Prediction of Immunotherapy Response with Geometric Deep Learning in Medical Imaging

利用医学影像中的几何深度学习预测免疫治疗反应

• 批准号: RGPIN-2020-06558
• 负责人: Kadoury, Samuel
• 金额: $ 3.5万
• 依托单位: École Polytechnique de Montréal
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=718387
• 关键词: Prediction; Immunotherapy; Response; Geometric; Deep

Cancer patients have limited treatment options. Immunotherapy is a promising strategy using the primary function of the immune system to rid the body cancer cells, showing long-term benefits for curing cancer. However, clinicians still do not have a reliable imaging biomarker that can reliably identify patients responding to immunotherapy prior to treatment. Image biomarkers can serve as a non-invasive alternative to characterize the spatial heterogeneity of tumors, but lack the statistical framework to predict therapy outcomes. Deep learning on graphs or manifolds, denoted as geometric deep learning, has recently gained interest for medical imaging problems, specifically in oncology and immunotherapy. They demonstrated the potential to process non-Euclidean domains, while addressing several challenges such as limited and unbalanced datasets. The global objective is to develop image-driven predictive tools for immunotherapy response, based on novel concepts in geometric deep learning. The proposed methods will synthesize complex and multi-modal sources (CT images and clinical data) described with discriminative graphs, capturing underlying trends from longitudinal patient datasets. It will also allow the interpretation of deep features to capture drug effects on outcomes, as well recover spatiotemporal latent representations specific to immune phenotypes. To achieve this global objective, the main objectives are: (1) Develop a discriminative graph structure trained with a manifold-regularized deep neural network to predict responsive patients; (2) Parameterize the topology of the latent space with unsupervised domain adaptation to quantify therapeutic effects on outcomes; (3) Exploit concepts in Riemannian geometry and recurrent networks to create a prediction model for treatment response from spatiotemporal deep features; (4) Apply and validate the proposed methods on cancer patient datasets, comparing predicted results with actual outcomes. Based on our recent work on geometric deep learning, the proposal's contributions lie in a predictive platform generating representative knowledge to discover predictive biomarkers of the immune system response and tumor evolution, aimed for diagnosis and therapy. This research proposal will have a significant impact in computational medical imaging, as the geometric deep learning framework will allow to uncover domain specific relationships for cancer characterization. It will synthesize large heterogeneous sets of medical images acquired longitudinally and provide a comprehensive portrait of cancerous tumor evolution. Finally, it will propose new functionalities to disentangle complex structures into joint subsets, as well as adapting to different manifold topologies obtained with deep learning. From a clinical perspective, these developments will contribute insights and indications for early detection of cancer and predictors of therapy outcomes, as well as reliable forecasting tools in medicine.

癌症患者的治疗选择有限。免疫疗法是一种有前途的策略，利用免疫系统的主要功能消除了身体癌细胞，显示出长期治愈癌症的益处。但是，临床医生仍然没有可靠的成像生物标志物，可以在治疗前可靠地识别出对免疫疗法反应的患者。图像生物标志物可以作为表征肿瘤空间异质性的一种非侵入性替代方法，但缺乏预测治疗结果的统计框架。 最近对图形或流形的深度学习是几何深度学习，最近对医学成像问题，特别是在肿瘤学和免疫疗法中引起了兴趣。他们证明了处理非欧国人领域的潜力，同时解决了有限和不平衡数据集等几个挑战。 全球目标是根据几何深度学习的新概念开发以图像为驱动的预测工具来进行免疫疗法反应。所提出的方法将用判别图综合复合和多模式源（CT图像和临床数据），从而捕获纵向患者数据集的潜在趋势。它还将允许对深层特征的解释来捕获药物对结果的影响，并恢复针对免疫表型特有的时空潜在表示。 为了实现这一全球目标，主要目标是：（1）开发一种歧视性图结构，该图形结构训练有歧管的深度神经网络，以预测反应敏感的患者； （2）对潜在空间的拓扑进行参数化，并具有无监督的域适应性，以量化对结局的治疗作用； （3）利用Riemannian几何形状和经常性网络中的概念创建一个预测模型，以从时空深度特征进行治疗响应； （4）在癌症患者数据集上应用并验证提出的方法，将预测结果与实际结果进行比较。根据我们最近的几何深度学习工作，该提案的贡献在于一个预测平台，该平台产生了代表性知识，以发现免疫系统反应和肿瘤进化的预测生物标志物，旨在诊断和治疗。 该研究建议将对计算医学成像产生重大影响，因为几何深度学习框架将使癌症表征的特定关系具有特定的关系。它将合成大量的异质医学图像集，并提供癌性肿瘤进化的全面肖像。最后，它将提出新的功能，以将复杂的结构分解为联合子集，并适应通过深度学习获得的不同歧管拓扑结构。从临床角度来看，这些发展将为癌症和治疗结果预测的早期发现以及医学上可靠的预测工具提供见解和指示。