Computer Vision News - January 2022

69 MedTech Spotlight News Can Artificial Intelligence Stop the Harsh Reality of Internet Trolling? Why is this in MedTech Spotlight News? Follow the guide. Believe it or not, Internet trolls are able to spread flashing images on social media that trigger seizures in people with photosensitive epilepsy . It’s a terrible online abuse that has triggered this response by Bristol-based innovation agency Gravitywell . They have developed a plugin named ‘unFlash’ , an ML AI that learns how to effectively detect and block images that fall within the critical photosensitive range, helping social media to prevent harmful imagery from being shared online - or to display a warning where necessary. Read More 3-D Imaging Method May Help Doctors Better Determine Prostate Cancer Aggressiveness The great folks at ITNonline inform us that a team led by the University of Washington has developed a new, non- destructive method that images entire 3D biopsies of instead of just a slice. The purpose is to make the computer use 3D and 2D results to predict the likelihood that a patient has aggressive prostate cancer and therefore needs to be treated right away. Looking for abnormalities in slices of biopsied tissue is a classical way to assess the aggressiveness of the disease. But turning the slices into 3D makes it much easier to properly diagnose even borderline cases. Read More Artificial Intelligence, MRI Detect Early Signs of Tumor Cell Death Massachusetts General Hospital (MGH) researchers found that MRI and AI can be used to detect early signs of tumor cell death in response to a novel virus-based cancer therapy . The researchers claim that they programmed an MRI scanner to non-invasively create unique signal ‘fingerprints’ for different molecular compounds and cellular pH. A deep learning neural network was thenused todecode the fingerprints andgenerate quantitative pH and molecular maps.” The main novelty of their approach lies in the use of simulated molecular fingerprints to train the ML neural network. Read More