Understanding the impact of statistical and machine learning
choices on predictive models for radiotherapy

D 2022

Understanding the impact of statistical and machine learning choices on predictive models for radiotherapy

BÖRÖNDY, Ádám, Katarína FURMANOVÁ a Renata Georgia RAIDOU

Základní údaje

Originální název

Understanding the impact of statistical and machine learning choices on predictive models for radiotherapy

Autoři

BÖRÖNDY, Ádám, Katarína FURMANOVÁ (703 Slovensko, domácí) a Renata Georgia RAIDOU

Vydání

Neuveden, Eurographics Workshop on Visual Computing for Biology and Medicine, od s. 65-69, 5 s. 2022

Nakladatel

The Eurographics Association

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Rakousko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Kód RIV

RIV/00216224:14330/22:00126656

Organizační jednotka

Fakulta informatiky

ISBN

978-3-03868-177-9

ISSN

DOI

http://dx.doi.org/10.2312/vcbm.20221188

Klíčová slova anglicky

Visual Analytics; Life and medical sciences

Štítky

firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 6. 4. 2023 13:31, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

During radiotherapy (RT) planning, an accurate description of the location and shape of the pelvic organs is a critical factor for the successful treatment of the patient. Yet, during treatment, the pelvis anatomy may differ significantly from the planning phase. A series of recent publications, such as PREVIS [FMCM∗21], have examined alternative approaches to analyzing and predicting pelvic organ variability of individual patients. These approaches are based on a combination of several statistical and machine learning methods, which have not been thoroughly and quantitatively evaluated within the scope of pelvic anatomical variability. Several of their design decisions could have an impact on the outcome of the predictive model. The goal of this work is to assess the impact of alternative choices, focusing mainly on the two key-aspects of shape description and clustering, to generate better predictions for new patients. The results of our assessment indicate that resolution-based descriptors provide more accurate and reliable organ representations than state-of-the-art approaches, while different clustering settings (distance metric and linkage) yield only slightly different clusters. Different clustering methods are able to provide comparable results, although when more shape variability is considered their results start to deviate. These results are valuable for understanding the impact of statistical and machine learning choices on the outcomes of predictive models for anatomical variability.

Citovat

BÖRÖNDY, Ádám, Katarína FURMANOVÁ a Renata Georgia RAIDOU. Understanding the impact of statistical and machine learning choices on predictive models for radiotherapy. Online. In Renata G. Raidou, Björn Sommer, Torsten W. Kuhlen, Michael Krone, Thomas Schultz, Hsiang-Yun Wu. Eurographics Workshop on Visual Computing for Biology and Medicine. Neuveden: The Eurographics Association, 2022, s. 65-69. ISBN 978-3-03868-177-9. Dostupné z: https://dx.doi.org/10.2312/vcbm.20221188.

@inproceedings{2217397,
   author = {Böröndy, Ádám and Furmanová, Katarína and Raidou, Renata Georgia},
   address = {Neuveden},
   booktitle = {Eurographics Workshop on Visual Computing for Biology and Medicine},
   doi = {http://dx.doi.org/10.2312/vcbm.20221188},
   editor = {Renata G. Raidou, Björn Sommer, Torsten W. Kuhlen, Michael Krone, Thomas Schultz, Hsiang-Yun Wu},
   keywords = {Visual Analytics; Life and medical sciences},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Neuveden},
   isbn = {978-3-03868-177-9},
   pages = {65-69},
   publisher = {The Eurographics Association},
   title = {Understanding the impact of statistical and machine learning choices on predictive models for radiotherapy},
   url = {https://diglib.eg.org/handle/10.2312/vcbm20221188},
   year = {2022}
}

TY  - JOUR
ID  - 2217397
AU  - Böröndy, Ádám - Furmanová, Katarína - Raidou, Renata Georgia
PY  - 2022
TI  - Understanding the impact of statistical and machine learning choices on predictive models for radiotherapy
PB  - The Eurographics Association
CY  - Neuveden
SN  - 9783038681779
KW  - Visual Analytics
KW  - Life and medical sciences
UR  - https://diglib.eg.org/handle/10.2312/vcbm20221188
N2  - During radiotherapy (RT) planning, an accurate description of the location and shape of the pelvic organs is a critical factor for the successful treatment of the patient. Yet, during treatment, the pelvis anatomy may differ significantly from the planning phase. A series of recent publications, such as PREVIS [FMCM∗21], have examined alternative approaches to analyzing and predicting pelvic organ variability of individual patients. These approaches are based on a combination of several statistical and machine learning methods, which have not been thoroughly and quantitatively evaluated within the scope of pelvic anatomical variability. Several of their design decisions could have an impact on the outcome of the predictive model. The goal of this work is to assess the impact of alternative choices, focusing mainly on the two key-aspects of shape description and clustering, to generate better predictions for new patients. The results of our assessment indicate that resolution-based descriptors provide more accurate and reliable organ representations than state-of-the-art approaches, while different clustering settings (distance metric and linkage) yield only slightly different clusters. Different clustering methods are able to provide comparable results, although when more shape variability is considered their results start to deviate. These results are valuable for understanding the impact of statistical and machine learning choices on the outcomes of predictive models for anatomical variability.
ER  -

BÖRÖNDY, Ádám, Katarína FURMANOVÁ a Renata Georgia RAIDOU. Understanding the impact of statistical and machine learning choices on predictive models for radiotherapy. Online. In Renata G. Raidou, Björn Sommer, Torsten W. Kuhlen, Michael Krone, Thomas Schultz, Hsiang-Yun Wu. \textit{Eurographics Workshop on Visual Computing for Biology and Medicine}. Neuveden: The Eurographics Association, 2022, s.~65-69. ISBN~978-3-03868-177-9. Dostupné z: https://dx.doi.org/10.2312/vcbm.20221188.

Podrobný výpis o publikaci