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.

项目摘要 肺癌是美国男性和女性癌症死亡的最常见原因。肺 低剂量计算机断层扫描（CT）癌症筛查已显示可降低肺癌死亡率。 但是，当前的放射学实践仍然患有（1）遗漏肿瘤的高率和（2）隐含的肺 结节表征（恶性与良性）。基于人工智能（AI）的计算机辅助诊断（CAD） 系统已帮助放射科医生中度降低错失率，但并未被广泛降低 采用三个关键原因：缺乏效率，缺乏实时协作以及缺乏解释性。 该建议的总体目标是创建以放射科医生为中心的人工智能算法 可解释和协作，并通过肺癌筛查来证明其提高效率 实验。这项工作的中心假设是创建基于AI的虚拟认知助手 （VCA）将更好地理解认知偏见，同时向放射科医生提供可解释的反馈 为了提高诊断准确性，可重复性和效率，可以提高筛查经验。 该提案的具体目的是三倍。目的1：开发一个提供眼睛追踪平台，提供一个 现实的放射学阅读室经验，同时从放射科医生那里提取凝视模式。这将准备 解决了放射科和CAD之间真正合作的问题。放射科医生将执行他们的 筛选没有任何约束（例如，戴眼镜），而他们的凝视图案和其他人类计算机 相互作用事件被实时跟踪，处理和存储。目标2：开发自动实时 涉及开发VCA和放射科医生的协作系统可以协同改善检测和 诊断性能。使用深度学习（DL）算法，VCA将体现强大的视觉关注 代表放射科医生的目光，视觉搜索和固定模式的模型，并将由检测组成 组件和诊断组件。深厚的增强学习算法将实现沟通 在VCA和放射科医生之间。最后，基于DL的分割组件将即时启用 VCA得出和可视化定量措施（HU统计，体积，长轴长等）和 将它们与肿瘤分类标签（良性/恶性）及其实时概率叠加在一起。目标3： 通过涉及六名放射科医生的肺癌筛查实验评估拟议VCA的效率 来自不同专家级别的两个机构（宾夕法尼亚大学和NIH大学）。 拟议的VCA是一个旨在利用强大DL技术和 与被动DL技术不同，专家（人类）尝试增强放射科医生的临床诊断性能 从标记的数据中学习。预计这项研究的结果将通过提供深刻的方式进行变革 重新设计当前CAD系统以真正与放射科医生合作的见解，而不是作为第二 为他们提供意见工具或更换它们，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.

• 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

Musculoskeletal MR Image Segmentation with Artificial Intelligence.

利用人工智能进行肌肉骨骼 MR 图像分割。

• DOI: 10.1016/j.yacr.2022.04.010
• 发表时间: 2022
• 期刊: Advances in clinical radiology
• 作者: Keles,Elif;Irmakci,Ismail;Bagci,Ulas
• 通讯作者: Bagci,Ulas