In the last decade, radiomics has proved its capability to quantitatively and noninvasively discover clinically relevant inter/intra-patient patterns not directly detectable from radiological images.
Radiomics consists of the extraction of high-throughput quantitative features from Regions of interest (ROIs) drawn into radiological imaging, such as computed tomography (CT), positron emission tomography (PET), or magnetic resonance imaging (MRI), and in the subsequent mining of such features to create models able to predict or characterize clinical outcomes.
Radiomics has recently gained a renewed wave of interest thanks to the novel developments of artificial intelligence. More and more networks are made publicly available speeding up the process of ROIs delineation that has always been considered the bottleneck of radiomic analysis.
Even if data is not information, the accuracy of these automatic segmentation models largely depends on the number of data involved in the training. Therefore, more and more groups are investing time and resources to deploy reliable big data repositories based on cloud infrastructures.
This Research Topic aims to showcase the latest methodological developments involved in radiomic analysis with a particular interest in the dissemination of code and data.
We welcome research papers focusing on novel methodological developments that deal with data augmentation, data simulation, automatic segmentation, and mining.
Specifically, this includes topics such as, but not limited to:
- Image registration
- Image segmentation
- Image fusion and synthesis
- Image acquisition and reconstruction
- Novel deep learning methods for medical imaging
- Statistics for medical imaging
- Texture analysis
- Big data analytics
- Information visualization
- Imaging and genomics
- Multimodal image processing and analysis
- Functional and molecular imaging
- Generative modeling
- Learning with noisy or limited data
- Statistical and mathematical models
- Shape modeling
- Machine vision and augmented reality
- Computer-aided detection and diagnosis
- Computational anatomy and physiology
- Transfer learning, domain adaptation, data harmonization
- Geometric learning, geometric deep learning, geometric statistics
- Cloud infrastructure
- New public available repositories
In the last decade, radiomics has proved its capability to quantitatively and noninvasively discover clinically relevant inter/intra-patient patterns not directly detectable from radiological images.
Radiomics consists of the extraction of high-throughput quantitative features from Regions of interest (ROIs) drawn into radiological imaging, such as computed tomography (CT), positron emission tomography (PET), or magnetic resonance imaging (MRI), and in the subsequent mining of such features to create models able to predict or characterize clinical outcomes.
Radiomics has recently gained a renewed wave of interest thanks to the novel developments of artificial intelligence. More and more networks are made publicly available speeding up the process of ROIs delineation that has always been considered the bottleneck of radiomic analysis.
Even if data is not information, the accuracy of these automatic segmentation models largely depends on the number of data involved in the training. Therefore, more and more groups are investing time and resources to deploy reliable big data repositories based on cloud infrastructures.
This Research Topic aims to showcase the latest methodological developments involved in radiomic analysis with a particular interest in the dissemination of code and data.
We welcome research papers focusing on novel methodological developments that deal with data augmentation, data simulation, automatic segmentation, and mining.
Specifically, this includes topics such as, but not limited to:
- Image registration
- Image segmentation
- Image fusion and synthesis
- Image acquisition and reconstruction
- Novel deep learning methods for medical imaging
- Statistics for medical imaging
- Texture analysis
- Big data analytics
- Information visualization
- Imaging and genomics
- Multimodal image processing and analysis
- Functional and molecular imaging
- Generative modeling
- Learning with noisy or limited data
- Statistical and mathematical models
- Shape modeling
- Machine vision and augmented reality
- Computer-aided detection and diagnosis
- Computational anatomy and physiology
- Transfer learning, domain adaptation, data harmonization
- Geometric learning, geometric deep learning, geometric statistics
- Cloud infrastructure
- New public available repositories