Biomedical image processing has seen a significant improvement due to the availability of advanced technologies to capture high resolution images. This leads to demand for automated segmentation of "Regions of Interest" in the images and its analysis from different perspectives. Supervised segmentation techniques require extensive training data, are not generic, and cannot be used for different types of applications. In contrast, fully automated segmentation techniques work without any intervention from the user and the recent surge of deep learning based approaches have shown very promising results. Furthermore, researchers have come up with semantic segmentation solutions using deep neural networks and currently there is a need for in-depth analysis of different deep learning architectures on diverse datasets to check their efficacy and computational efficiency.
Overall, the development of unsupervised techniques that can be used for multiple applications even in the absence of specific ground truth will be of key importance and these techniques should be able to work on multiple modalities ranging from CT SCANS, Ultrasounds, MRI, etc. Even though multiple images are captured during the analysis of patients, most of the developed techniques do not consider the sequence of these images and there is a need to develop a sequence-spatial model for better understanding of the underlying disease patterns. For the same patient, once the data of all previous and current images are obtained, then we should be able to correlate these to find the progress or recovery from a disease state. In order to achieve this, we need to verify the efficacy of such sequence based deep learning biomedical image segmentation model and if it can auto-configure itself as per the requirement of different image modalities.
We welcome manuscripts on any aspect of biomedical image processing and analysis. Here, biomedical image processing includes all kinds of biomedical images captured using different modalities such as MRI, CT-SCAN, Ultrasound, X-Rays, etc. It covers preprocessing and analysis of these images for better diagnosis. All research addressing image pre-processing, segmentation, thresholding, detection, marking, classification system, prediction, noise removal and regeneration will be considered. We welcome submissions related to the following sub-topics:
• Biomedical Image segmentation
• Medical Image Analysis
• Deep learning Techniques for Medical Images
• Deep learning for Medical Image Reconstructions
• Noise removal from Medical Images
• Photo-acoustics Image based Medical Applications
• Digital Pathology Image Analysis
• Supervised, Semi-Supervised and Unsupervised Learning Approaches
• Self-Attention based Active Learning Framework
• Sequence Modeling and Fusion Approaches
• Real Time Guiding based Approaches
Biomedical image processing has seen a significant improvement due to the availability of advanced technologies to capture high resolution images. This leads to demand for automated segmentation of "Regions of Interest" in the images and its analysis from different perspectives. Supervised segmentation techniques require extensive training data, are not generic, and cannot be used for different types of applications. In contrast, fully automated segmentation techniques work without any intervention from the user and the recent surge of deep learning based approaches have shown very promising results. Furthermore, researchers have come up with semantic segmentation solutions using deep neural networks and currently there is a need for in-depth analysis of different deep learning architectures on diverse datasets to check their efficacy and computational efficiency.
Overall, the development of unsupervised techniques that can be used for multiple applications even in the absence of specific ground truth will be of key importance and these techniques should be able to work on multiple modalities ranging from CT SCANS, Ultrasounds, MRI, etc. Even though multiple images are captured during the analysis of patients, most of the developed techniques do not consider the sequence of these images and there is a need to develop a sequence-spatial model for better understanding of the underlying disease patterns. For the same patient, once the data of all previous and current images are obtained, then we should be able to correlate these to find the progress or recovery from a disease state. In order to achieve this, we need to verify the efficacy of such sequence based deep learning biomedical image segmentation model and if it can auto-configure itself as per the requirement of different image modalities.
We welcome manuscripts on any aspect of biomedical image processing and analysis. Here, biomedical image processing includes all kinds of biomedical images captured using different modalities such as MRI, CT-SCAN, Ultrasound, X-Rays, etc. It covers preprocessing and analysis of these images for better diagnosis. All research addressing image pre-processing, segmentation, thresholding, detection, marking, classification system, prediction, noise removal and regeneration will be considered. We welcome submissions related to the following sub-topics:
• Biomedical Image segmentation
• Medical Image Analysis
• Deep learning Techniques for Medical Images
• Deep learning for Medical Image Reconstructions
• Noise removal from Medical Images
• Photo-acoustics Image based Medical Applications
• Digital Pathology Image Analysis
• Supervised, Semi-Supervised and Unsupervised Learning Approaches
• Self-Attention based Active Learning Framework
• Sequence Modeling and Fusion Approaches
• Real Time Guiding based Approaches