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

Roberto Gatta, Mauro Vallati, Nicola Dinapoli, Carlotta Masciocchi, Jacopo Lenkowicz, Davide Cusumano, Calogero Casà, Alessandra Farchione, Andrea Damiani, Johan van Soest, Andre Dekker, Vincenzo Valentini

Research output: Contribution to journalArticle

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 affect the performance of the generated predictive models.
LanguageEnglish
Pages145-153
Number of pages9
JournalArtificial Intelligence in Medicine
Volume96
Early online date4 Oct 2018
DOIs
Publication statusPublished - May 2019

Fingerprint

Rectal Neoplasms
Decision support systems
Oncology
Medicine
Precision Medicine
Datasets
Therapeutics

Cite this

Gatta, Roberto ; Vallati, Mauro ; Dinapoli, Nicola ; Masciocchi, Carlotta ; Lenkowicz, Jacopo ; Cusumano, Davide ; Casà, Calogero ; Farchione, Alessandra ; Damiani, Andrea ; van Soest, Johan ; Dekker, Andre ; Valentini, Vincenzo. / Towards a modular decision support system for radiomics : A case study on rectal cancer. In: Artificial Intelligence in Medicine. 2019 ; Vol. 96. pp. 145-153.
@article{1cb537c6fe4d49828272faea5b21132f,
title = "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 affect the performance of the generated predictive models.",
keywords = "Decision Support Systems, Radiomics, Predictive Models, Image Feature Analysis",
author = "Roberto Gatta and Mauro Vallati and Nicola Dinapoli and Carlotta Masciocchi and Jacopo Lenkowicz and Davide Cusumano and Calogero Cas{\`a} and Alessandra Farchione and Andrea Damiani and {van Soest}, Johan and Andre Dekker and Vincenzo Valentini",
year = "2019",
month = "5",
doi = "10.1016/j.artmed.2018.09.003",
language = "English",
volume = "96",
pages = "145--153",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

Gatta, R, Vallati, M, Dinapoli, N, Masciocchi, C, Lenkowicz, J, Cusumano, D, Casà, C, Farchione, A, Damiani, A, van Soest, J, Dekker, A & Valentini, V 2019, 'Towards a modular decision support system for radiomics: A case study on rectal cancer', Artificial Intelligence in Medicine, vol. 96, pp. 145-153. https://doi.org/10.1016/j.artmed.2018.09.003

Towards a modular decision support system for radiomics : A case study on rectal cancer. / Gatta, Roberto; Vallati, Mauro; Dinapoli, Nicola; Masciocchi, Carlotta; Lenkowicz, Jacopo; Cusumano, Davide; Casà, Calogero; Farchione, Alessandra; Damiani, Andrea; van Soest, Johan; Dekker, Andre; Valentini, Vincenzo.

In: Artificial Intelligence in Medicine, Vol. 96, 05.2019, p. 145-153.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Towards a modular decision support system for radiomics

T2 - Artificial Intelligence in Medicine

AU - Gatta, Roberto

AU - Vallati, Mauro

AU - Dinapoli, Nicola

AU - Masciocchi, Carlotta

AU - Lenkowicz, Jacopo

AU - Cusumano, Davide

AU - Casà, Calogero

AU - Farchione, Alessandra

AU - Damiani, Andrea

AU - van Soest, Johan

AU - Dekker, Andre

AU - Valentini, Vincenzo

PY - 2019/5

Y1 - 2019/5

N2 - 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 affect the performance of the generated predictive models.

AB - 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 affect the performance of the generated predictive models.

KW - Decision Support Systems

KW - Radiomics

KW - Predictive Models

KW - Image Feature Analysis

UR - http://www.scopus.com/inward/record.url?scp=85054192769&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2018.09.003

DO - 10.1016/j.artmed.2018.09.003

M3 - Article

VL - 96

SP - 145

EP - 153

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -