Can deep-learning algorithms identify genetic mutations or aberrant cellular signalling pathways from medical images?

深度学习算法能否从医学图像中识别基因突变或异常细胞信号通路？

• 批准号: 531111-2018
• 负责人: Lepage, Martin
• 金额: $ 10.44万
• 依托单位: Université de Sherbrooke
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2018
• 资助国家: 加拿大
• 起止时间: 2018-01-01 至 2019-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=657236
• 关键词: deep; learning; algorithms; identify; genetic

Our project will determine if cancer-related genetic mutations found in tumours can be detected using medical**imaging. Tumours arise from a series of genetic errors, and these determine much of the behaviour of a tumour,**including its aggressiveness and its response to a treatment. In day-to-day medical imaging, once a patient has**undergone a medical scan, a specialist will look at the images and provide a diagnosis (e.g., liver cancer).**Sometimes, a biopsy (tumour sample) is acquired to better determine the subtype of cancer. Our project aims at**assisting physicians by providing them with additional information extracted using artificial intelligence and**advanced computer software. These are already known to be superior to humans in finding and quantifying**subtle image characteristics. We hypothesize that these image characteristics could be predictive of the cancer**subtype and its optimal treatment. First, this software has to be trained to recognize mutations. Because human**tumours vary a lot, it is difficult to differentiate visual characteristics caused by an individual inherent**variability from those caused by the mutation. To overcome this, we will use genetically engineered mouse**models - these will have specific mutations that will result in cancer but with limited variability between**animals. This will allow us to train a software to recognize tumours that have specific mutations. If successful,**our project will ultimately lead to software tools with capabilities similar to biopsies, and better and less**invasive management of cancer.

我们的项目将确定是否可以使用医学成像检测肿瘤中发现的癌症相关基因突变。肿瘤由一系列遗传错误引起，这些错误决定了肿瘤的大部分行为，** 包括其侵袭性和对治疗的反应。在日常医学成像中，一旦患者接受了医学扫描，专家将查看图像并提供诊断（例如，肝癌）。**有时，获取活检（肿瘤样本）以更好地确定癌症的亚型。我们的项目旨在 ** 通过为医生提供使用人工智能和 ** 先进计算机软件提取的额外信息来协助他们。在发现和量化 ** 微妙的图像特征方面，这些已经被认为是优于人类的上级。我们假设这些图像特征可以预测癌症 ** 亚型及其最佳治疗。首先，这个软件必须经过训练才能识别突变。由于人类的 ** 肿瘤变化很大，很难区分由个体固有的 ** 变异性引起的视觉特征和由突变引起的视觉特征。为了克服这一点，我们将使用基因工程小鼠 ** 模型-这些模型将具有导致癌症的特定突变，但 ** 动物之间的变异性有限。这将使我们能够训练一个软件来识别具有特定突变的肿瘤。如果成功，** 我们的项目将最终导致软件工具具有类似于活组织检查的功能，以及更好和更少的癌症侵入性管理。