Combining Knowledge And Data Driven Approaches to Inverse Imaging Problems

结合知识和数据驱动的方法来解决逆向成像问题

• 批准号: EP/V029428/1
• 负责人: Carola-Bibiane Schönlieb
• 金额: $ 158.04万
• 依托单位: University of Cambridge
• 依托单位国家: 英国
• 项目类别: Fellowship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FV029428%2F1
• 关键词: Combining; Knowledge; Data; Driven; Approaches

Imaging plays an important role in many applications in the natural sciences, medicine and the life sciences, as well as in engineering and industrial applications. An example is an MRI image of a brain used by a physician to detect a brain tumour such as glioblastoma. At the core of many imaging applications is an inverse problem, i.e. the mathematical problem of reconstructing the image from data produced by the imaging machine, for example the MRI machine. Such inverse imaging problems have been approached for many years in a "knowledge-driven" way, using information about the device and the imaging procedure. However, the knowledge-driven models cannot always be solved, are computationally very expensive, or deliver suboptimal images.In recent years, new "data-driven" methods, which use past examples of successfully reconstructed images together with the data that produced them, have been shown to produce some impressive results in image reconstruction. The problem with such data-driven methods, however, is that currently they do not have "mathematical guarantees", in other words one cannot state the degree to which the results are reliable. They also have the property that even small deviations in the data could result in large differences in the results. This clearly could have devastating implications for many applications.In this proposal, we will develop a new hybrid approach that combines the best of knowledge-driven and data-driven methods for inverse imaging problems, crucially providing the mathematical guarantees essential to being able to use the methods in real-world applications. Once the challenging task of developing these mathematical methods is achieved, we will apply this learning to produce an imaging pipeline that draws into a single step the stages of the imaging process, thus optimising the process further. We will apply the new methods to real-world applications. For example, using the data driven mathematical methods developed in the project and working closely with the Radiology Department, we will create an end-to-end workflow where multi-modal image acquisition, reconstruction, segmentation and image analyses are performed jointly and optimised for the end task of real time treatment response assessment in patients with metastatic cancer.

成像在自然科学、医学和生命科学以及工程和工业应用中都扮演着重要的角色。一个例子是医生用脑部的核磁共振图像来检测脑瘤，如胶质母细胞瘤。许多成像应用的核心是逆问题，即从成像机器(例如，MRI机器)产生的数据重建图像的数学问题。这种逆成像问题多年来一直是以“知识驱动”的方式，利用有关设备和成像过程的信息来解决的。然而，知识驱动的模型并不总是能够解决的，计算非常昂贵，或者提供次优的图像。近年来，新的数据驱动的方法被证明在图像重建中产生了一些令人印象深刻的结果，这些方法使用过去成功重建图像的例子和产生它们的数据。然而，这种数据驱动的方法的问题是，目前它们没有“数学保证”，换句话说，人们无法说明结果的可靠程度。它们还具有这样一种特性，即即使数据中的微小偏差也可能导致结果的巨大差异。在这项建议中，我们将开发一种新的混合方法，将知识驱动和数据驱动的最佳方法结合起来用于逆成像问题，关键是提供关键的数学保证，以便能够在现实世界的应用中使用这些方法。一旦完成了开发这些数学方法的具有挑战性的任务，我们将应用这一学习来产生一种成像管道，将成像过程的各个阶段集中到一个步骤中，从而进一步优化该过程。我们将把新方法应用到实际应用中。例如，使用项目中开发的数据驱动的数学方法，并与放射科密切合作，我们将创建一个端到端的工作流程，其中联合执行多模式图像采集、重建、分割和图像分析，并针对转移性癌症患者的实时治疗反应评估的最终任务进行优化。

项目成果

Machine learning for COVID-19 diagnosis and prognostication: lessons for amplifying the signal whilst reducing the noise

用于 COVID-19 诊断和预测的机器学习：放大信号同时减少噪音的经验教训

• DOI: 10.17863/cam.65566
• 发表时间: 2021
• 作者: Driggs D

Spectral decomposition of atomic structures in heterogeneous cryo-EM

异质冷冻电镜中原子结构的光谱分解

• DOI: 10.1088/1361-6420/acb2ba
• 发表时间: 2023
• 期刊: Inverse Problems
• 影响因子: 2.1
• 作者: Esteve-Yagüe C

Imaging With Equivariant Deep Learning: From unrolled network design to fully unsupervised learning

• DOI: 10.1109/msp.2022.3205430
• 发表时间: 2022-09
• 期刊: IEEE Signal Processing Magazine
• 影响因子: 14.9
• 作者: Dongdong Chen;M. Davies;Matthias Joachim Ehrhardt;C. Schönlieb;Ferdia Sherry;Julián Tachella

Medical Image Computing and Computer Assisted Intervention - MICCAI 2022 - 25th International Conference, Singapore, September 18-22, 2022, Proceedings, Part III

医学图像计算和计算机辅助干预 - MICCAI 2022 - 第 25 届国际会议，新加坡，2022 年 9 月 18-22 日，会议记录，第三部分

• DOI: 10.1007/978-3-031-16437-8_69
• 发表时间: 2022
• 作者: Aviles-Rivero A

Deep learning-based Segmentation of Multi-site Disease in Ovarian Cancer

基于深度学习的卵巢癌多部位疾病分割

• DOI: 10.17863/cam.93840
• 发表时间: 2023
• 作者: Buddenkotte T