Accelerating retinal disease detection at low cost

Accelerating retinal disease detection at low cost

Key Impact

  • 60 seconds

    Time achieved to produced accurate retinal diagnosis

  • 40 percent

    reduced cost to perform Al eye screening

  • Increase in satisfaction on patient experience

Overview

A European healthcare technology company focusing on innovations for ophthalmology aims to make eye screening more accessible to wider public with accelerated speed and reduced cost. The goal is to improve care for eye patients and to detect eye disease as early as possible. To proceed at scale, AI is adopted at the core of the eye screening model, and the company partnered with Kili Technology to ensure the accuracy of this model with clean labelled retinal data of patients.

The mission to improve people’s vision at scale

Today, millions of people in the world are at risk or already have vision-threatening eye conditions that are left undetected, such as diabetic retinopathy or glaucoma. Some people even have eye conditions that rooted from even more serious life-threatening causes such as stroke or cardiovascular disease – which also are left undetected. While traditional eye screenings are fairly costly and time consuming, with artificial intelligence the company has an ambition to accelerate this process to provide access to wide public and detect all possible eye conditions within seconds on low cost, at scale.

To deliver precise eye diagnosis within seconds, the company acknowledged that its AI eye screening model needed to be trained rigorously and enriched with combination of accurately annotated data – such as retinal photography, CT scan images, and medical reports. Thus, data annotation process is essential to perform eye screening at scale to achieve the company mission to improve people’s vision.

The challenge to enrich AI eye screening model

Understanding the variety of patient data needed to diagnose eye condition, the company realized the complexity and challenge to train the AI eye screening model. One of the challenges is finding a solution that is fully compatible with the different data types, especially for specific one such as CT scan data. The company found it difficult to manage when they needed to host the labelling process with different tools to annotate different data, as each tool has different flow some are more complex than the other, and the whole process became inefficient.

I don’t think there were many tools that can annotate our data types. There were not many that can perform up to our standards as well. Let me tell you, using different tools at once can get your project to be all over the places. It was a headache.

– Alexander Chief Technology Officer

Another challenge is the need to speed up the labelling process, as to enrich the AI model, they need to only train rigorously in terms of rounded data types, but also in terms of voluminous amount – while ensuring precise quality. When the team annotate retinal and CT scan images, these images need to be cut down into manageable sizes to prevent being lost and missing details. Therefore, the total amount of training datasets multiplied significantly and the annotation process and ensuring quality is certainly time consuming.

Why Kili Technology

To solve these challenges, the healthcare company benchmarked Kili against multiple players in the market, including the different ones the company adopted previously. The company considered it highly practical when it found that Kili could accommodate all the data types needed – including CT scans format. On top of that, the customizable interface and reviewing features also improved their collaboration and flow of data annotation work.

Moreover, the company viewed Kili Technology as very efficient in being fast while keeping high standard of quality of annotation. The ability to plug in machine learning in the loop within Kili platform for the annotation process, speeds up the annotation significantly. Also, the quality management features such as consensus and honeypot facilitated the company to really scrutinize the quality of data labels effectively.

“It’s very convenient and simple to use. And when it’s simple to use, you get to be extremely more productive. No more headaches.” continues Alexander on his remarks on using Kili.

“Our mission is achieved – and will still continue”

Simplifying and scaling up data annotation process has enabled the healthcare technology company to perform fast delivery of eye diagnosis and to accurately detect potentially dangerous eye conditions early – at scale. Previously, patients who undergo eye diagnosis would receive the results in days or even weeks. With artificial intelligence model enriched with labelled training data, now patients the result can be obtained real time within a minute. It also reduces the cost of performing eye diagnosis by 40%, making it more accessible to wider public.

It’s exciting to see our model perform at hospitals and eye clinics. People get diagnosed within a minute. Our mission is achieved, and certainly will still continue.

– Alexander Chief Technology Officer

Lesson learned

  • Accurately labelled patient data play a critical role in enriching the AI model to deliver precise eye condition diagnosis. Hence investing time and effort in data labelling is the utmost importance to ensure the success of project.
  • Flexibility to apply machine learning in the loop during image annotation process is essential to significantly speed up the annotation process.
  • It is important to select the suitable data annotation partner to develop AI eye screening tool. Factors such as robustness, meticulous quality management, and simplicity of collaboration are key.

Photo by Nonsap Visuals on Unsplash