Reliable AI for Medical Image Reconstruction

用于医学图像重建的可靠人工智能

• 批准号: 10687707
• 负责人: Mahdi Soltanolkotabi
• 金额: $ 143.44万
• 依托单位: UNIVERSITY OF SOUTHERN CALIFORNIA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-20 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10687707
• 关键词: Acceleration; Address; Algorithms; Anatomy; Architecture; Brachial Plexus Neuropathies; Brachial plexus structure; Chest; Chondrite; Collaborations; Communities; Computer Vision Systems; Computer software; Data; Data Collection; Data Set; Devices; Discipline; Disease; Emergency Situation; Healthcare; Hospitals; Intelligence; Knee; Ligaments; Machine Learning; Magnetic Resonance; Magnetic Resonance Imaging; Magnetism; Medical Imaging; Modernization; Morphologic artifacts; Motion; Musculoskeletal; Natural Language Processing; Noise; Pathology; Patients; Privatization; Research; Scanning; Shoulder; System; Testing; Time; Training; Universities; Upper Extremity; Weight; Wrist; accurate diagnosis; clinical diagnostics; cost; deep learning; deep neural network; diagnostic accuracy; diagnostic tool; image reconstruction; imaging modality; improved; intelligent algorithm; meniscal tear; nerve supply; novel; novel diagnostics; open source; operation; point of care; reconstruction; success; trustworthiness

Project Abstract/Summary Deep neural networks have enjoyed wide empirical success in a variety of disciplines ranging from computer vision to natural language processing. However, in medical imaging such as Magnetic Resonance Imaging (MRI), a variety of challenges including lack of high-quality training data, lack of robustness to corruption/outliers and distribution shifts between train and test time as well as documented lack of reliability and trustworthiness impede the wide use and adaptation of AI. This project develops new deep learning-based architectures, algorithms and training mechanisms that that deals with these challenges creating a new toolkit for MRI reconstruction that is robust, reliable, trustworthy yet can be trained collaboratively and privately across multiple hospital systems. Using this new toolkit the project addresses three major MRI reconstruction challenges (1) reducing acquisition time via higher acceleration factors, (2) enabling high quality reconstruction even with low-intensity magnetic elds, and (3) dealing with motion artifacts. In collaboration with Musculoskeletal (MSK) sections of a few major universities, this project also involves gathering, curating and releasing new datasets and open source reconstruction software aimed at addressing these key challenges. This will also help attract further research from the machine learning/AI community to further improve this important medical imaging modality. Healthcare Impact: This project will signi cantly enhance MRI which is an important diagnostic tool. (1) reductions in the acquisition time will simultaneously increases both the accuracy of diagnosis and patient comfort. (2) the reduction of noise/nonlinear artifacts caused by low- eld scanners will lead to a reduction in the size and weight of the MR scanner. This may eventually allow MRI to be used at point of care or for emergency scenarios at the bedside and also open up a plethora of new use cases. (3) reductions in the motion artifacts increases the accuracy of diagnosis for a variety of new diseases and conditions enabling new diagnostic use cases for MRI. Also, (1) allows more patients to receive a scan using the same machine and (2) lowers the cost of the magnet and the space of operation of MR scanners. This can signi cantly reduce patient cost and thus increase the access to this diagnostically important medical imaging modality. Furthermore, the focus on MSK data collection can greatly facilitate accurate diagnosis of pathology such as subtle meniscal tears or chondrites in the knee, labral and rotator cu tears in the shoulder, and ligament out tears in the wrist. The particular focus on brachial plexopathy is also expected to have signi cant healthcare bene ts as the briachial plexus is an intricate anatomic structure with the critical function of providing innervation to the upper extremity, shoulder, and upper chest. The brachial plexus MRI study will enable great detail of this intricate anatomical structure with low/conventional eld strengths which is of paramount importance in patient treatment, especially in traumatic settings.

项目摘要/总结 深度神经网络在计算机等各个学科中都取得了广泛的经验成功 视觉到自然语言处理。然而，在磁共振成像 (MRI) 等医学成像中， 各种挑战，包括缺乏高质量的培训数据、缺乏对腐败/异常值的稳健性以及 训练和测试时间之间的分配变化以及记录的可靠性和可信度的缺乏阻碍 人工智能的广泛使用和适应。该项目开发了新的基于深度学习的架构、算法和 应对这些挑战的培训机制创建了一个新的 MRI 重建工具包 强大、可靠、值得信赖，但可以在多个医院系统中进行协作和私下培训。 使用这个新工具包，该项目解决了 MRI 重建的三个主要挑战 (1) 减少采集 通过更高的加速因子缩短时间，(2) 即使在低强度磁场下也能实现高质量重建 领域，以及（3）处理运动伪影。与一些组织的肌肉骨骼 (MSK) 部门合作 主要大学，该项目还涉及收集、整理和发布新的数据集和开源 重建软件旨在解决这些关键挑战。这也将有助于吸引更多的研究 机器学习/人工智能社区进一步改进这一重要的医学成像模式。 医疗保健影响：该项目将显着增强 MRI，这是一种重要的诊断工具。 (1) 采集时间的减少将同时提高诊断的准确性和患者的舒适度。 (2) 低场扫描仪引起的噪声/非线性伪影的减少将导致尺寸和尺寸的减小 MR 扫描仪的重量。这最终可能允许 MRI 在护理点或紧急情况下使用 在床边，还开辟了大量新的用例。 (3) 运动伪影的减少增加了 各种新疾病和病症的诊断准确性，为 MRI 提供新的诊断用例。还， (1) 允许更多患者使用同一台机器接受扫描，(2) 降低磁铁和扫描仪的成本 MR 扫描仪的操作空间。这可以显着降低患者费用，从而增加获得此服务的机会 具有重要诊断意义的医学成像方式。此外，关注 MSK 数据收集可以极大地促进 促进病理学的准确诊断，例如膝盖、盂唇和旋转肌中细微的半月板撕裂或球粒陨石 cu 肩膀上有泪水，韧带上有手腕上的泪水。对臂丛神经病的特别关注也 由于臂丛神经是一个复杂的解剖结构，预计将具有显着的医疗保健益处 为上肢、肩部和上胸部提供神经支配的关键功能。臂丛神经 MRI 研究将能够通过低/传统场强详细了解这种复杂的解剖结构 这对于患者治疗至关重要，尤其是在创伤环境中。