Due to the vigorous development of medical imaging technologies, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound, Single Photon Emission Computed Tomography (SPECT), Positron Emission Tomography (PET), Color Fundus Photographs (CFP), Fundus AutoFluorescence (FAF), and Optical Coherence Tomography (OCT), etc., a large amount of biomedical brain imaging information was massively accumulated.
Multimodality biomedical brain imaging can provide a better solution to overcome the limitations of the independent techniques and will improve and expand the scope of the information available. However, identifying how to develop new computational models for efficient data processing, analysis and modelling from multimodality brain imaging data is important for clinical applications and analysis. In addition, more and more attention has been drawn to the security issues of biomedical data, such as copyright identification, forgery, and secure storage, etc.
Machine learning has been vastly developed and successfully applied in brain image analysis for developing intelligent diagnosis models. The field of adversarial machine learning has emerged to study the vulnerabilities of machine learning approaches in adversarial settings and to develop techniques to make learning robust to adversarial manipulation.
However, adversarial machine learning with multimodal brain images is still a challenging issue due to the sophisticated computing involved in multimodal images. Therefore, it is necessary to further develop the adversarial machine learning models to tackle the variations in multimodal brain images and the diversity of biophysical-biochemical mechanisms.
We welcome investigators to contribute Original Research articles as well as Review articles that will address adversarial machine learning in the context of multimodal brain imaging. Potential topics include, but are not limited to:
• Reconstruction, registration, segmentation and visualization of multimodal brain images.
• Classification, prediction and regression models of multimodal brain data.
• Fusion of multimodal biomedical data for human organs and tissues recognition.
• Generative adversarial network with multimodal brain images.
• Adversarial machine learning with multimodal brain images.
• Weakly supervised learning for multimodal brain data.
• Cross-modality domain adaption for medical image analysis.
• Deep learning-based forensics for multimodal brain data.
Due to the vigorous development of medical imaging technologies, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Ultrasound, Single Photon Emission Computed Tomography (SPECT), Positron Emission Tomography (PET), Color Fundus Photographs (CFP), Fundus AutoFluorescence (FAF), and Optical Coherence Tomography (OCT), etc., a large amount of biomedical brain imaging information was massively accumulated.
Multimodality biomedical brain imaging can provide a better solution to overcome the limitations of the independent techniques and will improve and expand the scope of the information available. However, identifying how to develop new computational models for efficient data processing, analysis and modelling from multimodality brain imaging data is important for clinical applications and analysis. In addition, more and more attention has been drawn to the security issues of biomedical data, such as copyright identification, forgery, and secure storage, etc.
Machine learning has been vastly developed and successfully applied in brain image analysis for developing intelligent diagnosis models. The field of adversarial machine learning has emerged to study the vulnerabilities of machine learning approaches in adversarial settings and to develop techniques to make learning robust to adversarial manipulation.
However, adversarial machine learning with multimodal brain images is still a challenging issue due to the sophisticated computing involved in multimodal images. Therefore, it is necessary to further develop the adversarial machine learning models to tackle the variations in multimodal brain images and the diversity of biophysical-biochemical mechanisms.
We welcome investigators to contribute Original Research articles as well as Review articles that will address adversarial machine learning in the context of multimodal brain imaging. Potential topics include, but are not limited to:
• Reconstruction, registration, segmentation and visualization of multimodal brain images.
• Classification, prediction and regression models of multimodal brain data.
• Fusion of multimodal biomedical data for human organs and tissues recognition.
• Generative adversarial network with multimodal brain images.
• Adversarial machine learning with multimodal brain images.
• Weakly supervised learning for multimodal brain data.
• Cross-modality domain adaption for medical image analysis.
• Deep learning-based forensics for multimodal brain data.