Intelligent and Personalised Risk Stratification and Early Diagnosis of Lung Cancer

肺癌是男性和女性中第二常见的癌症，并且具有非常差的预后，每年导致> 35，000例癌症相关死亡（每天近100例）。这是由于大多数癌症的诊断非常晚：近50%的肺癌病例仅在非常晚的IV期诊断，此时不存在治愈性治疗。肺癌给英国经济带来的年度成本估计约为24亿英镑，其中包括治疗和过早死亡的成本，病假以及朋友和家人的无薪护理成本。它使任何其他癌症的成本黯然失色，并继续带来重大的经济和医疗负担。英国目前还没有全国性的肺癌筛查计划，因为目前的检测被认为是不够的，而且不能超过与辐射暴露相关的筛查风险。我们医疗保健影响伙伴关系的愿景是为一种根本不同的方法铺平道路，在这种方法中，肺癌可以在被确定为肺癌高风险患者的早期阶段被发现：在专门从事肺部疾病的临床医生，医疗保健行业和计算成像/机器学习研究人员之间的密切三方合作伙伴关系中，我们将共同开发，测试和临床评估新的计算方法，用于在低剂量纵向CT中检测，分类和监测肺结节。具体来说，我们将在以前使用EPSRC资金开发的肺部配准框架中嵌入强大的机器学习方法。通过使用深度特征学习技术以及通过学习复杂的呼吸运动模式，我们将探索从大型带注释的肺部CT图像数据库到接受低剂量CT成像的高风险患者队列的迁移学习。通过这种合作伙伴关系，汇集了计算成像和深度学习的专业知识，专家临床医生和领先的CT制造商，我们的目标是实现个性化诊断的计算创新，以及改善患者管理的强大转化重点，有效地引领为未来英国肺癌筛查计划提供先进的医疗保健技术。

Lung cancer is the second most common cancer in both males and females, and has a very poor prognosis, causing >35,000 of cancer-related deaths each year (nearly 100 every day). This is due to the mostly very late-stage diagnosis of cancer: nearly 50% of all lung cancer cases are only diagnosed at very late Stage IV where no curative treatment exists. The annual cost of lung cancer to the UK economy is estimated to be around £2.4 billion, taking into account the cost of treatment and premature death, the cost to business of sick leave and of unpaid care by friends and family. It eclipses the cost of any other cancer, and continues to present a significant economic and healthcare burden. There is currently no national lung cancer screening programme in the UK, as current tests are deemed to be inadequate, and not outweighing risks associated with screening that involves radiation exposure.The vision for our Healthcare Impact Partnership is to pave the way for a fundamentally different approach in which lung cancer can be detected at an early stage in patients identified as being at high risk of developing lung cancer: In a close three-way partnership between clinicians specialising in lung disease, healthcare industry, and computational imaging/machine learning researchers, we will jointly develop, test and clinically evaluate new computational methods for detecting, classifying and monitoring lung nodules in low-dose longitudinal CT of patients identified of being at risk of developing lung cancer. Specifically, we will embed powerful machine learning methods within a lung registration framework that has been previous developed using EPSRC funding. Through the use of deep feature learning techniques as well as through learning complex respiratory motion patterns, we will explore transfer learning from large, annotated lung CT image databases to a high-risk patient cohort receiving low-dose CT imaging. Through this partnership, which brings together expertise in computational imaging and deep learning, expert clinicians and a leading CT manufacturer, we aim to achieve both computational innovations in personalised diagnostics, as well as a strong translational focus for improved patient management, effectively leading the way in providing advanced healthcare technologies for a future UK lung cancer screening programme.