| [~i[Iu |
|---|
| ๚F | ฝฌ26N416๚(
)3ภ (13:30 -- 15:00) Wed., Apr. 16th, 2014 (3rd Period, 13:30 -- 15:00) |
|---|---|
| ๊F | L1 |
| uาF | Julia Schnabel (Institute of Biomedical Engineering, University of Oxford) |
|---|---|
| ฺ่F | Motion modelling for cancer imaging |
| TvF | In this talk I will give a brief overview of the Image Analysis Programme of the Cancer Imaging Centre at Oxford. I will in particular focus on some of our recent work in motion modelling for cancer imaging, recently presented at the MICCAI 2013 conference. I will first present an approach for complex lung motion estimation using adaptive bilateral filtering embedded in a popular gdemonsh registration framework. I will then discuss our new self-similarity metric, SSC, which generalises our previous gmodality-independent neighbourhood descriptorh (MIND), and which it outperforms in a challenging deformable 3D US/MR brain registration application. |
| uาF | Daniel Rueckert (Department of Computing, Imperial College London) |
|---|---|
| ฺ่F | Learning clinical useful information from medical images |
| TvF | This lecture will focus on the convergence medical imaging and machine learning techniques for the discovery and quantification of clinically useful information from medical images: The first part of the lecture will describe machine learning techniques such a dictionary learning that can be used for image reconstruction, e.g. the acceleration of MR imaging. The second part will discuss model-based approaches that employ statistical as well as probabilistic approaches for segmentation. In particular, we will focus on atlas-based segmentation approaches that employ advanced machine learning approaches such as manifold learning and classifier fusion to improve the accuracy and robustness of the segmentation approaches. |