensitivity of around 95%. 

The image shows two esophageal biopsies. Top: biopsy taken from a patient suffering from esophageal cancer; bottom: biopsy taken from a healthy patient. Left: microscopic images of the mentioned biopsies are visible after the H&E staining (Hematoxylin and Eosin) - in this image of the stained biopsy, the histopathologist visually assigns tissue types; middle: biopsy images obtained using infrared imaging are visible; right: histological picture of a biopsy obtained after assigning tissues and structures to three classes (cancer, other, benign) by Machine Learning (ML). Red - cancer, blue - other, green – benign.

Apart from the mentioned project, Dr. Wróbel’s group is also working on a full pancreatic cancer classification model including cancer types and staging differentiation, inflammations and surgical margin detection with the FT-IR imaging. Such studies are one of the possible avenues of research that will soon be available on a newly constructed SOLAIR beamline at the National Synchrotron Radiation Center SOLARIS.

The research team included Danuta Liberda - Jagiellonian University, NSRC SOLARIS, Michael Hermes - University of Exeter, Paulina Kozioł - Institute of Nuclear Physics - Polish Academy of Sciences, Nick Stone - University of Exeter, Dr Tomasz Wróbel (corresponding author) - Jagiellonian University, NSRC SOLARIS and Beckman Institute, and the University of Illinois at Urbana-Champaign.

The complete publication 'Translation of FT-IR imaging esophagus histopathological model to a fast QCL modality' can be found in the Journal of Biophotonics.

Source: SOLARIS National Synchrotron Radiation Centre

Polecamy również
Signs of life in Venus' atmosphere?
JU scientists discover a living molecular fossil
The Jagiellonian University allows different modes of learning
A whole new level of X-ray imaging

Widok zawartości stron Widok zawartości stron

Find us at