Radiologist-Centered Artificial Intelligence (RCAI) for Lung Cancer Screening and Diagnosis

以放射科医生为中心的人工智能（RCAI）用于肺癌筛查和诊断

• 批准号: 10640048
• 负责人: Ulas Bagci
• 金额: $ 44.75万
• 依托单位: NORTHWESTERN UNIVERSITY AT CHICAGO
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-01 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10640048
• 关键词: Address; Adopted; Artificial Intelligence; Benign; Cancer Etiology; Cessation of life; Classification; Clinical; Cognitive; Collaborations; Communication; Computer-Assisted Diagnosis; Cues; Data; Detection; Devices; Diagnosis; Diagnostic; Diagnostic Procedure; Event; Feedback; Glass; Goals; Human; Image; Intuition; Label; Learning; Learning Module; Length; Location; Lung Neoplasms; Lung nodule; Mainstreaming; Malignant - descriptor; Malignant neoplasm of lung; Measurement; Measures; Methodology; Modeling; Nodule; Outcomes Research; Pattern; Pennsylvania; Performance; Phase; Probability; Process; Radiology Specialty; Reading; Reproducibility; Research; Scanning; Screening for cancer; Screening procedure; Second Opinions; Shapes; System; Techniques; Technology; Testing; Texture; Three-Dimensional Image; Time; Training; United States; United States National Institutes of Health; Universities; Update; Visual attention; Visualization; Woman; Work; X-Ray Computed Tomography; artificial intelligence algorithm; attenuation; calcification; career; clinical decision-making; clinical diagnostics; computer human interaction; cone-beam computed tomography; deep learning; deep learning algorithm; deep reinforcement learning; design; diagnostic accuracy; educational atmosphere; efficacy evaluation; efficacy validation; experience; experimental study; flexibility; gaze; improved; inattention; insight; learning algorithm; learning network; low dose computed tomography; lung cancer screening; men; mortality; novel; radiologist; sample fixation; satisfaction; screening; statistics; synergism; technological innovation; tool; tumor; virtual; visual search; visual tracking

PROJECT SUMMARY Lung cancer is the most common cause of cancer death in both men and women in the United States. Lung cancer screening with low-dose computed tomography (CT) has been shown to reduce lung cancer mortality. However, current radiology practice still suffers from (1) high rates of missed tumors and (2) imprecise lung nodule characterization (malignant vs. benign). Artificial intelligence (AI) based computer aided diagnosis (CAD) systems have helped radiologists to reduce the missed-tumor rates moderately, but have not been widely adopted for three key reasons: lack of efficiency, lack of real-time collaboration, and lack of interpretability. The overall goal of this proposal is to create radiologist-centered artificial intelligence algorithms that are both interpretable and collaborative and to demonstrate their improved efficacy via lung cancer screening experiments. The central hypothesis of this effort is that the creation of an AI based virtual cognitive assistant (VCA) will provide a better understanding of cognitive biases while offering interpretable feedback to radiologists for an improved screening experience with higher diagnostic accuracy, reproducibility, and efficiency. Specific aims of the proposal are three-fold. Aim 1: To develop an eye-tracking platform that offers a realistic radiology reading room experience while extracting gaze patterns from radiologists. This will facilitate addressing the problem of true collaboration between radiologists and CAD. Radiologists will perform their screening without any constraints (e.g., wearing glasses) while their gaze patterns and other human-computer interaction events are tracked, processed, and stored in real time. Aim 2: To develop an automated real-time collaborative system involving a developed VCA and the radiologist to synergistically improve detection and diagnostic performances. Using deep learning (DL) algorithms, the VCA will embody a powerful visual attention model to represent radiologists’ gaze, visual search, and fixation patterns, and will be composed of a detection component and a diagnostic component. A deep reinforcement learning algorithm will enable communication between the VCA and the radiologist. Lastly, a DL-based segmentation component will, on the fly, enable the VCA to derive and visualize quantitative measures (HU statistics, volume, long/short axes lengths, etc.) and overlay them along with the tumor classification label (benign/malignant) and its probability in real time. Aim 3: To evaluate the efficacy of the proposed VCA via lung cancer screening experiments involving six radiologists from two institutes (University of Pennsylvania and NIH) at different expertise levels. The proposed VCA is a first-of-a-kind-system to exploit the synergy between powerful DL technology and experts (humans) to attempt boost clinical diagnostic performance of radiologists, unlike passive DL techniques that learn from labeled data. The outcome of this research are expected to be transformative by providing deep insights for re-designing current CAD systems to truly collaborate with radiologists, instead of acting as second opinion tools for them or replacing them, and by ultimately further reducing lung cancer-related deaths.

项目总结 肺癌是美国男性和女性癌症死亡的最常见原因。肺 使用低剂量计算机断层扫描(CT)进行癌症筛查已被证明可以降低肺癌死亡率。 然而，目前的放射学实践仍然存在(1)高漏诊率和(2)肺不精确的问题。 结节特征(恶性与良性)。基于人工智能的计算机辅助诊断 系统已经帮助放射科医生适度降低了肿瘤漏检率，但还没有得到广泛应用。 采用该协议有三个关键原因：缺乏效率、缺乏实时协作和缺乏可解释性。这个 该提案的总体目标是创建以放射科医生为中心的人工智能算法，该算法既 可理解性和协作性，并通过肺癌筛查展示其改善的疗效 实验。这项工作的中心假设是，基于人工智能的虚拟认知助手的创建 (VCA)将更好地理解认知偏差，同时向放射科医生提供可解释的反馈 以更高的诊断准确性、重复性和效率改善筛查体验。 该提案的具体目标有三个方面。目标1：开发一个眼球跟踪平台，提供 逼真的放射学阅览室体验，同时从放射科医生提取凝视模式。这将促进 解决放射科医生和CAD之间的真正协作问题。放射科医生将履行他们的职责 没有任何限制(例如，戴眼镜)的筛选，同时他们的凝视模式和其他人机 实时跟踪、处理和存储交互事件。目标2：开发一种自动化的实时 包括开发的VCA和放射科医生的协作系统，以协同改进检测和 诊断性表演。使用深度学习(DL)算法，VCA将体现出强大的视觉注意力 表示放射科医生的凝视、视觉搜索和注视模式的模型，并将由检测 组件和诊断组件。深度强化学习算法将使通信成为可能 在VCA和放射科医生之间。最后，基于DL的分段组件将在运行中启用 VCA以导出和可视化量化测量(HU统计数据、体积、长/短轴长度等)和 将它们与肿瘤分类标签(良性/恶性)及其概率实时叠加。目标3： 通过六位放射科医生参与的肺癌筛查实验，评估拟议的VCA的有效性 来自两个不同专业水平的研究所(宾夕法尼亚大学和美国国立卫生研究院)。 拟议的VCA是一种首创的系统，旨在利用强大的下行技术和 专家(人类)试图提高放射科医生的临床诊断性能，而不是被动的DL技术 从有标签的数据中学习。这项研究的结果预计将是革命性的，因为它提供了深入的 重新设计当前的CAD系统，以真正与放射科医生协作，而不是充当第二个角色 为他们提供意见工具或取代他们，并最终进一步减少与肺癌相关的死亡。

项目成果

Machine learning-based prediction of MRI-induced power absorption in the tissue in patients with simplified deep brain stimulation lead models.

• DOI: 10.1109/temc.2021.3106872
• 发表时间: 2021-10
• 期刊: IEEE transactions on electromagnetic compatibility
• 影响因子: 2.1
• 作者: Vu J;Nguyen BT;Bhusal B;Baraboo J;Rosenow J;Bagci U;Bright MG;Golestanirad L
• 通讯作者: Golestanirad L

Adipose Tissue Segmentation in Unlabeled Abdomen MRI using Cross Modality Domain Adaptation.

使用交叉模态域的适应性适应未标记的腹部MRI中的脂肪组织分割。

• DOI: 10.1109/embc44109.2020.9176009
• 发表时间: 2020-07
• 期刊: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
• 作者: Masoudi S;Anwar SM;Harmon SA;Choyke PL;Turkbey B;Bagci U
• 通讯作者: Bagci U

Multi-Contrast MRI Segmentation Trained on Synthetic Images.

• DOI: 10.1109/embc48229.2022.9871119
• 发表时间: 2022-07
• 期刊: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

Deep Learning Based Staging of Bone Lesions From Computed Tomography Scans.

基于深度学习的计算机断层扫描骨病变分期。

• DOI: 10.1109/access.2021.3074051
• 发表时间: 2021
• 期刊: IEEE access : practical innovations, open solutions
• 作者: Masoudi S;Mehralivand S;Harmon SA;Lay N;Lindenberg L;Mena E;Pinto PA;Citrin DE;Gulley JL;Wood BJ;Dahut WL;Madan RA;Bagci U;Choyke PL;Turkbey B
• 通讯作者: Turkbey B

A machine learning-based prediction of the micropapillary/solid growth pattern in invasive lung adenocarcinoma with radiomics.

• DOI: 10.21037/tlcr-21-44
• 发表时间: 2021-03
• 期刊: Translational lung cancer research
• 影响因子: 4
• 作者: He B;Song Y;Wang L;Wang T;She Y;Hou L;Zhang L;Wu C;Babu BA;Bagci U;Waseem T;Yang M;Xie D;Chen C
• 通讯作者: Chen C