The development of intelligent medical data analysis systems has experienced a significant boost in recent years thanks to the emergence of a machine learning paradigm known as deep learning. Deep learning (DL) algorithms have enabled development of highly accurate systems (with performance comparable to that of human experts, in some cases) and have become a standard choice for analyzing medical data, especially medical images, video, and electronic health records. Dozens of commercial applications using deep learning to analyze, classify, segment and measure data from different modalities of sensors and medical images are currently available. Deep learning methods applied on electronic health records are contributing to understand the evolution of chronic diseases and predicting the risk of developing those diseases. Researchers in industry, hospitals, and academia have published hundreds of scientific contributions in this area during the last year alone.

The “Deep Learning Applications in Medical Care” special track provides a forum for the discussion of the impact of deep learning on medical sensor/image/video data and electronic health record analysis and a focused venue for sharing novel scientific contributions in the area of deep learning.

Authors are invited to submit their original contributions before the deadline following the conference submission guidelines. Each contribution must be prepared following the IEEE two-column format, and should not exceed the length of 6 (six) Letter-sized pages. For detailed instructions please visit: http://www.cbms2019.org/calls/ and go to “Submission” -) “Instructions for Authors”.

Authors are invited to submit their original contributions with the following topics of interest (but not limited to):

-Novel approaches for medical sensor/image data analysis, event detection, segmentation, and abnormality detection, object/lesion classification, organ/region/landmark localization, object/lesion detection, organ/substructure segmentation, lesion segmentation, and medical image registration using DL.
-DL for electronic health records analysis.
-Content-Based Image Retrieval (CBIR) of medical images using DL.
-Medical sensor/image data understanding using DL.
-Medical sensor/image data visualisation.
-Sensor/image data generation and preprocessing methods using unsupervised DL like GANs, autoencoders, etc.
-Multimodal analysis and fusion using DL.
-Applications of DL in different fields of medicine such as psychology.
-Human behavior modelling using DL for mental healthcare applications.
-Organ-specific (brain, eye, breast, heart, skin, lungs, abdomen, etc.), modality-specific (MRI, X-rays, PET, CT, color fundus images, etc.) and disease-specific image analysis using DL.
-Applications of DL for digital pathology and microscopy.


Organizers
-Enrique Garcia Ceja, University of Oslo, Norway [e.g.mx (at) ieee (dot) org]
-Michael Riegler, SimulaMet & University of Oslo, Norway [michael (at) simula (dot) no]
-Pål Halvorsen, SimulaMet, Norway [paalh (at) ifi (dot) uio (dot) no]
-Venet Osmani, Fondazione Bruno Kessler, Italy [vosmani (at) fbk(dot)eu]
-Hugo Lewi Hammer, Oslo Metropolitian University, Norway [hugoh (at) oslomet(dot)no]
-Klaus Schoeffmann, Klagenfurt University, Austria [ks (at) itec(dot)aau(dot)at]
-Dag Johansen, The Arctic University of Norway, Norway [dag.johansen (at) uit(dot)no]
-Svein Arne Pettersen, The Arctic University of Norway, Norway [svein.arne.pettersen.no (at) uit(dot)no]