About this Research Topic
Magnetic Resonance Imaging (MRI) has become an indispensable tool in the field of medical diagnostics and prognostics, enabling the visualization of anatomical structures and physiological processes in living tissues.
Recent advancements in MRI scanner technology have led to a proliferation of diverse imaging sequences and techniques, resulting in a wealth of parametric maps that offer valuable quantitative information. To fully harness this potential, the integration of Artificial Intelligence (AI) and advanced computational algorithms has emerged as a promising avenue to extract reliable quantitative biomarkers and improve the accuracy and reproducibility of MRI-based diagnoses.
This Research Topic aims to explore the intersection of medical imaging and novel AI technologies, such as transformer AI, generative AI, and graph neural networks, to push the frontiers of quantitative MRI.
We welcome submissions of clinical and preclinical scientific studies that employ AI-based methods to extract quantitative information from MRI data, translating it into medical research or clinical practice. The scope of this collection encompasses a broad range of imaging applications, spanning from the investigation of technical developments in simulated or real data to basic science animal studies and physiological investigations, to clinical assessments of disease therapies.
Key Topics to Be Explored:
1. Optimization of Acquisition Protocols: Authors are encouraged to present studies focused on utilizing AI algorithms to optimize MRI acquisition protocols, enhancing image quality, reducing scan time, and minimizing artifacts. Such advancements have the potential to revolutionize MRI data acquisition, rendering it more efficient and clinically feasible.
2. Image Reconstruction and Post-processing: Novel AI technologies, including generative AI, super-resolution, and denoising techniques, hold great promise in refining image reconstruction and post-processing procedures. By reducing noise and enhancing image quality, these methodologies can unlock new avenues for extracting accurate quantitative data from MRI images.
3. Parameter Estimation and Quantitative Biomarkers: The development of AI-driven computational algorithms for parameter estimation is crucial to accurately depict biological mechanisms and pathological changes within tissues. Papers addressing the challenges of noise, artifacts, and complexity in parameter estimation are welcomed, as they contribute to the overall improvement of quantitative MRI techniques.
4. Radiomics and Radiogenomics: The integration of Radiomics and Radiogenomics with AI holds immense potential in unlocking the hidden information present in MRI data. Research investigating how AI can aid in discovering and interpreting meaningful correlations between imaging features and genetic/clinical data to improve the biological interpretation of radiomic features and to predict disease prognosis and treatment response is highly encouraged.
5. Multimodal Imaging and AI Fusion: With the advent of hybrid MRI-PET systems and novel contrast agents, the scope of multimodal imaging has expanded significantly. Authors are invited to explore the potential of AI in fusing data from different modalities to provide a more comprehensive and accurate understanding of tissue pathophysiology.
This Research Topic endeavors to accelerate the impact of quantitative imaging in MRI biomedical applications through the integration of cutting-edge AI techniques. By evaluating and fine-tuning AI algorithms for various imaging modalities and techniques, we aim to foster a multidisciplinary collaboration that will drive innovation and facilitate the translation of AI-driven quantitative MRI into real-world medical practice.
Topic Editor Nicola Bertolino is employed by Charles River Laboratories. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Recent advancements in MRI scanner technology have led to a proliferation of diverse imaging sequences and techniques, resulting in a wealth of parametric maps that offer valuable quantitative information. To fully harness this potential, the integration of Artificial Intelligence (AI) and advanced computational algorithms has emerged as a promising avenue to extract reliable quantitative biomarkers and improve the accuracy and reproducibility of MRI-based diagnoses.
This Research Topic aims to explore the intersection of medical imaging and novel AI technologies, such as transformer AI, generative AI, and graph neural networks, to push the frontiers of quantitative MRI.
We welcome submissions of clinical and preclinical scientific studies that employ AI-based methods to extract quantitative information from MRI data, translating it into medical research or clinical practice. The scope of this collection encompasses a broad range of imaging applications, spanning from the investigation of technical developments in simulated or real data to basic science animal studies and physiological investigations, to clinical assessments of disease therapies.
Key Topics to Be Explored:
1. Optimization of Acquisition Protocols: Authors are encouraged to present studies focused on utilizing AI algorithms to optimize MRI acquisition protocols, enhancing image quality, reducing scan time, and minimizing artifacts. Such advancements have the potential to revolutionize MRI data acquisition, rendering it more efficient and clinically feasible.
2. Image Reconstruction and Post-processing: Novel AI technologies, including generative AI, super-resolution, and denoising techniques, hold great promise in refining image reconstruction and post-processing procedures. By reducing noise and enhancing image quality, these methodologies can unlock new avenues for extracting accurate quantitative data from MRI images.
3. Parameter Estimation and Quantitative Biomarkers: The development of AI-driven computational algorithms for parameter estimation is crucial to accurately depict biological mechanisms and pathological changes within tissues. Papers addressing the challenges of noise, artifacts, and complexity in parameter estimation are welcomed, as they contribute to the overall improvement of quantitative MRI techniques.
4. Radiomics and Radiogenomics: The integration of Radiomics and Radiogenomics with AI holds immense potential in unlocking the hidden information present in MRI data. Research investigating how AI can aid in discovering and interpreting meaningful correlations between imaging features and genetic/clinical data to improve the biological interpretation of radiomic features and to predict disease prognosis and treatment response is highly encouraged.
5. Multimodal Imaging and AI Fusion: With the advent of hybrid MRI-PET systems and novel contrast agents, the scope of multimodal imaging has expanded significantly. Authors are invited to explore the potential of AI in fusing data from different modalities to provide a more comprehensive and accurate understanding of tissue pathophysiology.
This Research Topic endeavors to accelerate the impact of quantitative imaging in MRI biomedical applications through the integration of cutting-edge AI techniques. By evaluating and fine-tuning AI algorithms for various imaging modalities and techniques, we aim to foster a multidisciplinary collaboration that will drive innovation and facilitate the translation of AI-driven quantitative MRI into real-world medical practice.
Topic Editor Nicola Bertolino is employed by Charles River Laboratories. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Keywords: Artificial Intelligence, Machine learning, Neural Networks, MRI, Quantitative MRI, Parameter Estimation, Image Enhancement, Image Reconstruction, Protocol Optimization, Translational Research
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.
