The Federated Tumor Segmentation (FeTS) platform: An intuitive tool facilitating secure multi-institutional collaboration

联合肿瘤分割 (FeTS) 平台：促进安全多机构协作的直观工具

• 批准号: 10248412
• 负责人: Spyridon Bakas
• 金额: $ 35.8万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-05 至 2023-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10248412
• 关键词: Adoption; Agreement; Algorithms; Anatomy; Appearance; Back; Benchmarking; Brain; Brain Neoplasms; Clinical; Collaborations; Communities; Consensus; Data; Data Set; Databases; Development; Diagnostic radiologic examination; Docking; Face; Feedback; Glioma; Goals; Gold; Hospitals; Image; Image Analysis; Individual; Institution; International; Intuition; Knowledge; Label; Learning; Legal; Lesion; Letters; Liver neoplasms; Location; MRI Scans; Magnetic Resonance Imaging; Malignant Neoplasms; Mammary Neoplasms; Manuals; Medical Imaging; Modeling; Monitor; Multiple Myeloma; Observer Variation; Outcome; Ownership; Participant; Patients; Pattern; Performance; Phenotype; Privacy; Radio; Research; Research Personnel; Scanning; Secure; Shapes; Software Tools; Solid Neoplasm; Source Code; Structure; Technology; Testing; Training; Training Activity; Update; Validation; Variant; Work; X-Ray Computed Tomography; algorithm training; anticancer research; base; bone; clinical translation; clinically translatable; contrast enhanced; graphical user interface; human error; improved; interactive tool; light weight; open source; open source tool; predict clinical outcome; repository; segmentation algorithm; tool; tumor; user-friendly

ABSTRACT: Accurate segmentation of solid tumors is challenging, due to their heterogeneous shape, extent, and location, as well as their appearance variation caused by the diversity of medical imaging. Manual annotation is tedious, prone to misinterpretation, human error, and observer bias. All these factors hinder further image analysis towards understanding tumor radio-phenotypes, predicting clinical outcomes, and monitoring progression patterns. Computational competitions have been seeking optimal advanced computational segmentation algorithms (ACSAs) for specific abnormalities, by pooling multi-institutional data together and benchmarking ACSAs from international groups. Along these lines, we have been successfully leading the organization of the International Brain Tumor Segmentation (BraTS) challenge, since 2012, towards a publicly-available pooled dataset of 542 multi-parametric MRI scans of glioma patients from 19 institutions. In the summarized analysis of all BraTS results, we have shown that although individual ACSAs do not outperform the gold standard agreement across expert clinicians, their fusion does outperform it, in terms of both accuracy and consistency across subjects. Towards the wider application of these ACSAs, in 2017 we created the BraTS algorithmic repository to make available Docker containers of individual ACSAs, created by BraTS participants. However, fusion of these ACSAs is still out of reach for clinical researchers, as there is no graphical user interface (GUI) to facilitate it, and execution of such algorithms requires substantial computational background by the user. Furthermore, although competitions such as BraTS have shown promise, they cannot easily scale due to the requirement of pooling patient data from multiple institutions to a single location, that often faces legal, privacy, and data-ownership concerns. These concerns motivate distributed learning solutions, where the data are always retained within their institutions. We have been investigating such solutions to avoid the current paradigm of multi-institutional collaboration, i.e., data-sharing, and considering their potential multi-institutional adoption, with respect to privacy, scalability, and performance, we found federated learning (FL) to be most appropriate. In FL, each institution trains a model and shares it (without patient data) with an aggregation server, which then integrates institutional models in parallel and distributes back a consensus model. In this proposal, we focus on developing the open- source Federated Tumor Segmentation (FeTS) platform, which with a user-friendly GUI will aim at i) bringing pre- trained models of various ACSAs and their fusion closer to clinical experts, and ii) allowing secure multi- institutional collaborations via FL to improve these pre-trained models without sharing patient data, thereby overcoming legal, privacy, and data-ownership challenges. Successful completion of this project will lead to an easy-to-use potentially-translatable tool enabling easy, fast, objective, repeatable and accurate tumor segmentation, without requiring a computational background by the user, and while facilitating further analysis of tumor radio-phenotypes towards accelerating discovery.

抽象的： 由于其异质形状，范围和位置，实体瘤的准确分割是具有挑战性的 以及它们由医学成像的多样性引起的外观变化。手动注释很乏味， 容易误解，人为错误和观察者偏见。所有这些因素都阻碍了进一步的图像分析 要了解肿瘤放射性表型，预测临床结果并监测进展 模式。计算竞赛一直在寻求最佳的高级计算细分 用于特定异常的算法（ACSA），通过将多机构数据汇总并进行基准测试 来自国际团体的ACSA。沿着这些界限，我们一直在成功地领导 自2012年以来，国际脑肿瘤细分（BRAT）挑战迎接了公共可用的合并 来自19个机构的神经胶质瘤患者的542个多参数MRI扫描数据集。在总结的分析中 所有BRAT的结果，我们已经表明，尽管单个ACSA并没有表现优于黄金标准协议 在整个专家临床医生中，他们的融合确实优于整个精度和一致性 主题。为了更广泛地应用这些ACSA，我们在2017年创建了Brats算法存储库 由Brats参与者创建的单个ACSA的Docker容器可用。但是，这些融合 对于临床研究人员而言，ACSA仍然遥不可及，因为没有图形用户界面（GUI）来促进它，并且 执行此类算法需要用户实质性的计算背景。此外，虽然 小子等比赛表现出了承诺，由于需要汇总，他们无法轻易扩展 从多个机构到单个位置的患者数据通常面临法律，隐私和数据所有权 关注。这些问题激励分布式学习解决方案，其中数据始终保留在其内部 机构。我们一直在研究此类解决方案，以避免当前的多机构范式 合作，即数据共享，并考虑其潜在的多机构采用，在隐私方面 可伸缩性和性能，我们发现联合学习（FL）是最合适的。在佛罗里达州，每个机构 训练模型并与聚合服务器共享（无患者数据），然后整合机构 并行模型并分发了共识模型。在此提案中，我们专注于开放 来源联合肿瘤细分（FETS）平台，该平台以用户友好的GUI将以i的目标为目标 训练有素的各种ACSA及其融合的模型更接近临床专家，ii）允许安全的多种 通过FL的机构合作，以改善这些预训练的模型而无需共享患者数据，从而 克服法律，隐私和数据所有权挑战。成功完成该项目将导致 易于使用的潜在转换工具，可以轻松，快速，客观，可重复和准确的肿瘤 细分，不需要用户的计算背景，同时促进了进一步的分析 肿瘤射电型旨在加速发现。