Medical imaging is becoming indispensable nowadays for healthcare and many other biomedical applications. With advances in medical imaging, such as cone-beam/multi-slice CT, 3D ultrasound imaging, tomosynthesis, diffusion-weighted magnetic resonance imaging (MRI), positron-emission tomography (PET)/CT, electrical impedance tomography, and diffuse optical tomography, there are increasing demands for advanced machine learning algorithms and applications in medical imaging field. Machine learning plays an essential role such as in computer-assisted diagnosis, image segmentation, image registration, image fusion, image-guided therapy, image annotation, and image database retrieval. Due to large inter-subject variability, it is generally difficult to derive an analytic formulation or a simple equation to represent objects, such as lesions and anatomies in the medical data. Therefore, tasks in medical imaging demand learning from patient data for heuristics and prior knowledge, in order to facilitate the detection and diagnosis of abnormality in the medical data. Because of its essential needs, machine learning in medical imaging is becoming one of the most promising and growing fields.
The main aim of this special issue is to help advance the scientific research within the broad field of machine learning and data mining in medical imaging. The special issue was planned in conjunction with the MICCAI Workshop on Machine Learning in Medical Imaging (MLMI) 2014:
- Optimal MAP Parameters Estimation in STAPLE Using Local Intensity Similarity Information
- Subject-Specific Sparse Dictionary Learning for Atlas-Based Brain MRI Segmentation
- A Robust Deep Model for Improved Classification of AD/MCI Patients
- Feature Selection Based on the SVM Weight Vector for Classification of Dementia
- Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural Networks
- A Global Covariance Descriptor for Nuclear Atypia Scoring in Breast Histopathology Images