开发和综合评估基于 DBCG 共识的全国乳腺癌放疗淋巴结水平自动分割模型。

IF 4.9 1区医学 Q1 ONCOLOGY

Radiotherapy and Oncology Pub Date : 2024-10-05 DOI:10.1016/j.radonc.2024.110567

Emma Skarsø Buhl , Ebbe Laugaard Lorenzen , Lasse Refsgaard , Anders Winther Mølby Nielsen , Annette Torbøl Lund Brixen , Else Maae , Hanne Spangsberg Holm , Joachim Schøler , Linh My Hoang Thai , Louise Wichmann Matthiessen , Maja Vestmø Maraldo , Mathias Maximiliano Nielsen , Marianne Besserman Johansen , Marie Louise Milo , Marie Benzon Mogensen , Mette Holck Nielsen , Mette Møller , Maja Sand , Peter Schultz , Sami Aziz-Jowad Al-Rawi , Stine Sofia Korreman

{"title":"开发和综合评估基于 DBCG 共识的全国乳腺癌放疗淋巴结水平自动分割模型。","authors":"Emma Skarsø Buhl , Ebbe Laugaard Lorenzen , Lasse Refsgaard , Anders Winther Mølby Nielsen , Annette Torbøl Lund Brixen , Else Maae , Hanne Spangsberg Holm , Joachim Schøler , Linh My Hoang Thai , Louise Wichmann Matthiessen , Maja Vestmø Maraldo , Mathias Maximiliano Nielsen , Marianne Besserman Johansen , Marie Louise Milo , Marie Benzon Mogensen , Mette Holck Nielsen , Mette Møller , Maja Sand , Peter Schultz , Sami Aziz-Jowad Al-Rawi , Stine Sofia Korreman","doi":"10.1016/j.radonc.2024.110567","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and purpose</h3><div>This study aimed at training and validating a multi-institutional deep learning (DL) auto segmentation model for nodal clinical target volume (CTVn) in high-risk breast cancer (BC) patients with both training and validation dataset created with multi-institutional participation, with the overall aim of national clinical implementation in Denmark.</div></div><div><h3>Materials and methods</h3><div>A gold standard (GS) dataset and a high-quality training dataset were created by 21 BC delineation experts from all radiotherapy centres in Denmark. The delineations were created according to ESTRO consensus delineation guidelines. Four models were trained: One per laterality and extension of CTVn internal mammary nodes. The DL models were tested quantitatively in their own test-set and in relation to interobserver variation (IOV) in the GS dataset with geometrical metrics, such as the Dice Similarity Coefficient (DSC). A blinded qualitative evaluation was conducted with a national board, presented to both DL and manual delineations.</div></div><div><h3>Results</h3><div>A median DSC > 0.7 was found for all, except the CTVn interpectoral node in one of the models. In the qualitative evaluation ‘no corrections needed’ were acquired for 297 (36 %) in the DL structures and 286 (34 %) for manual delineations. A higher rate of ‘major corrections’ and ‘easier to start from scratch’ was found in the manual delineations. The models performed within the IOV of an expert group, with two exceptions.</div></div><div><h3>Conclusion</h3><div>DL models were developed on a national consensus cohort and performed on par with the IOV between BC experts and had a comparable or higher clinical acceptance than expert manual delineations.</div></div>","PeriodicalId":21041,"journal":{"name":"Radiotherapy and Oncology","volume":"201 ","pages":"Article 110567"},"PeriodicalIF":4.9000,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development and comprehensive evaluation of a national DBCG consensus-based auto-segmentation model for lymph node levels in breast cancer radiotherapy\",\"authors\":\"Emma Skarsø Buhl , Ebbe Laugaard Lorenzen , Lasse Refsgaard , Anders Winther Mølby Nielsen , Annette Torbøl Lund Brixen , Else Maae , Hanne Spangsberg Holm , Joachim Schøler , Linh My Hoang Thai , Louise Wichmann Matthiessen , Maja Vestmø Maraldo , Mathias Maximiliano Nielsen , Marianne Besserman Johansen , Marie Louise Milo , Marie Benzon Mogensen , Mette Holck Nielsen , Mette Møller , Maja Sand , Peter Schultz , Sami Aziz-Jowad Al-Rawi , Stine Sofia Korreman\",\"doi\":\"10.1016/j.radonc.2024.110567\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background and purpose</h3><div>This study aimed at training and validating a multi-institutional deep learning (DL) auto segmentation model for nodal clinical target volume (CTVn) in high-risk breast cancer (BC) patients with both training and validation dataset created with multi-institutional participation, with the overall aim of national clinical implementation in Denmark.</div></div><div><h3>Materials and methods</h3><div>A gold standard (GS) dataset and a high-quality training dataset were created by 21 BC delineation experts from all radiotherapy centres in Denmark. The delineations were created according to ESTRO consensus delineation guidelines. Four models were trained: One per laterality and extension of CTVn internal mammary nodes. The DL models were tested quantitatively in their own test-set and in relation to interobserver variation (IOV) in the GS dataset with geometrical metrics, such as the Dice Similarity Coefficient (DSC). A blinded qualitative evaluation was conducted with a national board, presented to both DL and manual delineations.</div></div><div><h3>Results</h3><div>A median DSC > 0.7 was found for all, except the CTVn interpectoral node in one of the models. In the qualitative evaluation ‘no corrections needed’ were acquired for 297 (36 %) in the DL structures and 286 (34 %) for manual delineations. A higher rate of ‘major corrections’ and ‘easier to start from scratch’ was found in the manual delineations. The models performed within the IOV of an expert group, with two exceptions.</div></div><div><h3>Conclusion</h3><div>DL models were developed on a national consensus cohort and performed on par with the IOV between BC experts and had a comparable or higher clinical acceptance than expert manual delineations.</div></div>\",\"PeriodicalId\":21041,\"journal\":{\"name\":\"Radiotherapy and Oncology\",\"volume\":\"201 \",\"pages\":\"Article 110567\"},\"PeriodicalIF\":4.9000,\"publicationDate\":\"2024-10-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiotherapy and Oncology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S016781402403545X\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiotherapy and Oncology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S016781402403545X","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

摘要

背景和目的：本研究旨在通过多机构参与创建的训练和验证数据集，训练和验证多机构深度学习（DL）自动分割模型，用于高危乳腺癌（BC）患者的结节临床靶体积（CTVn），总体目标是在丹麦全国范围内临床实施：金标准（GS）数据集和高质量训练数据集由来自丹麦所有放疗中心的 21 位 BC 划线专家创建。划线是根据 ESTRO 共识划线指南创建的。共训练了四个模型：每个侧位和 CTVn 内部乳腺结节的延伸各一个。DL 模型在自己的测试集中进行了定量测试，并根据 GS 数据集中的观察者间差异 (IOV) 使用几何指标（如骰子相似系数 (DSC)）进行了测试。国家委员会对 DL 和人工划线进行了盲法定性评估：结果：除了其中一个模型中的 CTVn 腔间结节外，所有模型的 DSC 中值均大于 0.7。在定性评估中，有 297 例（36%）DL 结构和 286 例（34%）人工划线获得了 "无需校正 "的结果。在人工划线中，"重大修正 "和 "更容易从头开始 "的比例较高。除两个例外情况外，这些模型的性能都在专家组的 IOV 范围内：DL模型是在全国共识队列的基础上开发的，其性能与BC专家之间的IOV相当，临床接受度与专家手动划线相当或更高。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Development and comprehensive evaluation of a national DBCG consensus-based auto-segmentation model for lymph node levels in breast cancer radiotherapy

Background and purpose

This study aimed at training and validating a multi-institutional deep learning (DL) auto segmentation model for nodal clinical target volume (CTVn) in high-risk breast cancer (BC) patients with both training and validation dataset created with multi-institutional participation, with the overall aim of national clinical implementation in Denmark.

Materials and methods

A gold standard (GS) dataset and a high-quality training dataset were created by 21 BC delineation experts from all radiotherapy centres in Denmark. The delineations were created according to ESTRO consensus delineation guidelines. Four models were trained: One per laterality and extension of CTVn internal mammary nodes. The DL models were tested quantitatively in their own test-set and in relation to interobserver variation (IOV) in the GS dataset with geometrical metrics, such as the Dice Similarity Coefficient (DSC). A blinded qualitative evaluation was conducted with a national board, presented to both DL and manual delineations.

Results

A median DSC > 0.7 was found for all, except the CTVn interpectoral node in one of the models. In the qualitative evaluation ‘no corrections needed’ were acquired for 297 (36 %) in the DL structures and 286 (34 %) for manual delineations. A higher rate of ‘major corrections’ and ‘easier to start from scratch’ was found in the manual delineations. The models performed within the IOV of an expert group, with two exceptions.

Conclusion

DL models were developed on a national consensus cohort and performed on par with the IOV between BC experts and had a comparable or higher clinical acceptance than expert manual delineations.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Radiotherapy and Oncology 医学-核医学

CiteScore

10.30

自引率

10.50%

发文量

2445

审稿时长

45 days

期刊介绍： Radiotherapy and Oncology publishes papers describing original research as well as review articles. It covers areas of interest relating to radiation oncology. This includes: clinical radiotherapy, combined modality treatment, translational studies, epidemiological outcomes, imaging, dosimetry, and radiation therapy planning, experimental work in radiobiology, chemobiology, hyperthermia and tumour biology, as well as data science in radiation oncology and physics aspects relevant to oncology.Papers on more general aspects of interest to the radiation oncologist including chemotherapy, surgery and immunology are also published.