Multi-center external validation of an automated method segmenting and differentiating atypical lipomatous tumors from lipomas using radiomics and deep-learning on MRI.

IF 9.6 1区医学 Q1 MEDICINE, GENERAL & INTERNAL

EClinicalMedicine Pub Date : 2024-09-18 eCollection Date: 2024-10-01 DOI:10.1016/j.eclinm.2024.102802

D J Spaanderman, S N Hakkesteegt, D F Hanff, A R W Schut, L M Schiphouwer, M Vos, C Messiou, S J Doran, R L Jones, A J Hayes, L Nardo, Y G Abdelhafez, A W Moawad, K M Elsayes, S Lee, T M Link, W J Niessen, G J L H van Leenders, J J Visser, S Klein, D J Grünhagen, C Verhoef, M P A Starmans

{"title":"Multi-center external validation of an automated method segmenting and differentiating atypical lipomatous tumors from lipomas using radiomics and deep-learning on MRI.","authors":"D J Spaanderman, S N Hakkesteegt, D F Hanff, A R W Schut, L M Schiphouwer, M Vos, C Messiou, S J Doran, R L Jones, A J Hayes, L Nardo, Y G Abdelhafez, A W Moawad, K M Elsayes, S Lee, T M Link, W J Niessen, G J L H van Leenders, J J Visser, S Klein, D J Grünhagen, C Verhoef, M P A Starmans","doi":"10.1016/j.eclinm.2024.102802","DOIUrl":null,"url":null,"abstract":"Background: As differentiating between lipomas and atypical lipomatous tumors (ALTs) based on imaging is challenging and requires biopsies, radiomics has been proposed to aid the diagnosis. This study aimed to externally and prospectively validate a radiomics model differentiating between lipomas and ALTs on MRI in three large, multi-center cohorts, and extend it with automatic and minimally interactive segmentation methods to increase clinical feasibility.Methods: Three study cohorts were formed, two for external validation containing data from medical centers in the United States (US) collected from 2008 until 2018 and the United Kingdom (UK) collected from 2011 until 2017, and one for prospective validation consisting of data collected from 2020 until 2021 in the Netherlands. Patient characteristics, MDM2 amplification status, and MRI scans were collected. An automatic segmentation method was developed to segment all tumors on T1-weighted MRI scans of the validation cohorts. Segmentations were subsequently quality scored. In case of insufficient quality, an interactive segmentation method was used. Radiomics performance was evaluated for all cohorts and compared to two radiologists.Findings: The validation cohorts included 150 (54% ALT), 208 (37% ALT), and 86 patients (28% ALT) from the US, UK and NL. Of the 444 cases, 78% were automatically segmented. For 22%, interactive segmentation was necessary due to insufficient quality, with only 3% of all patients requiring manual adjustment. External validation resulted in an AUC of 0.74 (95% CI: 0.66, 0.82) in US data and 0.86 (0.80, 0.92) in UK data. Prospective validation resulted in an AUC of 0.89 (0.83, 0.96). The radiomics model performed similar to the two radiologists (US: 0.79 and 0.76, UK: 0.86 and 0.86, NL: 0.82 and 0.85).Interpretation: The radiomics model extended with automatic and minimally interactive segmentation methods accurately differentiated between lipomas and ALTs in two large, multi-center external cohorts, and in prospective validation, performing similar to expert radiologists, possibly limiting the need for invasive diagnostics.Funding: Hanarth fonds.","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":null,"pages":null},"PeriodicalIF":9.6000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11440245/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EClinicalMedicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.eclinm.2024.102802","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}

引用次数: 0

Abstract

Background: As differentiating between lipomas and atypical lipomatous tumors (ALTs) based on imaging is challenging and requires biopsies, radiomics has been proposed to aid the diagnosis. This study aimed to externally and prospectively validate a radiomics model differentiating between lipomas and ALTs on MRI in three large, multi-center cohorts, and extend it with automatic and minimally interactive segmentation methods to increase clinical feasibility.

Methods: Three study cohorts were formed, two for external validation containing data from medical centers in the United States (US) collected from 2008 until 2018 and the United Kingdom (UK) collected from 2011 until 2017, and one for prospective validation consisting of data collected from 2020 until 2021 in the Netherlands. Patient characteristics, MDM2 amplification status, and MRI scans were collected. An automatic segmentation method was developed to segment all tumors on T1-weighted MRI scans of the validation cohorts. Segmentations were subsequently quality scored. In case of insufficient quality, an interactive segmentation method was used. Radiomics performance was evaluated for all cohorts and compared to two radiologists.

Findings: The validation cohorts included 150 (54% ALT), 208 (37% ALT), and 86 patients (28% ALT) from the US, UK and NL. Of the 444 cases, 78% were automatically segmented. For 22%, interactive segmentation was necessary due to insufficient quality, with only 3% of all patients requiring manual adjustment. External validation resulted in an AUC of 0.74 (95% CI: 0.66, 0.82) in US data and 0.86 (0.80, 0.92) in UK data. Prospective validation resulted in an AUC of 0.89 (0.83, 0.96). The radiomics model performed similar to the two radiologists (US: 0.79 and 0.76, UK: 0.86 and 0.86, NL: 0.82 and 0.85).

Interpretation: The radiomics model extended with automatic and minimally interactive segmentation methods accurately differentiated between lipomas and ALTs in two large, multi-center external cohorts, and in prospective validation, performing similar to expert radiologists, possibly limiting the need for invasive diagnostics.

Funding: Hanarth fonds.

查看原文本刊更多论文

利用放射组学和深度学习在核磁共振成像上分割和区分非典型脂肪瘤与脂肪瘤的自动方法的多中心外部验证。

背景：根据成像区分脂肪瘤和非典型脂肪瘤（ALTs）具有挑战性，而且需要活检，因此有人提出用放射组学来辅助诊断。本研究的目的是在三个大型多中心队列中对核磁共振成像上区分脂肪瘤和非典型脂肪瘤的放射组学模型进行外部和前瞻性验证，并用自动和微交互式分割方法对其进行扩展，以提高临床可行性：形成了三个研究队列，其中两个用于外部验证，包含美国医疗中心从 2008 年至 2018 年收集的数据和英国医疗中心从 2011 年至 2017 年收集的数据；另一个用于前瞻性验证，包含荷兰医疗中心从 2020 年至 2021 年收集的数据。收集了患者特征、MDM2扩增状态和磁共振成像扫描结果。开发了一种自动分割方法，用于分割验证队列中 T1 加权 MRI 扫描的所有肿瘤。随后对分割结果进行质量评分。如果质量不高，则采用交互式分割方法。对所有队列的放射组学性能进行了评估，并与两名放射科医生进行了比较：验证队列包括来自美国、英国和荷兰的 150 名患者（54% ALT）、208 名患者（37% ALT）和 86 名患者（28% ALT）。在 444 个病例中，78% 是自动分割的。有 22% 的患者由于质量不高而需要进行交互式分割，只有 3% 的患者需要进行手动调整。通过外部验证，美国数据的 AUC 为 0.74（95% CI：0.66, 0.82），英国数据的 AUC 为 0.86（0.80, 0.92）。前瞻性验证的 AUC 为 0.89 (0.83, 0.96)。放射组学模型的表现与两位放射科医生相似（美国：0.79 和 0.76；英国：0.86 和 0.86；荷兰：0.82 和 0.85）：在两个大型多中心外部队列和前瞻性验证中，使用自动和微交互式分割方法扩展的放射组学模型能准确区分脂肪瘤和ALT，其表现与放射科专家相似，可能会限制对侵入性诊断的需求：基金：Hanarth 基金会。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

EClinicalMedicine Medicine-Medicine (all)

CiteScore

18.90

自引率

1.30%

发文量

506

审稿时长

22 days

期刊介绍： eClinicalMedicine is a gold open-access clinical journal designed to support frontline health professionals in addressing the complex and rapid health transitions affecting societies globally. The journal aims to assist practitioners in overcoming healthcare challenges across diverse communities, spanning diagnosis, treatment, prevention, and health promotion. Integrating disciplines from various specialties and life stages, it seeks to enhance health systems as fundamental institutions within societies. With a forward-thinking approach, eClinicalMedicine aims to redefine the future of healthcare.