Computer Vision News - August 2020

AI Spotlight News 43 FDA clears Infervision’s AI- powered lung CT reader Infervision Technology has received the green light from the U.S. FDA for its Inferread Lung CT.AI product. The AI- and DL-based technology automatically performs lung segmentation and identifies and labels different types of lung nodules . It is designed to aid the radiologist in the detection of pulmonary nodules during the review of CT examinations of the chest on an asymptomatic population . The software requires that both lungs be in the field of view. Survival rates drop dramatically if the cancer has progressed to late- stage disease without treatment .The company believes the system could benefit lung cancer screening and improve timely detection of hard- to-spot smaller nodules. More AI in Pulmonology . Read More European Association of Urology (EAU 2020) - Recognising Images, Tissues, Signals As part of the “Thematic Session 10: New Technology for Urology” plenary session at the European Association of Urology (EAU) Virtual Annual Meeting, our friend Wiro Niessen discussed questions of technological improvements in image recognition as they may relate to pathology and radiology interpretation . There is a correlation between the radiographic appearance on a medical imaging and the underlying biology . Machine learning approaches seek to utilize such imaging features to provide useful classifications. Wiro highlighted his work which seeks to develop a classifier for patients with high-risk prostate cancer from MRI images. Read also RSIP Vision’s work in this magazine on page 10 . Read More The Machine Learning Summer School Time for Summer Schools and time to learn. The Max Planck Institute for Intelligent Systems at Tübingen, Germany gives access to a full series of vlogs posted on YouTube, including awesome videos by Yoshua Bengio ! Yes, if you want to learn Deep Learning I and Deep Learning II from Professor Bengio himself, you can do it now on this page: just click on the videos below. Read More