Presently, the convergence of medical science and engineering has shifted from theoretical exploration to practical implementation, exemplified by a proliferation of sophisticated medical apparatuses in clinical domains. Amid continuous technological progression and data accumulation, the amalgamation of extensive medical datasets for in-depth analysis and clinical diagnosis has emerged as a prominent focal point in contemporary medical inquiry. The intrinsic characteristics of medical big data, characterized by multi-modality, high dimensionality, complexity, and uncertainty, pose challenges for conventional data processing methodologies in comprehensively extracting and integrating information across diverse data modalities, thereby complicating the diagnostic and therapeutic processes for medical practitioners. However, leveraging multi-modal fusion and analytical technologies enables the effective exploitation of heterogeneous data sources within medical big data, enhancing both data processing efficiency and accuracy, and in turn, providing more robust and thorough support for medical decision-making processes.
Our research focuses on investigating multi-modal fusion technologies that amalgamate imaging omics, radiographic imaging, ultrasonic imaging, genetic sequences, and clinical big data. Leveraging cutting-edge methodologies such as computer graphics, machine learning, pattern recognition, and data mining, we aim to tackle the complexities associated with registration, fusion, information extraction, and cross-domain migration in medical data. By developing a comprehensive system that integrates multi-modal imaging for diagnostic support, our objective is to elevate the precision of imaging-driven diagnostics for prevalent diseases. This effort is geared towards providing indispensable technological support for the swift and accurate execution of clinical diagnosis and treatment.
We invite submissions of original research, methods, reviews, mini-reviews, perspectives, clinical trials, and brief research reports. The specific potential areas of clinical research include, but are not limited to:
● Genomics analysis
● Integration of medical information
● Medical image analysis
● Medical image detection, localization, classification
● Sequence data analysis
● Fusion and feature extraction of cross-modal data
● Cross-domain transfer of multi-center medical data
Keywords:
multimodal fusion, medical images, information extraction, Genomics analysis, clinical information
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Presently, the convergence of medical science and engineering has shifted from theoretical exploration to practical implementation, exemplified by a proliferation of sophisticated medical apparatuses in clinical domains. Amid continuous technological progression and data accumulation, the amalgamation of extensive medical datasets for in-depth analysis and clinical diagnosis has emerged as a prominent focal point in contemporary medical inquiry. The intrinsic characteristics of medical big data, characterized by multi-modality, high dimensionality, complexity, and uncertainty, pose challenges for conventional data processing methodologies in comprehensively extracting and integrating information across diverse data modalities, thereby complicating the diagnostic and therapeutic processes for medical practitioners. However, leveraging multi-modal fusion and analytical technologies enables the effective exploitation of heterogeneous data sources within medical big data, enhancing both data processing efficiency and accuracy, and in turn, providing more robust and thorough support for medical decision-making processes.
Our research focuses on investigating multi-modal fusion technologies that amalgamate imaging omics, radiographic imaging, ultrasonic imaging, genetic sequences, and clinical big data. Leveraging cutting-edge methodologies such as computer graphics, machine learning, pattern recognition, and data mining, we aim to tackle the complexities associated with registration, fusion, information extraction, and cross-domain migration in medical data. By developing a comprehensive system that integrates multi-modal imaging for diagnostic support, our objective is to elevate the precision of imaging-driven diagnostics for prevalent diseases. This effort is geared towards providing indispensable technological support for the swift and accurate execution of clinical diagnosis and treatment.
We invite submissions of original research, methods, reviews, mini-reviews, perspectives, clinical trials, and brief research reports. The specific potential areas of clinical research include, but are not limited to:
● Genomics analysis
● Integration of medical information
● Medical image analysis
● Medical image detection, localization, classification
● Sequence data analysis
● Fusion and feature extraction of cross-modal data
● Cross-domain transfer of multi-center medical data
Keywords:
multimodal fusion, medical images, information extraction, Genomics analysis, clinical information
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.