Computer Vision News - December 2021

44 MedTech Spotlight News Medical Imaging News has found great new stories, written somewhere else by somebody else. We share them with you, adding a short comment. Enjoy! Google Research Changes the Game for Medical Imaging with Self-Supervised Learning The guys at VentureBeat did not fail to notice this exceptional new work by a team at Google Research, led by awesome Shekoofeh Azizi : researchers suggest a new technique that uses self-supervised learning to train deep learning models for medical imaging. Early results show that the technique can reduce the need for annotated data and improve the performance of deep learning models in medical applications: “ Using self- supervised learning, we show that we can significantly reduce theneed for expensive annotated data to build medical image classification models! ” Read More Her Machine Learning Tools Pull Insights from Cell Images A very nice interview with awesome Anne Carpenter . Not as good an interview as ours, of course! Anne explains how computers can mine images of cells for patterns that identify their cell type and disease-associated traits. This kind of image- based profiling is speeding up drug discovery by improving screening for compounds that desirably modify cells’ characteristics. What she does (this is how she puts it) is turning “ messy, qualitative biology into precise, quantitative numbers ”. Annealsoexpandsonthe CellProfiler , her free, open-source software that enable biologists to do just that ! Read More Artificial Intelligence in the Intensive Care Unit: UF Researchers Developing Novel Solutions The pandemic has brought many previously healthy people to Intensive Care Units all over the world. University of Florida Health researchers are developing an intelligent ICU , an autonomous patient-monitoring system driven by artificial intelligence . Capturing, analyzing and acting on information provided by cameras and other sensors should improve patient care and facilitate physicians’ decision- making. Ideally, the AI-driven systemwill predict whether an ICU patient will improve or decline, giving the docs precious time to intervene before a patient’s condition changes. Read More