Brazil has been hit harder by the COVID-19 as compared to any other country except the US. It has nearly 2.8 million infections and 95,000 deaths. Among all this, under-testing remains the biggest problem in Brazil, and experts say that the number would have been much higher if there were more widespread testing.
Now AI is helping to fill the gap with a system called RadVid-19 developed by using algorithms from German company Siemens and Chinese firm Huawei.
RadVid-19 helps doctors to decide the right course of treatment for their patients. It analyses chest X-rays and CT Scans to spot the likely marks of coronavirus infection on patients’ lungs. It estimates the probability of a case of COVID-19.
43 Brazilian hospitals and 60% of the public are using the software. Though it is not a replacement for a lab-based diagnosis by a physician, it can certainly help doctors to decide the treatment to pursue during a long wait for test results to come.
In other news:
Hypotenuse AI is a YC-backed startup that is using computer vision and machine learning to automate product descriptions for e-commerce. The core tech for hypotenuse lies in computer vision and natural language processing and is extremely cutting edge.
Hypotenuse AI’s founder Joshua Wong says, “We use computer vision to understand product images really well. And we use this together with any metadata that the product already has to generate a very ‘human fluent’ type of description. We can do this really quickly — we can generate thousands of them within seconds.”
The machine learning models have been trained on the internet all over the web so that they are able to understand the English language very well. Therefore, the neural network models could speak very fluently and in a human-like manner. A lot of work has gone into ensuring this, says Wong. This ability is combined with computer vision models to generate fluent descriptions.
Below is an example:
Head to the Great Learning Academy for free courses on Artificial Intelligence and Machine Learning.0