Radiomics and dosiomics, aims to investigate the correlation between the characteristics of radiological, diagnostic images and the 3D distribution of doses in the volume of the treated tumor and to determine the optimal markers. The integration of radiomics, dosiomics, and deep learning could facilitate diagnosis, selection of treatment tactics, and predict the outcome of the disease.
The project aims to identify and investigate new radiological and dosiomics markers that predict the course and outcome of the disease in patients with head and neck tumors, to create a multiparametric model for predicting the localization of locoregional recurrence of head and neck tumors using positron emission tomography/computed tomography (PET/CT) images and deep learning methodology.
Project funding:
KTU Research and Innovation Fund
Project results:
During the project, a prognostic model of local control was developed for head and neck cancer patients after induction chemotherapy and chemoradiation treatment, integrating radiomics, dosiomics and clinical parameters.
Unique data processing algorithms were developed for the collection and analysis of radiomics parameters.
The obtained data and the developed model allowed to identify a group of radiomics parameters allowing to differentiate patients according to the expected complexity of the treatment course.
Period of project implementation: 2022-04-01 - 2022-12-31
Project partners: Lithuanian University of Health Sciences
