Foundational Segmentation Models and Clinical Data Mining Enable Accurate Computer Vision for Lung Cancer.

Nathaniel C Swinburne, Christopher B Jackson, Andrew M Pagano, Joseph N Stember, Javin Schefflein, Brett Marinelli, Prashanth Kumar Panyam, Arthur Autz, Mohapar S Chopra, Andrei I Holodny, Michelle S Ginsberg
{"title":"Foundational Segmentation Models and Clinical Data Mining Enable Accurate Computer Vision for Lung Cancer.","authors":"Nathaniel C Swinburne, Christopher B Jackson, Andrew M Pagano, Joseph N Stember, Javin Schefflein, Brett Marinelli, Prashanth Kumar Panyam, Arthur Autz, Mohapar S Chopra, Andrei I Holodny, Michelle S Ginsberg","doi":"10.1007/s10278-024-01304-6","DOIUrl":null,"url":null,"abstract":"<p><p>This study aims to assess the effectiveness of integrating Segment Anything Model (SAM) and its variant MedSAM into the automated mining, object detection, and segmentation (MODS) methodology for developing robust lung cancer detection and segmentation models without post hoc labeling of training images. In a retrospective analysis, 10,000 chest computed tomography scans from patients with lung cancer were mined. Line measurement annotations were converted to bounding boxes, excluding boxes < 1 cm or > 7 cm. The You Only Look Once object detection architecture was used for teacher-student learning to label unannotated lesions on the training images. Subsequently, a final tumor detection model was trained and employed with SAM and MedSAM for tumor segmentation. Model performance was assessed on a manually annotated test dataset, with additional evaluations conducted on an external lung cancer dataset before and after detection model fine-tuning. Bootstrap resampling was used to calculate 95% confidence intervals. Data mining yielded 10,789 line annotations, resulting in 5403 training boxes. The baseline detection model achieved an internal F1 score of 0.847, improving to 0.860 after self-labeling. Tumor segmentation using the final detection model attained internal Dice similarity coefficients (DSCs) of 0.842 (SAM) and 0.822 (MedSAM). After fine-tuning, external validation showed an F1 of 0.832 and DSCs of 0.802 (SAM) and 0.804 (MedSAM). Integrating foundational segmentation models into the MODS framework results in high-performing lung cancer detection and segmentation models using only mined clinical data. Both SAM and MedSAM hold promise as foundational segmentation models for radiology images.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1552-1562"},"PeriodicalIF":0.0000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092863/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of imaging informatics in medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10278-024-01304-6","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/22 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This study aims to assess the effectiveness of integrating Segment Anything Model (SAM) and its variant MedSAM into the automated mining, object detection, and segmentation (MODS) methodology for developing robust lung cancer detection and segmentation models without post hoc labeling of training images. In a retrospective analysis, 10,000 chest computed tomography scans from patients with lung cancer were mined. Line measurement annotations were converted to bounding boxes, excluding boxes < 1 cm or > 7 cm. The You Only Look Once object detection architecture was used for teacher-student learning to label unannotated lesions on the training images. Subsequently, a final tumor detection model was trained and employed with SAM and MedSAM for tumor segmentation. Model performance was assessed on a manually annotated test dataset, with additional evaluations conducted on an external lung cancer dataset before and after detection model fine-tuning. Bootstrap resampling was used to calculate 95% confidence intervals. Data mining yielded 10,789 line annotations, resulting in 5403 training boxes. The baseline detection model achieved an internal F1 score of 0.847, improving to 0.860 after self-labeling. Tumor segmentation using the final detection model attained internal Dice similarity coefficients (DSCs) of 0.842 (SAM) and 0.822 (MedSAM). After fine-tuning, external validation showed an F1 of 0.832 and DSCs of 0.802 (SAM) and 0.804 (MedSAM). Integrating foundational segmentation models into the MODS framework results in high-performing lung cancer detection and segmentation models using only mined clinical data. Both SAM and MedSAM hold promise as foundational segmentation models for radiology images.

基础分割模型和临床数据挖掘实现了肺癌的精确计算机视觉。
本研究旨在评估将 "任意分割模型"(Segment Anything Model,SAM)及其变体 "医疗分割模型"(MedSAM)集成到自动挖掘、对象检测和分割(MODS)方法中的有效性,以开发鲁棒的肺癌检测和分割模型,而无需对训练图像进行事后标记。在一项回顾性分析中,对肺癌患者的 10,000 张胸部计算机断层扫描图像进行了挖掘。线性测量注释被转换为边界框,不包括 7 厘米的框。利用 "只看一次 "对象检测架构进行师生学习,对训练图像上未标注的病灶进行标注。随后,对最终的肿瘤检测模型进行了训练,并将其与 SAM 和 MedSAM 一起用于肿瘤分割。在人工标注的测试数据集上评估了模型性能,并在检测模型微调前后在外部肺癌数据集上进行了额外评估。使用 Bootstrap 重采样法计算 95% 的置信区间。数据挖掘获得了 10789 条线注释,产生了 5403 个训练框。基线检测模型的内部 F1 得分为 0.847,自我标记后提高到 0.860。使用最终检测模型进行肿瘤分割的内部戴斯相似系数(DSC)分别为 0.842(SAM)和 0.822(MedSAM)。经过微调后,外部验证显示 F1 为 0.832,DSC 为 0.802(SAM)和 0.804(MedSAM)。将基础分割模型集成到 MODS 框架中,只需使用挖掘出的临床数据,就能建立高性能的肺癌检测和分割模型。SAM 和 MedSAM 都有望成为放射学图像的基础分割模型。
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
自引率
0.00%
发文量
0
×
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:481959085
Book学术官方微信