Advances in Breast Imaging (cancelled, due to insufficient number of submissions)
Workshop website: http://users.aber.ac.uk/hgs08/ABI2015/
Call for papers: http://users.aber.ac.uk/hgs08/ABI2015/
Paper submission details: http://users.aber.ac.uk/hgs08/ABI2015/
Workshop chairs:
- Harry Strange, Aberystwyth University, UK
- Reyer Zwiggelaar, Aberystwyth University, UK
- Moi Hoon Yap, Manchester Metropolitan University, UK
Breast cancer is the most common cancer affect- ing women worldwide causing 1 in 6 cancer related deaths in European women. Although incidence statistics remain high, mortality rates are dropping, thanks in part to early detection methods such as mammographic screening. Computer aided meth- ods for diagnosis and detection can play a key role in the diagnosis pathway and can help radiologists obtain a faster and more accurate diagnosis.
This workshop seeks to provide a platform for current and recent research within the field of breast imaging. In particular, we would welcome work with a specific focus on employing novel and in- teresting computer vision and machine learning to the problem domain of breast image analysis.
Work considered is not restricted to a single imaging modality, submissions are welcome that cover:
- Digital mammography
- Digital breast tomosynthesis
- Digital pathology
- MRI
- CT
- Ultrasound
- Aesthetic evaluation of treatments
The workshop is expected to cover topics relating to technical advances in breast imaging including, but not limited to:
- Image processing and reconstruction
- Image segmentation
- Image registration
- Image quality assessment
- Computer-aided diagnosis (CAD)
- Computer-aided detection (CADx)
- Multi-modal imaging
- Visualisation
- Large scale learning and analysis
- Incorporation of semantic and clinical informa- tion
- Phantom image generation
Keynote Speaker: The workshop will have two invited speakers, one of whom will discuss the challenges presented by breast imaging research from a clinical perspective and one of whom will discuss the challenges from a computer vision/machine learning perspective.