Rudjer Boskovic Institute

Ruder Boscovic Institute

Ruder Boskovic Institute

Ivica Kopriva

Mirko Hadzija

Ivanka Jeric

Gorana Aralica

Jeric Ivanka

Marijana Popovic-Hadzija

Proposed invention is related to the field of photodynamic therapy and photodiagnosis. Specifically, a new algorithm is presented for visualization and spatial demarcation of various types of tumors and unhealthy tissue through unsupervised segmentation of the fluorescent multispectral image. Image is acquired through recording of the emission of the tissue illuminated by the light that induces fluorescence in the tumor. For this purpose tissue is treated by photo sensitizer. Algorithm for real time visualization and spatial demarcation of the tumor by means of the analysis of fluorescent image consists of the recording of the fluorescent image () that represents linear combination of the unknown classes S by multispectral camera, transformation of the fluorescent multispectral image into new multispectral image () applying nonlinear dimensionality expansion, linear transformation of the multispectral image () with extended dimensionality, independent component analysis of the innovation representations of the multispectral image () that is result of the transformation of the fluorescent image () and multispectral image (), extraction o the tumor map or class of interest in accordance with the chosen criterion and visualization of tumor on monitor.

Method for real time tumour visualisation and demarcation by means of photodynamic diagnosis

A computer-implemented data processing system for blind extraction of more pure components than mixtures recorded in 1D or 2D NMR spectroscopy and mass spectrometry. Sparse component analysis is combined with single component points (SCPs) to blind decomposition of mixtures data X into pure components S and concentration matrix A, whereas the number of pure components S is greater than number of mixtures X. NMR mixtures are transformed into wavelet domain, where pure components are sparser than in time domain and where SCPs are detected. Mass spectrometry (MS) mixtures are extended to analytical continuation in order to detect SCPs. SCPs are used to estimate number of pure components and concentration matrix. Pure components are estimated in frequency domain (NMR data) or m/z domain (MS data) by means of constrained convex programming methods. Estimated pure components are ranked using negentropy-based criterion.

Method of and system for blind extraction of more pure components than mixtures in 1D and 2D NMR spectroscopy and mass spectrometry combining sparse component analysis and single component points

Growing community of inventors

Zagreb, Croatia

Ivica Kopriva