《皮肤癌的AI诊断课件.pptx》由会员分享，可在线阅读，更多相关《皮肤癌的AI诊断课件.pptx（39页珍藏版）》请在三一办公上搜索。
1、由一篇Nature引发的思考,PPT制作、主讲 朱明哲文献查找、翻译、Word文档制作 李卓,是什么研究成果震撼了生物医学界？,生物医学传感领域的新突破,百度搜索引擎都膜拜的第一作者,荣获斯坦福大学AI领域的理学博士并修德克萨斯大学奥斯汀分校电子计算机工程及纯数学双专业,Dermatologist-level classification of skin cancerwith deep neural networks,利用深度神经网络，进行皮肤科专家级别的皮肤癌诊断,这项研究成果被x-mol官网评为2017年2月全球科学技术十大突破之五,这种所谓的深度神经网络就是近年来经常提及 但又充满神秘的
2、,人工智能 (Artificial Intelligence),人工智能我们该如何理解？,从数学上看,深度神经网络(Deep Neural Networks),卷积神经网络(Convolutional Neural Networks),浅析CNNs,Logistic回归模型,浅析CNNs,卷积的处理看起来使得问题复杂了，这是否会增大计算难度，降低效率？,课堂讨论环节显然让课堂效率提高了而它正是卷积过程的体现,Layer L1在座近100位同学都提出了自己的观点,Layer L2通过小组讨论，初步得出问题的解答,Layer L3对每个小组的讨论结果进行评估，考虑其对问题的偏离程度（权重），得出最
3、终结果,CNNs的工作就是将全局映射转化为区域映射的过程。,另一个现实中的例子是图像处理,卷积神经网络在该课题中如何运用？,Classical diagnosing method,Initial clinical screening,Dermoscopic analysis,Biopsy,Histopathological examination,Observing undermicroscope,Diagnosticreport,Formation of AI dermatologist A process of machine learning,Figure 1 | Deep CNN la
4、yout. Formed by Google Inception v3 CNN architecture,Step1 They demonstrated classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs.,Figure 2 | A schematic illustration of the taxonomy and example test set images,a,
5、A subset of the top of the tree-structured taxonomy of skin disease.b, Malignant and benign example images from two disease classes.,Step 2 They trained a CNN using a dataset of 129,450 clinical images, consisting of 2,032 different diseases.,Step 3 Grasp the characteristic message of pictures by an
6、alyzing pixels.,Figure 3 | Skin cancer classification performance of dermatologists (a) and CNN (b).,Practical diagnose Analyzing up-loaded picture from mobile devices,Figure 4 | t-SNE visualization of the last hidden layer representations in the CNN for four disease classes,Real case analysis as su
7、pport information,AI诊断的发展前景如何？,Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 and can therefore potentially provide low-cost universal
8、access to vital diagnostic care.,Ericsson Mobility Report, 2016,除了诊断病症AI还给我们带来了什么？,Deep learning algorithms, powered by advances in computation and very large datasets, have recently been shown to exceed human performance in visual tasks such as playing Atari games, strategic board games like Go and object recognition.,AI应用于生活的几个例子,2017年5月23日5月27日 “第二次围棋人机大战”,论决策和价值评估，人类真的输了！,Demis Hassabis，创业公司DeepMind创始人。,“AI是人类探索世界的工具。”,属于我们自己的AlphaGo又在何方？,像AlphaGo一样思考,对历史的旁征博引对当今的运筹帷幄对未来的高瞻远瞩,“人生如棋”,Karl Popper(1902.7.281994.9.17),“一切伟大的科学理论都意味着对未知领域的新征服。”,
