M-ISIC: A Multimodal Open-Source International Skin Imaging Collaboration Informatics Platform for Automated Skin Cancer Detection

M-ISIC：用于自动皮肤癌检测的多模式开源国际皮肤成像协作信息学平台

• 批准号: 10689201
• 负责人: Kivanc Kose
• 金额: $ 81.07万
• 依托单位: SLOAN-KETTERING INST CAN RESEARCH
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2027-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10689201
• 关键词: Address; Algorithms; Archives; Artificial Intelligence; Automation; Boston; Cancer Detection; Clinical; Clinical Distribution; Clinical Trials; Collaborations; Complex; Computer Vision Systems; Computer software; Custom; Data; Data Set; Data Sources; Database Management Systems; Dermatology; Detection; Development; Devices; Diagnosis; Diagnostic; Disparate; Early Diagnosis; Education; Evaluation; Experimental Models; Goals; Health protection; Human; Image; Informatics; Ingestion; International; Intervention; Label; Link; Machine Learning; Malignant Neoplasms; Manuals; Medical Education; Metadata; Methods; Modality; Modeling; Morbidity - disease rate; Morphologic artifacts; Multimodal Imaging; Online Systems; Operative Surgical Procedures; Organizational Efficiency; Participant; Pathology; Performance; Persons; Plug-in; Process; Quality Control; Radiology Specialty; Research; Resolution; Retrieval; Screening for Skin Cancer; Skin; Skin Cancer; Sorting; Tattooing; Techniques; Testing; Training and Education; United States; Visual; Visualization; Work; algorithm development; analysis pipeline; archive data; artificial intelligence algorithm; cancer type; clinical application; clinical translation; data curation; data ingestion; data integration; data quality; data wrangling; design; diagnostic platform; digital technology; flexibility; image archival system; image registration; improved; informatics tool; large datasets; melanoma; microscopic imaging; mortality; multidimensional data; multimodal data; multimodality; next generation; open source; open source tool; prevent; primary care clinician; quality assurance; reflectance confocal microscopy; research clinical testing; response; success; teledermatology; tool

ABSTRACT Skin cancer is the most common type of cancer in the United States. It is critical to detect it early as skin cancers, especially melanoma, can be cured by surgery alone if detected early. As digital technology improves, skin cancer detection, and especially automated skin cancer detection, is increasingly being performed over images either in person or remotely via teledermatology. While artificial intelligence (AI) for skin cancer detection exceeds human performance on static images, algorithm performance on representative, multimodal data is still underdeveloped due to data collected piecemeal with different devices, without consistent image acquisition standards or automated registration. A well-curated dataset of annotated skin images helps meet a unique need beyond machine learning, as primary care clinicians also require expertly annotated images for education and training. We will overcome the lack of imaging standards and disparate data sources problematic in dermatology imaging by developing automated ingestion, organization, registration, and curation pipeline to improve AI for skin cancer detection. The International Skin Imaging Collaboration (ISIC) Archive includes over 2,500 citations, 156,000 images, 100 daily users, and 5 AI grand challenges with over 3,500 participants. The ISIC archive is built upon the open- source, NCI- supported, open-source web-based data management platform, Girder. The Girder platform is highly flexible, and has been extended to multiple applications (e.g., pathology, radiology). The flexibility of the Girder platform will enable us to address four major barriers that prevent our ability to efficiently ingest, host and serve large amounts of multidimensional data at the scale of non-medical image repositories (e.g. ImageNet): (1) need for laborious expert data curation and quality assurance review for protected health information, imaging artifacts, and incorrect labels (SA1.1); (2) limited metadata without content-based features creating cumbersome image retrieval (SA1.2); (3) lack of multimodal viewing capabilities (SA2); and (4) inadequate integration to existing AI and annotation software, preventing flexible, hypothesis-driven experimentation (SA3). The proposed informatics project aimed at data ingestion, multimodal visualization, and organization through ML and computer vision-based automation build on the initial success of the International Skin Imaging Collaboration (ISIC) Archive and the Girder platform upon which it is built. They will enable scaling of the Archive to millions of images, enabling multimodal experimentation with registered reflectance confocal microscopy images, and nimbly facilitate AI and translational experimentation for improved skin cancer detection.

摘要 皮肤癌是美国最常见的癌症类型。关键是要及早发现， 癌症，特别是黑色素瘤，如果早期发现，可以通过手术治愈。随着数字技术的进步， 皮肤癌检测，尤其是自动化皮肤癌检测， 图像，无论是在人或远程通过teledermatology。虽然用于皮肤癌的人工智能（AI） 静态图像上的检测性能超过人类，代表性多模态图像上的算法性能 由于使用不同设备收集的数据是零碎的，没有一致的图像， 收购标准或自动登记。一个精心策划的带注释的皮肤图像数据集有助于满足 除了机器学习之外，初级保健临床医生还需要专业注释的图像， 教育培训我们将克服成像标准的缺乏和数据源的分散 通过开发自动摄取、组织、配准和策展， 用于改善皮肤癌检测的AI管道。 国际皮肤成像合作组织（ISIC）档案包括超过2，500次引用，156，000张图像，100张照片，100张照片，100张照片，100张照片。 每日用户，以及5个AI大挑战，超过3，500名参与者。ISIC档案建立在开放的基础上- 源，NCI支持的，开源的基于Web的数据管理平台，梁。梁平台是 高度灵活，并且已经扩展到多个应用（例如，病理学、放射学）。 梁平台的灵活性将使我们能够解决四个主要障碍， 以非医学图像的规模有效地摄取、托管和服务大量多维数据 存储库（例如ImageNet）：（1）需要费力的专家数据管理和质量保证审查， 受保护的健康信息、成像伪影和错误标签（SA1.1）;（2）有限的元数据， 基于内容的功能创建繁琐的图像检索（SA1.2）;（3）缺乏多模态查看 能力（SA 2）;以及（4）与现有AI和注释软件的集成不足，阻碍了灵活， 假设驱动实验（SA 3）。 拟议的信息学项目旨在通过以下方式获取数据、实现多模态可视化和组织 ML和基于计算机视觉的自动化建立在国际皮肤成像的初步成功基础上 协作（ISIC）档案和它所建立的梁平台。它们将使 存档数百万张图像，通过配准反射共焦实现多模式实验 显微镜图像，并灵活地促进AI和翻译实验，以改善皮肤癌 侦测