Towards a modular decision support system for radiomics: A case study on rectal cancer

Abstract

Following the personalized medicine paradigm, there is a growing interest in medical agents capable of predicting the effect of therapies on patients, by exploiting the amount of data that is now available for each patient. In disciplines like oncology, where images and scans are available, the exploitation of medical images can provide an additional source of potentially useful information. The study and analysis of features extracted by medical images, exploited for predictive purposes, is termed radiomics. A number of tools are available for supporting some of the steps of the radiomics process, but there is a lack of approaches which are able to deal with all the steps of the process. In this paper, we introduce a medical agent-based decision support system capable of handling the whole radiomics process. The proposed system is tested on two independent data sets of patients treated for rectal cancer. Experimental results indicate that the system is able to generate highly performant centre-specific predictive model, and show the issues related to differences in data sets collected by different centres, and how such issues can

A Multicentre Evaluation of Dosiomics Features Reproducibility, Stability and Sensitivity

“…The extraction of dosiomic features was centralised and carried out by a specific routine in the MODDICOM library, a free software package developed in R language optimised for automatic loading of DICOM images and radiomic analysis [28]. A specific routine for dose distribution texture analysis was realised for the purpose of this study, loading and processing the required DICOM dataset (planning CT, RT-Structure and RT-Dose).…”

A field strength independent MR radiomics model to predict pathological complete response in locally advanced rectal cancer

“…The DICOM files were imported in Moddicom, an R package (R Core Team, Vienna, Austria) designed for radiomics analyses of biomedical images [27,28]. All the images were resampled to a spatial planar resolution of 0.7 × 0.7 mm 2 prior to their quantitative analysis.…”

An Empirical Analysis of Predictors for Workload Estimation in Healthcare

“…Secondly, we plan to extend our analysis to different departments, in order to evaluate how general the presented results are. Thirdly, we are interested in evaluating whether sharing information between departments of different hospitals can help improving the performance of predictors, by leveraging on privacy-preserving approaches [6].Finally, we will focus on approaches aimed at integrating the strengths of machine learning with the capabilities of human experts, possibly using an overarching framework that encompasses all the relevant steps of the process [8].…”