Deep learning-based segmentation of gallbladder cancer on abdominal computed tomography scans: a multicenter study

IF 2.2 3区 医学 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Pankaj Gupta, Niharika Dutta, Ajay Tomar, Shravya Singh, Sonam Choudhary, Nandita Mehta, Vansha Mehta, Rishabh Sheth, Divyashree Srivastava, Salai Thanihai, Palki Singla, Gaurav Prakash, Thakur Yadav, Lileswar Kaman, Santosh Irrinki, Harjeet Singh, Niket Shah, Amit Choudhari, Shraddha Patkar, Mahesh Goel, Rajnikant Yadav, Archana Gupta, Ishan Kumar, Kajal Seth, Usha Dutta, Chetan Arora
{"title":"Deep learning-based segmentation of gallbladder cancer on abdominal computed tomography scans: a multicenter study","authors":"Pankaj Gupta,&nbsp;Niharika Dutta,&nbsp;Ajay Tomar,&nbsp;Shravya Singh,&nbsp;Sonam Choudhary,&nbsp;Nandita Mehta,&nbsp;Vansha Mehta,&nbsp;Rishabh Sheth,&nbsp;Divyashree Srivastava,&nbsp;Salai Thanihai,&nbsp;Palki Singla,&nbsp;Gaurav Prakash,&nbsp;Thakur Yadav,&nbsp;Lileswar Kaman,&nbsp;Santosh Irrinki,&nbsp;Harjeet Singh,&nbsp;Niket Shah,&nbsp;Amit Choudhari,&nbsp;Shraddha Patkar,&nbsp;Mahesh Goel,&nbsp;Rajnikant Yadav,&nbsp;Archana Gupta,&nbsp;Ishan Kumar,&nbsp;Kajal Seth,&nbsp;Usha Dutta,&nbsp;Chetan Arora","doi":"10.1007/s00261-025-04887-y","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><p>To train and validate segmentation models for automated segmentation of gallbladder cancer (GBC) lesions from contrast-enhanced CT images.</p><h3>Materials and methods</h3><p>This retrospective study comprised consecutive patients with pathologically proven treatment naïve GBC who underwent a contrast-enhanced CT scan at four different tertiary care referral hospitals. The training and validation cohort comprised CT scans of 317 patients (center 1). The internal test cohort comprised a temporally independent cohort (<i>n</i> = 29) from center 1 (internal test 1). The external test cohort comprised CT scans from three centers [ (<i>n</i> = 85)]. We trained the state-of-the-art 2D and 3D image segmentation models, SAM Adapter, MedSAM, 3D TransUNet, SAM-Med3D, and 3D-nnU-Net, for automated segmentation of the GBC. The models’ performance for GBC segmentation on the test datasets was assessed via dice score and intersection over union (IoU) using manual segmentation as the reference standard.</p><h3>Results</h3><p>The 2D models performed better than 3D models. Overall, MedSAM achieved the highest dice and IoU scores on both the internal [mean dice (SD) 0.776 (0.106) and mean IoU 0.653 (0.133)] and external [mean dice (SD) 0.763 (0.098) and mean IoU 0.637 (0.116)] test sets. Among the 3D models, TransUNet showed the best segmentation performance with mean dice (SD) and IoU (SD) of 0.479 (0.268) and 0.356 (0.235) in the internal test and 0.409 (0.339) and 0.317 (0.283) in the external test sets. The segmentation performance was not associated with GBC morphology. There was weak correlation between the dice/IoU and the size of the GBC lesions for any segmentation model.</p><h3>Conclusion</h3><p>We trained 2D and 3D GBC segmentation models on a large dataset and validated these models on external datasets. MedSAM, a 2D prompt-based foundational model, achieved the best segmentation performance.</p><h3>Graphical abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":7126,"journal":{"name":"Abdominal Radiology","volume":"50 10","pages":"4615 - 4624"},"PeriodicalIF":2.2000,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Abdominal Radiology","FirstCategoryId":"3","ListUrlMain":"https://link.springer.com/article/10.1007/s00261-025-04887-y","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives

To train and validate segmentation models for automated segmentation of gallbladder cancer (GBC) lesions from contrast-enhanced CT images.

Materials and methods

This retrospective study comprised consecutive patients with pathologically proven treatment naïve GBC who underwent a contrast-enhanced CT scan at four different tertiary care referral hospitals. The training and validation cohort comprised CT scans of 317 patients (center 1). The internal test cohort comprised a temporally independent cohort (n = 29) from center 1 (internal test 1). The external test cohort comprised CT scans from three centers [ (n = 85)]. We trained the state-of-the-art 2D and 3D image segmentation models, SAM Adapter, MedSAM, 3D TransUNet, SAM-Med3D, and 3D-nnU-Net, for automated segmentation of the GBC. The models’ performance for GBC segmentation on the test datasets was assessed via dice score and intersection over union (IoU) using manual segmentation as the reference standard.

Results

The 2D models performed better than 3D models. Overall, MedSAM achieved the highest dice and IoU scores on both the internal [mean dice (SD) 0.776 (0.106) and mean IoU 0.653 (0.133)] and external [mean dice (SD) 0.763 (0.098) and mean IoU 0.637 (0.116)] test sets. Among the 3D models, TransUNet showed the best segmentation performance with mean dice (SD) and IoU (SD) of 0.479 (0.268) and 0.356 (0.235) in the internal test and 0.409 (0.339) and 0.317 (0.283) in the external test sets. The segmentation performance was not associated with GBC morphology. There was weak correlation between the dice/IoU and the size of the GBC lesions for any segmentation model.

Conclusion

We trained 2D and 3D GBC segmentation models on a large dataset and validated these models on external datasets. MedSAM, a 2D prompt-based foundational model, achieved the best segmentation performance.

Graphical abstract

基于深度学习的腹部计算机断层扫描胆囊癌分割:一项多中心研究。
目的:训练和验证从增强CT图像中自动分割胆囊癌(GBC)病变的分割模型。材料和方法:本回顾性研究纳入了病理证实治疗naïve GBC的连续患者,这些患者在四家不同的三级保健转诊医院接受了对比增强CT扫描。训练和验证队列包括317名患者的CT扫描(中心1)。内部测试队列包括来自中心1的临时独立队列(n = 29)(内部测试1)。外部测试队列包括来自三个中心的CT扫描[(n = 85)]。我们训练了最先进的2D和3D图像分割模型,SAM Adapter, MedSAM, 3D TransUNet, SAM- med3d和3D- nnu - net,用于GBC的自动分割。以人工分割为参考标准,通过骰子分数和交集比联合(IoU)来评估模型在测试数据集上的GBC分割性能。结果:二维模型优于三维模型。总体而言,MedSAM在内部[平均骰子(SD) 0.776(0.106)和平均IoU 0.653(0.133)]和外部[平均骰子(SD) 0.763(0.098)和平均IoU 0.637(0.116)]测试集中获得了最高的骰子和IoU分数。在3D模型中,TransUNet的分割效果最好,内部测试集的平均dice (SD)和IoU (SD)分别为0.479(0.268)和0.356(0.235),外部测试集的平均dice (SD)和IoU (SD)分别为0.409(0.339)和0.317(0.283)。分割性能与GBC形态无关。对于任何分割模型,骰子/IoU与GBC病变大小之间存在弱相关性。结论:我们在大型数据集上训练了2D和3D GBC分割模型,并在外部数据集上对这些模型进行了验证。基于二维提示符的基础模型MedSAM的分割效果最好。
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
Abdominal Radiology
Abdominal Radiology Medicine-Radiology, Nuclear Medicine and Imaging
CiteScore
5.20
自引率
8.30%
发文量
334
期刊介绍: Abdominal Radiology seeks to meet the professional needs of the abdominal radiologist by publishing clinically pertinent original, review and practice related articles on the gastrointestinal and genitourinary tracts and abdominal interventional and radiologic procedures. Case reports are generally not accepted unless they are the first report of a new disease or condition, or part of a special solicited section. Reasons to Publish Your Article in Abdominal Radiology: · Official journal of the Society of Abdominal Radiology (SAR) · Published in Cooperation with: European Society of Gastrointestinal and Abdominal Radiology (ESGAR) European Society of Urogenital Radiology (ESUR) Asian Society of Abdominal Radiology (ASAR) · Efficient handling and Expeditious review · Author feedback is provided in a mentoring style · Global readership · Readers can earn CME credits
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信