|
|
PratikShah_2017G-_人工智能:让诊断疾病变得更容易_
|
Computer algorithms today are performing incredible tasks with high accuracies , at a massive scale , using human-like intelligence. |
今天的计算机算法, 正在使用类似人类的智能, 大规模的执行具有高精度的, 不可思议的任务。 |
performing:adj.表演的;演奏的;v.做;执行;演出;运转(perform的现在分词) incredible:adj.难以置信的,惊人的; accuracies:用法,发音,音标,搭配,同义词,反义词和例句等在线英语服务。; massive:adj.大量的;巨大的,厚重的;魁伟的; scale:n.规模;比例;鳞;刻度;天平;数值范围;v.衡量;攀登;剥落;生水垢;
|
And this intelligence of computers is often referred to as AI or artificial intelligence . |
而这种计算机智能,通常被称为AI, 或“人工智能”。 |
referred:v.提到;引用;认为;指示;涉及;(refer的过去式和过去分词) artificial intelligence:n.人工智能;
|
AI is poised to make an incredible impact on our lives in the future. |
人工智能有望在未来对我们的生活 产生令人难以置信的影响。 |
poised:adj.摆好姿势准备行动的; v.保持(某种姿势); impact:n.影响;效果;碰撞;冲击力;v.挤入,压紧;撞击;对…产生影响;
|
Today, however, we still face massive challenges in detecting and diagnosing several life-threatening illnesses, such as infectious diseases and cancer . |
然而今天,在检测和诊断 几种危及生命的疾病, 比如传染病和癌症时, 我们仍然面临着大量的挑战。 |
detecting:n.检测;检定;v.发现;探知(detect的现在分词);adj.探测的; diagnosing:n.诊断;v.诊断(diagnose的现在分词); life-threatening:adj.威胁生命的; infectious:adj.传染的;传染性的;易传染的; diseases:n.[医]病(disease的复数);[医]疾病;[植保]病害;疾病种类; cancer:n.癌症;恶性肿瘤;
|
Thousands of patients every year lose their lives due to liver and oral cancer. |
每年,数以千计的病人 因患上肝癌和口腔癌失去生命。 |
patients:n.接受治疗者,病人;(patient的复数) liver:n.肝;(动物供食用的)肝; oral:adj.口头的; n.(尤指外语考试中的)口试; (大学里的)口试;
|
Our best way to help these patients is to perform early detection and diagnoses of these diseases. |
帮助病人最好的方式 就是对这些疾病进行 早期检测和诊断。 |
detection:n.侦查,探测;发觉,发现;察觉; diagnoses:n.诊断;调查分析;评价(diagnosis的复数形式);
|
So how do we detect these diseases today, and can artificial intelligence help? |
那么,今天我们如何检测这些疾病? AI可以提供帮助吗? |
In patients who, unfortunately , are suspected of these diseases, an expert physician first orders very expensive medical imaging technologies such as fluorescent imaging, CTs, MRIs, to be performed . |
对于不幸被怀疑 患有这些疾病的患者, 专家医师会先要求他们照射 非常昂贵的医疗图像, 例如荧光成像,CT,MRI等。 |
unfortunately:adv.不幸地; suspected:v.怀疑;不信任;(suspect的过去分词和过去式) physician:n.[医]医师;内科医师; imaging:n.[物]成像;造像;v.反映;想像;作…的像;象征;(image的现在分词形式) technologies:n.技术;科技(technology的复数); fluorescent:adj.荧光的;萤光的;发亮的;n.荧光;日光灯; performed:v.表演;执行;履行;演出;工作,运转(好/不好)(perform的过去分词和过去式)
|
Once those images are collected, another expert physician then diagnoses those images and talks to the patient. |
收集到这些图像之后, 另一位专家医师会进行诊断, 并与患者交流。 |
images:n.印象;声誉;形象;画像;雕像;(image的第三人称单数和复数)
|
As you can see , this is a very resource-intensive process , requiring both expert physicians , expensive medical imaging technologies, and is not considered practical for the developing world. |
显而易见,这是个 非常耗费资源的过程, 需要两位专家医师 和昂贵的医学图像技术。 这在发展中国家被认为并不实用, |
As you can see:正如你所看到的;你是知道的; resource-intensive:[环境]资源密集; process:v.处理;加工;列队行进;n.过程,进行;方法,adj.经过特殊加工(或处理)的; physicians:n.[内科]内科医生(physician的复数); practical:adj.实际的;真实的;客观存在的;n.实习课;实践课;
|
And in fact, in many industrialized nations, as well. |
事实上,在许多 工业化国家也是如此。 |
industrialized:adj.工业化的;v.使工业化;将…组成产业(industrialize的过去分词);
|
So, can we solve this problem using artificial intelligence? |
那么,我们能够用 人工智能解决这个问题吗? |
Today, if I were to use traditional artificial intelligence architectures to solve this problem, |
今天,如果使用传统的 人工智能架构 来解决这个问题, |
traditional:传统的,惯例的, architectures:n.建筑;架构(architecture的复数);
|
I would require 10,000 -- |
我可能需要1万张—— |
I repeat, on an order of 10,000 of these very expensive medical images first to be generated . |
我重复一次,我首先需要 生成1万张这种非常昂贵的 医学图像。 |
generated:v.产生;引起;(generate的过去式和过去分词)
|
After that, I would then go to an expert physician, who would then analyze those images for me. |
之后,我会去找一位专业医师 为我分析这些图像。 |
analyze:v.对…进行分析,分解(等于analyse);
|
And using those two pieces of information, |
利用这两条信息, |
I can train a standard deep neural network or a deep learning network to provide patient's diagnosis . |
我可以训练标准的深度神经网络, 或深度学习网络 对患者进行诊断。 |
standard:n.标准;水准;旗;度量衡标准;adj.标准的;合规格的;公认为优秀的; neural network:n.神经网络; diagnosis:n.诊断;
|
Similar to the first approach, traditional artificial intelligence approaches suffer from the same problem. |
与第一步相似, 传统人工智能方法 遭遇了同样的问题: |
approaches:v.靠近,接近; n.方式,方法,态度;
|
Large amounts of data, expert physicians and expert medical imaging technologies. |
那就是需要大量的数据、 专家医师和专业的医疗图像技术。 |
So, can we invent more scalable , effective and more valuable artificial intelligence architectures to solve these very important problems facing us today? |
我们是否能够创造出一种 规模更大、更有效率、 同时更有价值的人工智能架构, 来解决我们今天面临的 这些重要的问题呢? |
scalable:adj.可攀登的;可去鳞的;可称量的; effective:adj.有效的,起作用的;实际的,实在的;给人深刻印象; valuable:adj.有价值的;贵重的;可估价的;n.贵重物品;
|
And this is exactly what my group at MIT Media Lab does. |
而这就是我们的团队 在MIT媒体实验室所研究的内容。 |
Media:n.媒体;媒质(medium的复数);血管中层;浊塞音;中脉;
|
We have invented a variety of unorthodox AI architectures to solve some of the most important challenges facing us today in medical imaging and clinical trials. |
我们开发了各种新型AI架构, 来解决一些我们当今 在医疗图像和临床试验中 面临的最重要的挑战。 |
variety:n.多样;种类;杂耍;变化,多样化; unorthodox:adj.非正统的;异端的;异教的; clinical:adj.临床的;诊所的;
|
In the example I shared with you today, we had two goals. |
在我今天分享的例子中, 包括了我们的两个目标。 |
Our first goal was to reduce the number of images required to train artificial intelligence algorithms. |
第一个目标,是减少 用来训练人工智能算法 所需要的图片数量。 |
Our second goal -- we were more ambitious , we wanted to reduce the use of expensive medical imaging technologies to screen patients. |
第二个目标——更大的志向, 我们希望让患者减少使用昂贵的 医疗图像技术。 |
ambitious:adj.野心勃勃的;有雄心的;热望的;炫耀的;
|
So how did we do it? |
那么我们是怎样做的? |
For our first goal, instead of starting with tens and thousands of these very expensive medical images, like traditional AI, we started with a single medical image. |
我们的第一个目标, 相比于传统AI 从成千上万张昂贵的医疗图像开始, 我们选择从单张图像开始。 |
From this image, my team and I figured out a very clever way to extract billions of information packets. |
根据这张图片, 我和我的团队想出了 一种非常聪明的方法 来提取数十亿个信息包。 |
extract:v.提取;取出;摘录;榨取;n.汁;摘录;榨出物;选粹;
|
These information packets included colors, pixels , geometry and rendering of the disease on the medical image. |
这些信息包包含颜色、像素、形态 和疾病呈现在医疗图像上的效果。 |
pixels:n.像素(组成屏幕图像的最小独立元素);(pixel的复数) geometry:n.几何学;几何结构; rendering:n.演奏;扮演;表演;翻译作品;v.使成为;给予;提供;回报;(render的现在分词)
|
In a sense , we converted one image into billions of training data points, massively reducing the amount of data needed for training. |
这样一来,我们就将一张图像 转换成了数十亿个训练数据点, 需要训练的数据量就大大减少了。 |
In a sense:在某种意义上; converted:adj.修改的;改变信仰的;v.转变;改变信仰(convert的过去式和过去分词形式); massively:adv.大量地;沉重地;庄严地;
|
For our second goal, to reduce the use of expensive medical imaging technologies to screen patients, we started with a standard, white light photograph, acquired either from a DSLR camera or a mobile phone , for the patient. |
第二个目标, 是减少对患者使用医疗图像技术。 最开始,我们会从 数码单反相机或手机中 获取一张标准的白色光线照片。 |
white light:n.白光; acquired:adj.习得的; v.获得; (acquire的过去分词和过去式) mobile phone:移动电话
|
Then remember those billions of information packets? |
然后,还记得那 数十亿个信息包吗? |
We overlaid those from the medical image onto this image, creating something that we call a composite image. |
将这些医疗图像的信息包 覆盖在这张图片上, 这时我们就创建了一张合成图像。 |
overlaid:v.覆盖(overlay的过去分词); composite:n.复合材料;合成物;菊科;adj.复合的;合成的;菊科的;vt.使合成;使混合;
|
Much to our surprise, we only required 50 -- |
令人惊讶的是,我们只需要50张—— |
I repeat, only 50 -- of these composite images to train our algorithms to high efficiencies . |
强调一下,仅仅50张—— 这些复合图像, 就能训练我们的算法提高效率。 |
efficiencies:n.效率(efficiency的复数);
|
To summarize our approach, instead of using 10,000 very expensive medical images, we can now train the AI algorithms in an unorthodox way, using only 50 of these high-resolution , but standard photographs, acquired from DSLR cameras and mobile phones, and provide diagnosis. |
总结一下我们的方法, 区别于用1万张昂贵的 医疗图像训练AI算法, 我们使用了一种全新的方式, 只需要将数码相机或手机拍摄的 50张高分辨率的标准照片, 即可提供诊断。 |
summarize:v.总结;概述;概括;归纳; high-resolution:n.高分辨率;
|
More importantly, our algorithms can accept, in the future and even right now, some very simple, white light photographs from the patient, instead of expensive medical imaging technologies. |
更重要的是, 在未来,甚至现在, 我们的算法可以接受 一些病人自己拍摄的白光照片, 来替代昂贵的医疗图像技术。 |
I believe that we are poised to enter an era where artificial intelligence is going to make an incredible impact on our future. |
我相信,我们已经准备好 进入这样一个时代, 人工智能 正在对我们的未来产生 不可思议的影响。 |
And I think that thinking about traditional AI, which is data-rich but application-poor, we should also continue thinking about unorthodox artificial intelligence architectures, which can accept small amounts of data |
我也认为相比拥有丰富数据 但应用困难的传统AI, 我们应该不断思考 非传统的人工智能架构。 它们能够接受少量数据, |
and solve some of the most important problems facing us today, especially in health care . |
并解决一些今天 我们所面临的重要问题, 特别是在医疗健康方面。 |
especially:adv.尤其;特别;格外;十分; health care:n.卫生保健;
|
Thank you very much. |
非常感谢。 |
(Applause) |
(掌声) |