Radiomika. (Slovenian)

Radiomics is a recent, rapidly evolving field that aims to extract new patterns and image biomarkers not visible by eye from standard medical images. The data are gathered by extracting and quantitative features from images obtained with x-ray, (positron-emission) computed tomography and magnetic resonance imaging. Radiomics exploits advanced tools for image analysis, thus creating large databases used by clinical decisionsupport systems with the aim to improve diagnostic and prognostic accuracy, and subsequently also treatment outcomes. Due to the lack of standardisation of radiomics methods and limitations of machine learning, clinical applicability is still limited and subject to current research. [ABSTRACT FROM AUTHOR]

Radiomika je novejše, hitro razvijajoče se področje, ki odkriva nove vzorce in slikovne biomarkerje, ki jih s prostim očesom ne moremo zaznati, iz standardnega medicinskega slikovnega materiala. Podatke zbira z ekstrakcijo in kvantifikacijo značilnosti radioloških slik, pridobljenih z rentgenskim slikanjem, (pozitronsko emisijsko) računalniško tomografijo ali magnetno resonančnim slikanjem. Radiomika izkorišča napredna orodja za analizo slik in njihove rezultati uporabi v sistemih za podporo kliničnem odločanju s ciljem izboljšati diagnostično in prognostično natančnost, s tem pa tudi izide zdravljenja. Zaradi pomanjkanja standardizacije metod v radiomiki in omejitev strojnega učenja, je klinična uporabnost teh metod še omejena oziroma predmet raziskav. [ABSTRACT FROM AUTHOR]

Copyright of Informatica Medica Slovenica is the property of Slovenian Medical Informatics Association and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)