Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy

Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fischer, Paul, Willms, Hannah, Schneider, Moritz, Thorwarth, Daniela, Muehlebach, Michael, Baumgartner, Christian F
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Fischer, Paul
Willms, Hannah
Schneider, Moritz
Thorwarth, Daniela
Muehlebach, Michael
Baumgartner, Christian F
description Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving this requires fast and accurate dose calculations. While Monte Carlo simulations offer accuracy, they are computationally intensive. Deep learning frameworks show promise, yet lack uncertainty quantification crucial for high-risk applications like RT. Risk-controlling prediction sets (RCPS) offer model-agnostic uncertainty quantification with mathematical guarantees. However, we show that naive application of RCPS may lead to only certain subgroups such as the image background being risk-controlled. In this work, we extend RCPS to provide prediction intervals with coverage guarantees for multiple subgroups with unknown subgroup membership at test time. We evaluate our algorithm on real clinical planing volumes from five different anatomical regions and show that our novel subgroup RCPS (SG-RCPS) algorithm leads to prediction intervals that jointly control the risk for multiple subgroups. In particular, our method controls the risk of the crucial voxels along the radiation beam significantly better than conventional RCPS.
doi_str_mv 10.48550/arxiv.2407.08432
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2407_08432</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2407_08432</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2407_084323</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zOwMDE24mRwDC5NSi_KLy3QDS5ITc5My0xWCMosztZ1zs8rKcrPyUlNUXDJL05VcC0uycxNLMnMz1PIzFMISkzJzC_JSC1KLKjkYWBNS8wpTuWF0twM8m6uIc4eumDL4guKgPqKKuNBlsaDLTUmrAIAU6o3YA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy</title><source>arXiv.org</source><creator>Fischer, Paul ; Willms, Hannah ; Schneider, Moritz ; Thorwarth, Daniela ; Muehlebach, Michael ; Baumgartner, Christian F</creator><creatorcontrib>Fischer, Paul ; Willms, Hannah ; Schneider, Moritz ; Thorwarth, Daniela ; Muehlebach, Michael ; Baumgartner, Christian F</creatorcontrib><description>Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving this requires fast and accurate dose calculations. While Monte Carlo simulations offer accuracy, they are computationally intensive. Deep learning frameworks show promise, yet lack uncertainty quantification crucial for high-risk applications like RT. Risk-controlling prediction sets (RCPS) offer model-agnostic uncertainty quantification with mathematical guarantees. However, we show that naive application of RCPS may lead to only certain subgroups such as the image background being risk-controlled. In this work, we extend RCPS to provide prediction intervals with coverage guarantees for multiple subgroups with unknown subgroup membership at test time. We evaluate our algorithm on real clinical planing volumes from five different anatomical regions and show that our novel subgroup RCPS (SG-RCPS) algorithm leads to prediction intervals that jointly control the risk for multiple subgroups. In particular, our method controls the risk of the crucial voxels along the radiation beam significantly better than conventional RCPS.</description><identifier>DOI: 10.48550/arxiv.2407.08432</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2024-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2407.08432$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2407.08432$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Fischer, Paul</creatorcontrib><creatorcontrib>Willms, Hannah</creatorcontrib><creatorcontrib>Schneider, Moritz</creatorcontrib><creatorcontrib>Thorwarth, Daniela</creatorcontrib><creatorcontrib>Muehlebach, Michael</creatorcontrib><creatorcontrib>Baumgartner, Christian F</creatorcontrib><title>Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy</title><description>Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving this requires fast and accurate dose calculations. While Monte Carlo simulations offer accuracy, they are computationally intensive. Deep learning frameworks show promise, yet lack uncertainty quantification crucial for high-risk applications like RT. Risk-controlling prediction sets (RCPS) offer model-agnostic uncertainty quantification with mathematical guarantees. However, we show that naive application of RCPS may lead to only certain subgroups such as the image background being risk-controlled. In this work, we extend RCPS to provide prediction intervals with coverage guarantees for multiple subgroups with unknown subgroup membership at test time. We evaluate our algorithm on real clinical planing volumes from five different anatomical regions and show that our novel subgroup RCPS (SG-RCPS) algorithm leads to prediction intervals that jointly control the risk for multiple subgroups. In particular, our method controls the risk of the crucial voxels along the radiation beam significantly better than conventional RCPS.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw1zOwMDE24mRwDC5NSi_KLy3QDS5ITc5My0xWCMosztZ1zs8rKcrPyUlNUXDJL05VcC0uycxNLMnMz1PIzFMISkzJzC_JSC1KLKjkYWBNS8wpTuWF0twM8m6uIc4eumDL4guKgPqKKuNBlsaDLTUmrAIAU6o3YA</recordid><startdate>20240711</startdate><enddate>20240711</enddate><creator>Fischer, Paul</creator><creator>Willms, Hannah</creator><creator>Schneider, Moritz</creator><creator>Thorwarth, Daniela</creator><creator>Muehlebach, Michael</creator><creator>Baumgartner, Christian F</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240711</creationdate><title>Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy</title><author>Fischer, Paul ; Willms, Hannah ; Schneider, Moritz ; Thorwarth, Daniela ; Muehlebach, Michael ; Baumgartner, Christian F</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2407_084323</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Fischer, Paul</creatorcontrib><creatorcontrib>Willms, Hannah</creatorcontrib><creatorcontrib>Schneider, Moritz</creatorcontrib><creatorcontrib>Thorwarth, Daniela</creatorcontrib><creatorcontrib>Muehlebach, Michael</creatorcontrib><creatorcontrib>Baumgartner, Christian F</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fischer, Paul</au><au>Willms, Hannah</au><au>Schneider, Moritz</au><au>Thorwarth, Daniela</au><au>Muehlebach, Michael</au><au>Baumgartner, Christian F</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy</atitle><date>2024-07-11</date><risdate>2024</risdate><abstract>Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving this requires fast and accurate dose calculations. While Monte Carlo simulations offer accuracy, they are computationally intensive. Deep learning frameworks show promise, yet lack uncertainty quantification crucial for high-risk applications like RT. Risk-controlling prediction sets (RCPS) offer model-agnostic uncertainty quantification with mathematical guarantees. However, we show that naive application of RCPS may lead to only certain subgroups such as the image background being risk-controlled. In this work, we extend RCPS to provide prediction intervals with coverage guarantees for multiple subgroups with unknown subgroup membership at test time. We evaluate our algorithm on real clinical planing volumes from five different anatomical regions and show that our novel subgroup RCPS (SG-RCPS) algorithm leads to prediction intervals that jointly control the risk for multiple subgroups. In particular, our method controls the risk of the crucial voxels along the radiation beam significantly better than conventional RCPS.</abstract><doi>10.48550/arxiv.2407.08432</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2407.08432
ispartof
issn
language eng
recordid cdi_arxiv_primary_2407_08432
source arXiv.org
subjects Computer Science - Learning
title Subgroup-Specific Risk-Controlled Dose Estimation in Radiotherapy
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T02%3A37%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Subgroup-Specific%20Risk-Controlled%20Dose%20Estimation%20in%20Radiotherapy&rft.au=Fischer,%20Paul&rft.date=2024-07-11&rft_id=info:doi/10.48550/arxiv.2407.08432&rft_dat=%3Carxiv_GOX%3E2407_08432%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true