Webpages tagged with «deep learning»

Deep-learning models work well on medical images, but whole-slide images (WSIs) used in histopathology are so large that researchers usually have to freeze much of the model (the whole encoder) during training. This work proposes a novel method to train the full model end-to-end under realistic GPU memory constraints and investigates when this is beneficial.

Are you interested in making machines learned without labels?  Keep reading then...

The use of deep learning to detect and characterise histopathological images is anticipated to substantially enhance current clinical practice through more efficient and objective evaluation of diseases and more personalised treatment for the individual patient. Interested students are encourage to reach out to discuss current possibilities in the longstanding collaboration between the DSB group and the Institute for Cancer Genetics and Informatics at Oslo University Hospital.

Humans interpret the body language of others (both human and other animals) every day. The way we walk, posture and gestures tell a story of our inner lives and emotions. Emotion recognition has emerged as a crucial aspect of human-computer interaction, healthcare, and entertainment. In the future, we hope our robot and AI counterparts will be able to both understand and express emotional content through movement. Robot bodies take many forms, some more humanoid than others. How might we delvelop a method for transforming the emotional content of a movement - regardless of the body that is moving?

Two new papers from SANT were presented at the NoDaLiDa conference.

The SANT project develops resources for Sentiment Analysis for Norwegian Text. While coordinated by the Language Technology Group (LTG) at IFI/UiO, collaborating partners include NRK, Schibsted and Aller Media.

Cardiac related disease is the number one cause of death in the Western world, including Norway. Echocardiography is the most important imaging tool for the cardiologist to assess cardiac function. An echo examination of the heart is real time, cost effective and can be performed without discomfort to the patient and without harmful radiation. These are great advantages compared to other medical imaging modalities.