AI项目可帮助诊断皮肤癌
2020年10月11日
A team of researchers and clinicians at the University of Dundee and NHS Tayside has received £150,000 in support of its ‘Deep learning for effective triaging of skin disease in the NHS’ project aiming to develop an AI system that can accurately distinguish between benign lesions and cancers. The funding was allocated under the £50 million Artificial Intelligence in Health and Care Awards announced by former Secretary of State for Health and Social Care Matt Hancock in September 2020
在早期检测到癌症资助的试点项目中，邓迪团队开发了一个深度学习系统，能够以最先进的精度检测常见的皮肤癌。这项初步工作使用了不代表常规NHS数据的选定和预处理图像数据集，研究人员现在将开发其技术以通过NHS Clinics的图像数据实现诊断准确性。
下一阶段将开始将学习AI系统集成到NHS Tayside内的日常临床护理中，以在现实环境中完善临床能力。
该大学计算系的项目负责人斯蒂芬·麦肯纳（Stephen McKenna）说：“我们的跨学科小组在凭借其福利方面具有独特的位置，可以利用和开发这项技术。”
“这一领域的成功将是逐渐的，从最常见的良性病变的临床决策支持等目标开始。皮肤疾病自然可以自动图像分析。可以轻松拍摄病变，然后在深度学习技术的帮助下进行分析。”
the team also consists of the University’s Professor Emanuele Trucco, a renowned expert in Computer Vision & Image Processing, Charlotte Proby, Professor of Dermatology at the School of Medicine, and Professor Colin Fleming, Consultant Dermatologist at Ninewells Hospital and Director of the Discovery Institute of Dermatology.
该项目是第一次公开比赛回合中从530多名申请人中选出的42个奖项之一。人工智能（AI）奖与NHSX和美国国家健康研究所（NIHR）合作，由加速访问协作（AAC）颁发。
更多信息在线的
