A worldwide leader in endoscopic technology needed help in building medical diagnostic tool. The company’s mission is to build and provide medical diagnostic tools and increase the access of medical testing in remote and rural areas around the world. The company approached Clarifai to use its deep learning AI lifecycle platform, so it could build a smartphone app that could take professional-grade medical images of the human ear and use them to diagnose problems.
Medical device manufacturer
The company wanted to utilize the thousands of medical images it had on file to build a diagnostic platform that would be able to assist doctors in identifying ear problems but had a limited budget. They also knew that they needed the modeling capabilities of an end-to-end computer vision and deep learning to build it Their expectation was build a solution that would not only provide accurate results for a very esoteric data set (pictures of the insides of ears), but would also be able to improve with more training.
The company built a diagnostic tool that could assist general practitioners and nurses to identify and treat ear problems accurately, thereby making the best medical care accessible to anyone in the world. While Clarifai’s core model can recognize over 11,000 general concepts, ear diseases unsurprisingly are not among those core models, so the company worked with Clarifai to build a custom model for the sole purpose of analyzing ear patterns.
With over 100,000 ear images collected from their widely distributed endoscopic tool, the company asked Clarifai to build a custom computer vision model for ear pictures and video. Clarifai’s team of data scientists used their expertise to fully train a solution that recognized ear problems with near perfect accuracy.
It only took a week for a custom model to be fully trained with near perfect accuracy. Now, Clarifai’s platform powers the software layer in the company’s endoscopic hardware, enabling the tool to not only take pictures of the ear, but also analyze the results.