多尺度视网膜图像增强_视网膜图像怪异的预测

多尺度视网膜图像增强

If you’ve ever been to see an opthamologistst, you’ve probably undergone a routine procedure where a specialist takes a picture of the back of your eye.

如果您曾经去看过眼科医师，则可能已经过了例行程序，即由专家为您的眼后部拍照。

You will not be surprised to hear that retinal images are rather handy for diagnosing eye diseases. However, you may not have expected that they can also provide a lot of insight into a person’s risk of cardiovascular disease. Retinal imaging is a non-invasive way to examine the condition of someone’s blood vessels, which may be indicative of that person’s wider cardiovascular health.

听到视网膜图像对于诊断眼部疾病非常方便，您不会感到惊讶。 但是，您可能没有想到它们也可以提供有关人患心血管疾病风险的大量见解。 视网膜成像是检查某人血管状况的一种非侵入性方式，可能表明该人的心血管健康状况更强。

If you’ve seen one of these retinal images before, you’ll probably be able to point out the optic disc and the various blood vessels (if you haven’t, try sticking “retina image” into Google — or “fundus”, which is the medical term for the back of the eye).

如果您以前看过这些视网膜图像之一，则可能可以指出视盘和各种血管(如果没有，请尝试将“视网膜图像”粘贴到Google中或“眼底”中，这是眼后的医学术语)。

A doctor will be able to go one step further by identifying abnormalities and suggesting features that may warrant further investigation or treatment.

通过识别异常并建议可能需要进一步检查或治疗的特征，医生将可以进一步走下去。

However, feed it to a machine and it’ll be able to predict:

但是，将其输入到机器中，它将能够预测：

• how old you are;
  你几岁
• your gender;
  您的性别;
• your ethnicity;
  你的种族;
• whether or not you smoke; and even
  你是否吸烟； 乃至
• what you had for breakfast that morning.
  你那天早上吃的早餐。

Okay, so I may have made that last one up — but remarkably, the rest are true. Make no mistake, retinal images are weirdly predictive.

好吧，所以我可能已经提出了最后一个建议-但值得注意的是，其余的都是正确的。 毫无疑问， 视网膜图像具有奇异的预测性。

眼睛有它 (The eyes have it)

Researchers at Google wrote a 2017 paper setting out an investigation into how deep learning could be used to predict a range of cardiovascular risk factors from retinal images. The paper briefly explains the more traditional approach to medical discovery: first observing associations and correlations between potential risk factors and disease, and only then designing and testing a hypothesis. Ryan Poplin et al then go on to demonstrate how deep learning architectures can pick up these associations by themselves without being told what to look for.

谷歌的研究人员在2017年发表了一篇论文 ，对如何使用深度学习从视网膜图像预测一系列心血管危险因素进行了调查。 这篇论文简要解释了更传统的医学发现方法：首先观察潜在风险因素与疾病之间的关联和相关性，然后才设计和检验假设。 然后，Ryan Poplin等人继续演示了深度学习架构如何在不被告知要寻找什么的情况下自行获取这些关联。

I’m sure we’ve all heard at some point the assertion that certain medical specialists are going to be replaced by AI algorithms that will be able to outperform them at recognising abnormalities in medical images. This research takes things in a slightly different direction — not seeking to outperform doctors at an existing task but to see what new information machines can glean from these particular images.

我敢肯定，我们都在某个时候听说过这样的断言，即某些医学专家将被AI算法所取代，这些AI算法在识别医学图像异常方面将胜过他们。 这项研究的方向略有不同-不是试图在现有任务上胜过医生，而是要从这些特定图像中了解哪些新的信息机器可以收集信息。

Early on in their research, the team found that their model was remarkably good at predicting variables like age and gender — so much so that they initially thought that it was a bug in the model (Ryan walks us through how the project developed on TWiML talk 112). But as they looked further into things, they discovered that these were real predictions. Not only that, they were incredibly robust ones as well — age, for example, could be successfully predicted with a mean absolute error of 3.26 years.

在研究的早期，团队发现他们的模型非常擅长预测年龄和性别等变量-如此之多，以至于他们最初认为这是模型中的错误 (Ryan引导我们了解了TWiML上的项目开发方式) 112 )。 但是当他们深入研究事物时，他们发现这些是真实的预测。 不仅如此，它们也非常健壮-例如，可以成功预测年龄，平均绝对误差为3.26年。

A number of other associations were found, and it turned out that the team could obtain better predictive power than their baseline model across all kinds of variables including blood pressure, blood glucose levels and even ethnicity — all risk factors for cardiovascular disease.

还发现了许多其他关联，结果表明，该团队在所有变量(包括血压，血糖水平甚至种族)的所有变量中都比其基线模型获得更好的预测能力，所有变量都是心血管疾病的危险因素。

After observing these results, the team reasoned that if this range of cardiovascular risk factors could be predicted so well, then the model may even have predictive power when it came to identifying which patients were most likely to suffer from a major cardiovascular event (eg a stroke or heart attack) in the future. Despite some limitations in their training data, a model trained only on retinal images (so no explicitly given risk factors) was able to achieve an AUC of 0.70 (skim the ROC/AUC section of this article to learn more about AUC as a performance metric) — which becomes especially impressive in comparison to the 0.72 obtained by another existing risk scoring system which makes use of a great deal more input variables.

在观察了这些结果之后，研究小组认为，如果可以很好地预测这一范围的心血管危险因素，那么该模型甚至可以在确定哪些患者最可能患有重大心血管事件(例如中风或心脏病发作)。 尽管在他们的训练数据的一些局限性，一个模型中训练只对视网膜图像(所以没有明确给出风险因素)能够达到0.70的AUC(脱脂的ROC / AUC部分这篇文章 ，详细了解AUC性能度量)-与另一个现有风险评分系统(使用大量输入变量)获得的0.72相比，这尤其令人印象深刻。

不只是心灵的窗户 (More than just windows to the soul)

Photo by Liam Welch on Unsplash

利亚姆·韦尔奇 ( Liam Welch)在 Unsplash上 拍摄的照片

In the TWiML podcast mentioned earlier, Ryan speculates about a possibile future in which retinal images are taken as vital signs to give a picture of overall patient health instead of just being used to diagnose eye diseases. As we have seen, this isn’t just fantasy — this straightforward and non-invasive procedure could give a much broader snapshot into a patient’s health than we might have previously expected.

在前面提到的TWiML播客中，Ryan推测了一个可能的未来，其中视网膜图像被视为生命体征，以提供总体患者健康状况的图像，而不仅仅是用于诊断眼部疾病。 如我们所见，这不仅是幻想，而且这种简单，无创的程序可以比我们以前预期的更广泛地了解患者的健康状况。

To conclude — cardiovascular disease remains the leading cause of death across the world, but 80% of premature heart disease and stroke is preventable. Research like the paper discussed above can help us better understand who is at highest risk of cardiovascular disease and how these groups can be best managed — appropriate early interventions could go a very long way to extending and improving the quality of human life.

总而言之，心血管疾病仍然是世界范围内主要的死亡原因，但是80％的心脏病和中风是可以预防的 。 像上面讨论的论文这样的研究，可以帮助我们更好地了解谁最容易患心血管疾病，以及如何最好地管理这些人群-适当的早期干预措施对延长和改善人类生活质量可能有很长的路要走。

积分和更多信息 (Credits and more info)

Andrew Hetherington is an actuary-in-training and data enthusiast based in London, UK.

安德鲁·赫瑟灵顿 ( Andrew Hetherington)是英国伦敦的精算师和数据爱好者。

• Check out my website.

  查看我的网站 。

• Connect with me on LinkedIn.

  在LinkedIn上与我联系。

• See what I’m tinkering with on GitHub.

  在GitHub上查看我正在修补的内容。

Paper discussed: R. Poplin et al., “Predicting cardiovascular risk factors from retinal fundus photographs using deep learning,” DOI 10.1038/s41551–018–0195–0, https://arxiv.org/abs/1708.09843v2.

讨论的论文：R. Poplin等人，“使用深度学习从视网膜眼底照片预测心血管危险因素”，DOI 10.1038 / s41551–018–0195-0 ， https： //arxiv.org/abs/1708.09843v2 。

Photos by nrd and Liam Welch on Unsplash.

由nrd和Liam Welch 拍摄的Unsplash照片 。

翻译自: https://towardsdatascience.com/retinal-images-are-weirdly-predictive-888744b4a153

多尺度视网膜图像增强