课件：皮肤癌的AI诊断.pptx

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CNNsLogistic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 L2通过小组讨论，初步得出问题的解答Layer L1在座近100位同学都提出了自己的观点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），得出最终结果另一个现实中的例子是图像处理CNNs的工作就是将全局映射转化为区域映射的过程。卷积神经网络在该课题中如何运用？Classical diagnosing methodDermoscopic analysisBiopsyInitial clinical screening Histopathological examinationObserving undermicroscopeDiagnosticreportFormation of AI dermatologist ——A process of machine learningStep1 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 1 | Deep CNN layout. Formed by Google Inception v3 CNN architectureStep 2 They trained a CNN using a dataset of 129,450 clinical images, consisting of 2,032 different diseases.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 from two disease classes.Step 3 Grasp the characteristic message of pictures by analyzing pixels.Figure 3 | Skin cancer classification performance of dermatologists (a) and CNN (b).Practical diagnose ——Analyzing up-loaded picture from mobile devicesFigure 4 | t-SNE visualization of the last hidden layer representations in the CNN for four disease classesReal case analysis as support informationAI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 20