Spotlight on Bioimaging and Signal Processing

The Bio-Imaging and Signal Processing Technical Committee (BISP-TC) of the IEEE Signal Processing Society (SPS) promotes activities in the broad technical areas of computerized image and signal processing with a clear focus on applications in biology and medicine. Specific topics of interest include image reconstruction, compressed sensing, superresolution, image restoration, re - gistration and segmentation, pattern recognition, object detection, localization, tracking, quantification and classification, machine learning, multimodal image and signal fusion, analytics, visualization, and statistical modeling. Application areas covered by the TC include biomedical imaging from nano to macroscale, encompassing all modalities of molecular imaging and microscopy, anatomical imaging, and functional imaging, as well as genomic signal processing, computational biology, and bioinformatics, with the ultimate overarching aim of enabling precision medicine.

 

Since its creation in 2004, the TC has served as the expert review and organization panel for the IEEE International Symposium on Biomedical Imaging (ISBI) as well as the bioimaging and signal processing tracks of the IEEE International Conference on Acoustics, Speech, and Signal Processing and the IEEE International Conference on Image Processing. Over the years, members of the TC have played leading roles in these flagship SPS meetings and organized numerous workshops, special sessions, and tutorials to deepen the understanding of theoretical concepts, broaden their range of applications, and highlight emerging hot topics in the field.

 

The TC maintains strong ties with other communities within SPS, the IEEE, and beyond. For example, multiple past and present members are active in the SPS Computational Imaging Special Interest Group, the Engineering in Medicine and Biology Society Biomedical Imaging and Image Processing TC, the cross-Society IEEE Life Sciences Technical Community, the Medical Image Computing and Computer-Assisted Intervention Society (MICCAI), the International Society for Optical Engineering, and the Society for Industrial and Applied Mathematics. Many TC members also serve on the editorial boards of SPS publications, such as IEEE Transactions on Medical Imaging, IEEE Transactions on Computational Imaging, IEEE Transactions on Image Processing, and IEEE Transactions on Signal Processing.

 

Computerized image and signal processing technologies have been key to biological research and medical diagnostics for at least a half-century. Revolutionary inventions such as magnetic resonance imaging (2003 Nobel Prize), superresolution microscopy (2014 Nobel Prize), cryo-electron microscopy (2017 Nobel Prize), and, in a sense, even the sequencing of the human genome (which will inevitably be awarded a Nobel Prize) all relied on or spurred the development of image and signal processing. As a con-sequence, we now live in an era that is flooded with data produced by imaging and sequencing devices and craves powerful solutions to extract maximum knowledge from them. Undoubtedly, machine-learning approaches, in particular, deep learning using artificial neural networks, will be an essential ingredient of these solutions and are already pervading the field, outperforming classical image and signal processing approaches in many tasks. But many open questions remain as to how they can be optimally designed and trained in a semi- or weakly supervised manner to get around the need for excessive human input in data annotation and to improve their transferability between applications.