1、PPT制作、主讲 朱明哲朱明哲文献查找、翻译、Word文档制作 李卓李卓1皮肤癌的ai诊断2皮肤癌的ai诊断生物医学传感领域的新突破生物医学传感领域的新突破3皮肤癌的ai诊断百度搜索引擎都膜拜的第一作者百度搜索引擎都膜拜的第一作者4皮肤癌的ai诊断荣获斯坦福大学荣获斯坦福大学AI领域的理学博士领域的理学博士并修德克萨斯大学奥斯汀分校电子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计算机工程及纯数学双专业5皮肤癌的ai诊断6皮肤癌的ai诊断7皮肤癌的ai诊断Dermatologist-level classification of skin cancerwith deep neural
2、 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年年2月全球科学技术十大突破之五月全球科学技术十大突破之五8皮肤癌的ai诊断这种所谓的深度神经网络这种所谓的深度神经网络就是近年来经常提及就是近年来经常提及 但又充满神秘的但又充满神秘的9皮肤癌的ai诊断10皮肤癌的ai诊断从数学上看从数学上看深度神经网络深度神经网络(Deep Neural Networks)卷积神经网络卷积神经网络(Convolutional Neural Networks)11皮肤癌的ai诊断浅析浅析CNNsLogistic回归模型12皮肤癌的ai诊断浅析浅析CNNs
3、13皮肤癌的ai诊断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？14皮肤癌的ai诊断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），得出最终结果15皮肤癌的ai诊断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16皮肤癌的ai诊断17皮肤癌的ai诊断Classical diagnosing methodInitial clinical screening Der
4、moscopic analysisBiopsyHistopathological examinationObserving undermicroscopeDiagnosticreport18皮肤癌的ai诊断Formation of AI dermatologist A process of machine learning19皮肤癌的ai诊断Figure 1|Deep CNN layout.Formed by Google Inception v3 CNN architectureStep1 They demonstrated classification of skin lesions us
5、ing a single CNN,trained end-to-end from images directly,using only pixels and disease labels as inputs.20皮肤癌的ai诊断Figure 2|A schematic illustration of the taxonomy and example test set imagesa,A subset of the top of the tree-structured taxonomy of skin disease.b,Malignant and benign example images f
6、rom two disease classes.Step 2 They trained a CNN using a dataset of 129,450 clinical images,consisting of 2,032 different diseases.21皮肤癌的ai诊断Step 3 Grasp the characteristic message of pictures by analyzing pixels.Figure 3|Skin cancer classification performance of dermatologists(a)and CNN(b).22皮肤癌的a
7、i诊断Practical diagnose Analyzing up-loaded picture from mobile devices23皮肤癌的ai诊断Figure 4|t-SNE visualization of the last hidden layer representations in the CNN for four disease classes24皮肤癌的ai诊断Real case analysis as support information25皮肤癌的ai诊断26皮肤癌的ai诊断 Outfitted with deep neural networks,mobile d
8、evices 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 access to vital diagnostic care.27皮肤癌的ai诊断Ericsson Mobility Report,201628皮肤癌的
9、ai诊断29皮肤癌的ai诊断 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.30皮肤癌的ai诊断AI应用于生活的几个例子31皮肤癌的ai诊断32皮肤癌的ai诊断2017年5月23日5月27日“第二次围棋人机大战”33皮肤癌的ai诊断论决策和价值评估，人类真的输了！论决策和价值评估，人类真的输了！34皮肤癌的ai诊断Demis Hassabis，创业公司DeepMind创始人。“AI是人类探索世界的工具。”35皮肤癌的ai诊断36皮肤癌的ai诊断像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”37皮肤癌的ai诊断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。”38皮肤癌的ai诊断39皮肤癌的ai诊断
