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: $ 8.13万
• 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: 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=698046
• 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.

我们的项目将确定肿瘤中发现的与癌症相关的基因突变是否可以用医学方法检测出来。 显像肿瘤是由一系列遗传错误引起的，这些错误决定了肿瘤的大部分行为， 包括它的攻击性和它对治疗的反应。在日常医学成像中，一旦患者 在进行医学扫描时，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 通过向医生提供使用人工智能提取的额外信息来帮助他们， 先进的计算机软件。这些已经被认为是上级人类在寻找和量化 微妙的图像特征。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。因为人类 肿瘤变化很大，很难区分由个体固有的视觉特征引起的 由突变引起的变异。为了克服这一点，我们将使用基因工程小鼠 模型-这些将有特定的突变，将导致癌症，但有限的变异之间 动物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的功能类似于活检，更好，更少， 癌症的侵入性管理。