JavaScript Beats Cancer

Rate this content
Bookmark

Skin cancer is a serious problem worldwide but luckily treatment in the early stage can lead to recovery. JavaScript together with a machine learning model can help Medical Doctors increase the accuracy in melanoma detection. During the presentation, we show how to use Tensorflow.js, Keras and React Native to build a solution that can recognize skin moles and detect if they are a melanoma or a benign mole. We also show issues that we have faced during development. As a summary, we present the pros and cons of JavaScript used for machine learning projects.

This talk has been presented at JSNation 2022, check out the latest edition of this JavaScript Conference.

FAQ

Karel Prystalski is an expert with 15 years of experience in machine learning, particularly in medical imaging and dermatoscopy. He holds a PhD in artificial intelligence and has founded a company that provides data science and machine learning solutions.

Karel Prystalski has 15 years of experience in machine learning, specifically in applications related to medical imaging and dermatoscopy. He has also published research papers on the topic.

JavaScript is used in skin cancer analysis primarily for building mobile and web applications that utilize machine learning models trained in Python. TensorFlow.js is used to load, use, and retrain these models on mobile devices.

Karel Prystalski chose JavaScript for its robustness, ease of use in mobile app development, and the ability to leverage libraries like TensorFlow.js for deploying machine learning models on mobile devices.

The highest risk group for skin cancer includes individuals with phototype I, characterized by blond hair, blue eyes, and skin that turns red rather than brown when exposed to the sun.

Karel Prystalski used tools and libraries such as TensorFlow.js, React Native, Docker, JupyterLab, and various JavaScript libraries for data manipulation and visualization.

The app works by using a dermatoscope attached to a mobile phone to capture high-quality images of skin moles. These images are then analyzed using machine learning models to detect patterns indicative of skin cancer.

Data sets like the one available on ISICarchive.com, which contains around 26,000 images of skin moles, are available for skin cancer research.

Challenges include a lack of robust machine learning libraries compared to Python, limited support for machine learning DevOps, and a smaller community focused on machine learning topics.

Karel Prystalski’s research papers can be found on Google Scholar, and his code samples are available on his GitHub repository.

Karol Przystalski
Karol Przystalski
25 min
20 Jun, 2022

Comments

Sign in or register to post your comment.

Video Summary and Transcription

This Talk discusses using JavaScript to combat skin cancer, with a focus on machine learning integration. The speaker has experience in medical imaging and has partnered with dermatoscopy companies to develop hardware. JavaScript libraries like TensorFlow.js and Pandas.js are used for model deployment and data analysis. The Talk also covers building neural networks, analyzing skin cancer using scoring methods and image processing techniques, and extracting asymmetry in skin images using Python and JavaScript.
Available in Español: JavaScript Vence al Cáncer

1. Introduction to JavaScript and Skin Cancer

Short description:

Hi, my name is Karel Prystalski and I will tell you more today about how to use JavaScript to beat skin cancer. I have 15 years of experience in machine learning and specifically in medical imaging. I decided to cover this topic and build solutions in this area because of the increasing importance of skin cancer, especially in countries like Germany, Scandinavia, the US, and Australia. I have also partnered with dermatoscopy companies to develop hardware, such as the dermatoscope, which is used by dermatologists. My solution combines the dermatoscope with special lenses and light to capture high-quality images of skin moles.

Hi, my name is Karel Prystalski, and I will tell you more today about how to use JavaScript to beat skin cancer. My experience is about 15 years in machine learning. So my background is machine learning, it's computer science, I did a PhD degree in artificial intelligence, how to use it in medical imaging and dermatoscopy as well.

You can find some of my papers, research papers in this topic on Google Scholar, for example. So feel free here is one of the articles that I have published, actually it is around five years ago, about analysing of skin cancer on multispectral images. Actually, in that case I use Python, but because of the, well, became more and more popular in the recent years, and also the usage of JavaScript specifically for this topic, I decided to also, well, prepare a presentation and also a solution app for skin cancer analysis.

So my background is not only scientific, I also have founded in 2010 so 12 years ago, a company, a service company working for fortune 500 companies, building also data science, machine learning solutions. And yeah, before that I had I did also some some, you know, some other commercial work, for example, at IBM. So, as I said, I have 15 years of experience in machine learning and specifically in medical imaging, I mean, in applications in medical imaging.

So, how, why I why I decided to actually cover this topic and to build some solutions in this area? Well, as you can see, I don't I'm not really in the risk group when it comes to skin cancer because, you know, the biggest group of of the risk group is actually the blond people with blue eyes. So, this is the phototype number one with the highest risk of having skin cancer, especially if you're becoming kind of your skin doesn't doesn't isn't well it doesn't become brown when you're exposed to the sun but actually it's more going in the direction of red, and actually also, the risk of actually getting skin cancer is high in this group.

So, the darker the skin is and how it reacts to the sun, the lower the the probability is to get a skin cancer. So, there are six type phototypes of skin. I'm more or less in the third group because of my color, hair color, eye color, and so on. That's why the biggest problem actually, it is the biggest, the countries like Germany, Scandinavia, and the Nordic countries, the US, Australia, especially Australia, this is actually where this problem is even more and more important. In the meantime, I also have done some partnership with some dermatoscopy companies, I mean companies who actually develop the hardware. So yeah, as you can see here, here's one of the device. This is our dermatoscope here. That's something, that is a device that is actually used by the dermatologists. In this case, I have also used an iPhone here on the front because this is actually an extension. So it's not a typical dermatoscope, usually it doesn't come with an iPhone or any kind of mobile phone. It comes alone, it's a standard on the device. Some dermatologists use also this kind of extension case just to take the pictures in an easier way. And obviously it's quite small, so we can take it to your pocket and actually visit even your patient to take a look on the mole like this. So this is how actually my solution is used and it is combined with the special lenses, special light to get the best possible image of the skin mole. When comes to the data set because any kind of machine learning topic, model should be fed by some data. Now when I started my research I actually started with 50, 53 images or less. So as you can imagine, that's not a big enough data set to do any kind of research. So what I did is I met, I guess, almost every company in public or private that do anything with dermatology in the city where I live, in Krakow, in Poland. Most of them actually declined to collaborate and actually build some models.

2. Machine Learning and JavaScript Integration

Short description:

Machine learning became a buzzword and the hype around AI has dramatically increased. Obtaining data sets for research has become easier, allowing the development of algorithms for various skin illnesses. Code samples and a Docker image with JavaScript libraries are available for download. The architecture involves combining machine learning with JavaScript to build a mobile app.

It was in 2007, 2008. So the way how people thought about machine learning was totally different than actually compared to what's happening now. Actually, machine learning is AI became a buzzword and everyone wanted to do AI. In the past, I mean, 15 years ago when I said AI, most people said, oh, no, thank you. I'm not interested. Now it's totally opposite. I need to explain people why not to use machine learning rather than actually use machine learning. So it changed dramatically in the COVID pandemic, even increased the hype on AI.

So when I reached to the companies, I obtained a data set of around 5,000 images. Now you can easily download a data set of about 26,000 images of skin moles. It's available on the ISICarchive.com website, and you can use it for your research. So now it's even easier to develop algorithms to find different kind of skin illnesses, not only cancer, which is technically, I mean, it's not the most popular. That's good illness when it comes to skin.

So for all of you that want to use of my code samples that I have prepared for you, you can always download my Docker image that contains a JupyterLab, JupyterHub, together with some kernels for JavaScript as well, and also some libraries, JavaScript libraries. It's a bit old because I am doing it for many years already. So it might be that I will update it soon, but it's still working. So you can easily use it with the notebooks that I will show you next. So the architecture, how I started to actually use machine learning, well, how I combined machine learning with JavaScript, because of this device, I decided, obviously, to use one of the JavaScript solutions to build a mobile app because the mobile devices are changing every year.