Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest

Agata Małgorzata Wilk; Emilia Kozłowska; Damian Borys; Andrea D’Amico; Izabela Gorczewska; Iwona Debosz-Suwińska; Seweryn Gałecki; Krzysztof Fujarewicz; Rafał Suwiński; Andrzej Świerniak

doi:10.1007/978-3-031-38430-1_13

Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest

Agata Małgorzata Wilk
, Emilia Kozłowska
, Damian Borys
, Andrea D’Amico
, Izabela Gorczewska
, Iwona Debosz-Suwińska
, Seweryn Gałecki
, Krzysztof Fujarewicz
, Rafał Suwiński
, Andrzej Świerniak

Maria Sklodowska-Curie Institute of Oncology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Radiomic features, numeric values extracted from a region of interest (ROI) in medical images, can be used to train prognostic models for various types of cancer. However, in locally advanced diseases, more than one lesion may be present. Using the information contained in multiple regions increases the complexity and necessitates additional processing. Here, we tested seven strategies of handling multiple regions in radiomic-based regularized Cox regression for predicting metastasis-free survival using a cohort of 115 non-small cell lung cancer patients. We have found that using all ROIs to fit the model allowed for better results than using only the largest ROI, achieving c-indexes of 0.617 and 0.581, respectively.

Original language	English
Title of host publication	The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering
Editors	Paweł Strumiłło, Artur Klepaczko, Michał Strzelecki, Dorota Bociąga
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	163-173
Number of pages	11
ISBN (Print)	9783031384295
DOIs	https://doi.org/10.1007/978-3-031-38430-1_13
Publication status	Published - 2024
Event	Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023 - Lodz, Poland Duration: 27 Sept 2023 → 29 Sept 2023

Publication series

Name	Lecture Notes in Networks and Systems
Volume	746 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023
Country/Territory	Poland
City	Lodz
Period	27/09/23 → 29/09/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Lung cancer
Metastasis free survival
ROI
Radiomics
Regularized Cox regression

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-3-031-38430-1_13

Cite this

Wilk, A. M., Kozłowska, E., Borys, D., D’Amico, A., Gorczewska, I., Debosz-Suwińska, I., Gałecki, S., Fujarewicz, K., Suwiński, R., & Świerniak, A. (2024). Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest. In P. Strumiłło, A. Klepaczko, M. Strzelecki, & D. Bociąga (Eds.), The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering (pp. 163-173). (Lecture Notes in Networks and Systems; Vol. 746 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-38430-1_13

Wilk, Agata Małgorzata ; Kozłowska, Emilia ; Borys, Damian et al. / Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest. The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering. editor / Paweł Strumiłło ; Artur Klepaczko ; Michał Strzelecki ; Dorota Bociąga. Springer Science and Business Media Deutschland GmbH, 2024. pp. 163-173 (Lecture Notes in Networks and Systems).

@inproceedings{0d7d63d3fa514cd8bb187125710a73f1,

title = "Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest",

abstract = "Radiomic features, numeric values extracted from a region of interest (ROI) in medical images, can be used to train prognostic models for various types of cancer. However, in locally advanced diseases, more than one lesion may be present. Using the information contained in multiple regions increases the complexity and necessitates additional processing. Here, we tested seven strategies of handling multiple regions in radiomic-based regularized Cox regression for predicting metastasis-free survival using a cohort of 115 non-small cell lung cancer patients. We have found that using all ROIs to fit the model allowed for better results than using only the largest ROI, achieving c-indexes of 0.617 and 0.581, respectively.",

keywords = "Lung cancer, Metastasis free survival, ROI, Radiomics, Regularized Cox regression",

author = "Wilk, \{Agata Ma{\l}gorzata\} and Emilia Koz{\l}owska and Damian Borys and Andrea D{\textquoteright}Amico and Izabela Gorczewska and Iwona Debosz-Suwi{\'n}ska and Seweryn Ga{\l}ecki and Krzysztof Fujarewicz and Rafa{\l} Suwi{\'n}ski and Andrzej {\'S}wierniak",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023 ; Conference date: 27-09-2023 Through 29-09-2023",

year = "2024",

doi = "10.1007/978-3-031-38430-1\_13",

language = "English",

isbn = "9783031384295",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "163--173",

editor = "Pawe{\l} Strumi{\l}{\l}o and Artur Klepaczko and Micha{\l} Strzelecki and Dorota Boci{\c a}ga",

booktitle = "The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering",

address = "Germany",

}

Wilk, AM, Kozłowska, E, Borys, D, D’Amico, A, Gorczewska, I, Debosz-Suwińska, I, Gałecki, S , Fujarewicz, K, Suwiński, R & Świerniak, A 2024, Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest. in P Strumiłło, A Klepaczko, M Strzelecki & D Bociąga (eds), The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering. Lecture Notes in Networks and Systems, vol. 746 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 163-173, Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023, Lodz, Poland, 27/09/23. https://doi.org/10.1007/978-3-031-38430-1_13

Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest. / Wilk, Agata Małgorzata; Kozłowska, Emilia; Borys, Damian et al.
The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering. ed. / Paweł Strumiłło; Artur Klepaczko; Michał Strzelecki; Dorota Bociąga. Springer Science and Business Media Deutschland GmbH, 2024. p. 163-173 (Lecture Notes in Networks and Systems; Vol. 746 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest

AU - Wilk, Agata Małgorzata

AU - Kozłowska, Emilia

AU - Borys, Damian

AU - D’Amico, Andrea

AU - Gorczewska, Izabela

AU - Debosz-Suwińska, Iwona

AU - Gałecki, Seweryn

AU - Fujarewicz, Krzysztof

AU - Suwiński, Rafał

AU - Świerniak, Andrzej

PY - 2024

Y1 - 2024

N2 - Radiomic features, numeric values extracted from a region of interest (ROI) in medical images, can be used to train prognostic models for various types of cancer. However, in locally advanced diseases, more than one lesion may be present. Using the information contained in multiple regions increases the complexity and necessitates additional processing. Here, we tested seven strategies of handling multiple regions in radiomic-based regularized Cox regression for predicting metastasis-free survival using a cohort of 115 non-small cell lung cancer patients. We have found that using all ROIs to fit the model allowed for better results than using only the largest ROI, achieving c-indexes of 0.617 and 0.581, respectively.

AB - Radiomic features, numeric values extracted from a region of interest (ROI) in medical images, can be used to train prognostic models for various types of cancer. However, in locally advanced diseases, more than one lesion may be present. Using the information contained in multiple regions increases the complexity and necessitates additional processing. Here, we tested seven strategies of handling multiple regions in radiomic-based regularized Cox regression for predicting metastasis-free survival using a cohort of 115 non-small cell lung cancer patients. We have found that using all ROIs to fit the model allowed for better results than using only the largest ROI, achieving c-indexes of 0.617 and 0.581, respectively.

KW - Lung cancer

KW - Metastasis free survival

KW - ROI

KW - Radiomics

KW - Regularized Cox regression

UR - https://www.scopus.com/pages/publications/85172305885

U2 - 10.1007/978-3-031-38430-1_13

DO - 10.1007/978-3-031-38430-1_13

M3 - Conference contribution

AN - SCOPUS:85172305885

SN - 9783031384295

T3 - Lecture Notes in Networks and Systems

SP - 163

EP - 173

BT - The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering

A2 - Strumiłło, Paweł

A2 - Klepaczko, Artur

A2 - Strzelecki, Michał

A2 - Bociąga, Dorota

PB - Springer Science and Business Media Deutschland GmbH

T2 - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering, PCBEE 2023

Y2 - 27 September 2023 through 29 September 2023

ER -

Wilk AM, Kozłowska E, Borys D, D’Amico A, Gorczewska I, Debosz-Suwińska I et al. Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest. In Strumiłło P, Klepaczko A, Strzelecki M, Bociąga D, editors, The Latest Developments and Challenges in Biomedical Engineering - Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical Engineering. Springer Science and Business Media Deutschland GmbH. 2024. p. 163-173. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-38430-1_13

Improving the Predictive Ability of Radiomics-Based Regression Survival Models Through Incorporating Multiple Regions of Interest

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this