Research Council of Norway - NFR FRINATEK 

Project partners: 
Wesleyan University, Middletown, US
Ruhr University, Bochum, Germany
Belarusian Academy of Science, Minsk, Belarus

The information content in infrared microspectroscopic image data is overwhelming. An infrared microspectroscopic image typically consists of several thousands to several hundred thousands of pixels, with a full infrared spectrum with several thousand frequency readings in every pixel. Today, only chemical information extracted from the spectral domain is used for classification of tissues into healthy tissue and different cancer types. While morphological information is utilized in medical image analysis of histological images without a spectral domain, the morphological information in the analysis of infrared microspectroscopic images is ignored.

DeepHyperSpec project will combine deep learning methods with multivariate modelling of scattering and absorption in biomedical vibrational spectroscopy in order to develop a new paradigm for the analysis of hyperspectral imaging data. The acquired knowledge and methodology will allow to fully exploit the spectral and the image domain in hyperspectral imaging data and thus substantially increase the precision, interpretability and stability of classification models. The results will have an impact on other fields employing hyperspectral imaging, such as geospatial hyperspectral imaging and monitoring by satellites and drones. The research will be conducted by the multidisciplinary Biospectroscopy and Data Modelling (BioSpec) Group at the Faculty of Science and Technology/Realtek, NMBU in close collaboration with four internationally renowned research teams: University of Milwaukee-Wisconsin (Milwaukee, USA), Wesleyan University (Middletown, USA), Ruhr University (Bochum, Germany) and Belarusian Academy of Science (Minsk, Belarus).

Literature:

Kong B., Brandsrud M.A., Heitmann Solheim J., Nedrebø I., Blümel R., Kohler A.
Effects of the coupling of dielectric spherical particles on signatures in infrared microspectroscopy
Scientific Reports 12 (2022) 13327

Solheim J.H., Zimmermann B., Tafintseva V., Dzurendová S., Shapaval V., Kohler A.
The Use of Constituent Spectra and Weighting in Extended Multiplicative Signal Correction in Infrared Spectroscopy.
Molecules 27 (2022) 1900

Heitmann Solheim J., Borondics F., Zimmermann B., Sandt C., Muthreich F., Kohler A.
An automated approach for fringe frequency estimation and removal in infrared spectroscopy and hyperspectral imaging of biological samples
Journal of Biophotonics 14 (2021) e202100148

Blazhko U., Shapaval V., Kovalev V., Kohlera A.
Comparison of augmentation and pre-processing for deep learning and chemometric classification of infrared spectra
Chemometrics and Intelligent Laboratory Systems 215 (2021) 104367

Brandsrud M.A., Blümel R., Heitmann Solheim J., Kohler A.
The effect of deformation of absorbing scatterers on Mie-type signatures in infrared microspectroscopy
Scientific Reports 11 (2021) 4675

Almklov Magnussen E., Heitmann Solheim J., Blazhko U., Tafintseva V., Tøndel K., Liland K.H., Dzurendova S., Shapaval V., Kohler A. 
Deep convolutional neural network recovers pure absorbance spectra from highly scatter‐distorted spectra of cells 
Journal of Biophotonics (2020) e202000204