Dr. Gurcan will present a tutorial at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2010 entitled “Biomedical Image Processing and Analysis Techniques.” ( http://www.icassp2010.org/Tutorial_03.asp)
Biomedical image processing and analysis requires coordinated efforts of medical professionals, algorithmic and software engineers, and statisticians. Basic image processing techniques are frequently used in every aspect of the development from initial pre-processing techniques for noise reduction, to segmentation of lesions, to registration of lesions. Recent advances in hardware and software have made it possible to create digital scans of whole slides. These images are relatively large (100k x 100k) and in color, hence processing them present new challenges. Similarly, new computed tomography and magnetic resonance imaging scanners produce thousands of slices of images. The processing need for these images are enormous. Although biomedical image analysis research is getting increasingly popular, it does not receive sufficient coverage in most curriculums. This tutorial will introduce the current challenges and recent advances and innovations in this newly developing area while reviewing several frequently used image processing techniques in this context. It will be taught from the perspective of a researcher, who carried out biomedical image analysis and processing research for over 10 years both in academia and industry.
While most images can be easily processed using a high-end computer, very large scale microscopic images require special processing techniques. This tutorial will talk about virtual microscopy, cluster/grid computing and parallel processing techniques. Some novel computational architectures such as general purpose GPUs and cell blades (e.g. those in Sony PlayStation™ 3) are extremely suitable to process these types of images, however, they require special coding techniques. It will also discuss how some of microscopic image processing can be done using these novel computational architectures, which can also be used for efficient processing of all kinds of images.
Biomedical image processing and analysis requires coordinated efforts of medical professionals, algorithmic and software engineers, and statisticians. Basic image processing techniques are frequently used in every aspect of the development from initial pre-processing techniques for noise reduction, to segmentation of lesions, to registration of lesions. Recent advances in hardware and software have made it possible to create digital scans of whole slides. These images are relatively large (100k x 100k) and in color, hence processing them present new challenges. Similarly, new computed tomography and magnetic resonance imaging scanners produce thousands of slices of images. The processing need for these images are enormous. Although biomedical image analysis research is getting increasingly popular, it does not receive sufficient coverage in most curriculums. This tutorial will introduce the current challenges and recent advances and innovations in this newly developing area while reviewing several frequently used image processing techniques in this context. It will be taught from the perspective of a researcher, who carried out biomedical image analysis and processing research for over 10 years both in academia and industry.
While most images can be easily processed using a high-end computer, very large scale microscopic images require special processing techniques. This tutorial will talk about virtual microscopy, cluster/grid computing and parallel processing techniques. Some novel computational architectures such as general purpose GPUs and cell blades (e.g. those in Sony PlayStation™ 3) are extremely suitable to process these types of images, however, they require special coding techniques. It will also discuss how some of microscopic image processing can be done using these novel computational architectures, which can also be used for efficient processing of all kinds of images.
Comments
Post a Comment