SCH: Blazing Data Trails: Digital Pathology and Specialist Attention
SCH:惊人的数据线索:数字病理学和专家关注
基本信息
- 批准号:2123920
- 负责人:
- 金额:$ 120万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2021
- 资助国家:美国
- 起止时间:2021-09-01 至 2025-08-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
When looking for cancer in clinical slides, pathologists move the focus of their attention around the slides in complex ways. These skilled shifts of attention are critical to how pathologists make expert diagnoses. This research program seeks to understand these shifts in attention in order to build an artificial intelligence (AI) system that that will be able to look at a slide the way a human pathologist would. Building an “AI expert pathologist,” however, requires a lot of data for it to learn, just like a pathologist needs years of training to become an expert. In order to provide the model with many examples of expert attention behavior, essential for it to make good predictions, the investigators will collect a large dataset of attention behavior from human pathologists. The human pathologists’ behavior will also serve as feedback to the AI model, enabling the AI system to model and reproduce how the human pathologists expertly sample the slides by moving their focus of attention. The investigators will also build AI-fueled tools that can predict where an expert would have focused their attention in a slide, thereby giving human pathologists feedback from the AI pathologist. The aim is to improve human accuracy of cancer diagnoses, which is paramount to improving the healthcare infrastructure of the country. The work also has the potential to improve histopathology training in medical personnel and to lead to next-generation AI models for cancer classification. The AI scientists trained through this project will be experts in building AI-tools that understand human expert performance and synergistically enhance it. A large database will be created of pathologist’s cursor-based movements during cancer interpretations, referred to as attention trajectories. These will be collected online from pathologists searching for metastatic cancer in Whole Slide Images (WSIs) of lymph nodes that were excised as part of cancer surgeries. For each WSI, one of four “diagnoses” will also be collected: negative, small, medium, or large metastases. Using a family of AI methods called imitation learning, the investigators will generate personalized as well as group prediction models of pathologist attention trajectories, applying Active Imitation Learning to real human behavior. Techniques for batch processing and pathologist-in-the-loop learning of attention trajectories will also be developed. An improvement in the efficiency and accuracy of pathology classification algorithms is expected through use of a multi-resolution approach that only processes small parts of WSIs by combining computational and human attention priors. Lastly, attention-based diagnostic aids that suggest areas to examine at higher magnification will be developed for human pathologists to use during slide interpretationThis award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
当在临床切片中寻找癌症时,病理学家以复杂的方式将注意力集中在切片上。 这些熟练的注意力转移对于病理学家如何做出专家诊断至关重要。该研究计划旨在了解这些注意力的转移,以建立一个人工智能(AI)系统,该系统将能够像人类病理学家一样查看幻灯片。然而,建立一个“人工智能专家病理学家”需要大量的数据来学习,就像病理学家需要多年的培训才能成为专家一样。为了给模型提供许多专家注意力行为的例子,研究人员将从人类病理学家那里收集大量的注意力行为数据集。人类病理学家的行为也将作为对AI模型的反馈,使AI系统能够模拟和再现人类病理学家如何通过移动他们的注意力焦点来熟练地对载玻片进行采样。研究人员还将构建人工智能驱动的工具,可以预测专家在幻灯片中将注意力集中在哪里,从而为人类病理学家提供来自人工智能病理学家的反馈。其目的是提高人类癌症诊断的准确性,这对改善该国的医疗保健基础设施至关重要。这项工作也有可能改善医务人员的组织病理学培训,并导致下一代癌症分类AI模型。通过该项目培训的人工智能科学家将成为构建人工智能工具的专家,这些工具可以理解人类专家的表现并协同增强。将创建一个大型数据库,其中包含病理学家在癌症解释期间基于光标的运动,称为注意力轨迹。这些将从病理学家在线收集,这些病理学家在作为癌症手术的一部分切除的淋巴结的全载玻片图像(WSI)中搜索转移性癌症。对于每个WSI,还将收集四种“诊断”之一:阴性、小、中或大转移。使用一系列称为模仿学习的人工智能方法,研究人员将生成病理学家注意力轨迹的个性化和群体预测模型,将主动模仿学习应用于真实的人类行为。还将开发用于注意力轨迹的批处理和病理学家在环学习的技术。预期通过使用多分辨率方法来提高病理分类算法的效率和准确性,所述多分辨率方法通过结合计算和人类注意力先验来仅处理小部分WSI。最后,基于注意力的诊断辅助工具,建议在更高的放大倍率下检查的区域,将被开发用于人类病理学家在幻灯片解释期间使用。该奖项反映了NSF的法定使命,并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。
项目成果
期刊论文数量(22)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Token Sparsification for Faster Medical Image Segmentation
- DOI:10.48550/arxiv.2303.06522
- 发表时间:2023-03
- 期刊:
- 影响因子:0
- 作者:Lei Zhou;Huidong Liu;Joseph Bae;Junjun He;D. Samaras;P. Prasanna
- 通讯作者:Lei Zhou;Huidong Liu;Joseph Bae;Junjun He;D. Samaras;P. Prasanna
Using Generated Object Reconstructions to Study Object-based Attention
使用生成的对象重建来研究基于对象的注意力
- DOI:10.32470/ccn.2023.1685-0
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Ahn S
- 通讯作者:Ahn S
Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images
通过多重免疫组织化学图像的反转调节进行无监督染色分解
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Shahira Abousamra, Danielle Fassler
- 通讯作者:Shahira Abousamra, Danielle Fassler
Gigapixel Whole-Slide Images Classification using Locally Supervised Learning
- DOI:10.1007/978-3-031-16434-7_19
- 发表时间:2022-07
- 期刊:
- 影响因子:0
- 作者:Jingwei Zhang;Xin Zhang;Ke Ma;Rajarsi R. Gupta;J. Saltz;M. Vakalopoulou;D. Samaras
- 通讯作者:Jingwei Zhang;Xin Zhang;Ke Ma;Rajarsi R. Gupta;J. Saltz;M. Vakalopoulou;D. Samaras
Topology-Guided Multi-Class Cell Context Generation for Digital Pathology
用于数字病理学的拓扑引导多类细胞上下文生成
- DOI:10.1109/cvpr52729.2023.00324
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Abousamra, Shahira;Gupta, Rajarsi;Kurc, Tahsin;Samaras, Dimitris;Saltz, Joel;Chen, Chao
- 通讯作者:Chen, Chao
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Dimitrios Samaras其他文献
Modular supervisory control for push-out games with mobile robots
移动机器人推出游戏的模块化监控
- DOI:
10.1063/5.0182631 - 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
N. Kouvakas;F. Koumboulis;D. Fragkoulis;Dimitrios Samaras - 通讯作者:
Dimitrios Samaras
The impact of steatotic liver disease on coronary artery disease through changes in the plasma lipidome
- DOI:
10.1038/s41598-024-73406-8 - 发表时间:
2024-09-27 - 期刊:
- 影响因子:3.900
- 作者:
Elias Björnson;Dimitrios Samaras;Malin Levin;Fredrik Bäckhed;Göran Bergström;Anders Gummesson - 通讯作者:
Anders Gummesson
Cauliflower Bowel: A Tumor-Induced Mesenteric Retraction
- DOI:
10.1097/maj.0b013e318270a1dc - 发表时间:
2014-04-01 - 期刊:
- 影响因子:
- 作者:
Dimitrios Samaras;Nikolaos Samaras;Olivier Ferlay;Maria-Aikaterini Papadopoulou;Claude Pichard - 通讯作者:
Claude Pichard
A modular programmable and linear charge pump with low current mismatch
- DOI:
10.1007/s10470-023-02183-7 - 发表时间:
2023-09-30 - 期刊:
- 影响因子:1.400
- 作者:
Dimitrios Samaras;Alkiviadis Hatzopoulos - 通讯作者:
Alkiviadis Hatzopoulos
Dimitrios Samaras的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Dimitrios Samaras', 18)}}的其他基金
RI: Medium: Information Super-Resolution for Very Large Images
RI:中:超大图像的信息超分辨率
- 批准号:
2212046 - 财政年份:2022
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
相似海外基金
Blazing the Trail for STEM Teachers: A Noyce Capacity Building Project
为 STEM 教师开辟道路:诺伊斯能力建设项目
- 批准号:
1758227 - 财政年份:2018
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Blazing to Biomedical Careers II (BBC II)
开拓生物医学职业 II (BBC II)
- 批准号:
10201632 - 财政年份:2014
- 资助金额:
$ 120万 - 项目类别:
"Blazing Galactic Trails " Camp Kit and Digital Activity (Working Title)
“炽热银河轨迹”营地套件和数字活动(暂定名称)
- 批准号:
312983-2004 - 财政年份:2004
- 资助金额:
$ 120万 - 项目类别:
PromoScience