“Healthcare systems are trying to evolve and benefit from
cloud services. This is because information technologies and
information-rich services such as medical imaging can be
greatly enhanced by use of cloud technologies. Collaboration among medical institutions and hospitals is required for sharing medical data and images. Patient data can be easily stored in virtual archives that are accessible by different
healthcare providers, thus facilitating data sharing and significantly reducing local storage requirements. Privacy issues arise from use of cloud systems for confidential personal data.”
” Nevertheless, there are significant advantages in the interpretation of difficult clinical cases when employing cloud computing services. Experts from different medical fields can consult on the diagnosis from around the world.
Continuing education and teaching efforts can also be facilitated by the cloud. Teaching files can be accessed by several institutions, and training courses can be co-organized to provide shared access to learning tools such as software, presentations, and medical images of clinical interest.”
“Location independence means that physicians can read\ studies created at other hospitals or outpatient centers. They can read from home, office, or from different locations inside or outside hospitals or clinics. Further, physicians can
refer patients to other physicians or request consults from physicians at different locations, with the consultations taking place through the cloud.”
“Three recent technological developments have made Cloud
PACS possible: (1) remote visualization, which moves much
of the graphics processing to the cloud and decreases the
amount of data that has to be moved from the cloud to the
end-point device, (2) increased processing power and resolution of end-point devices, and (3) maturation of HTML5,
CSS3, and JavaScript to the point where zero-footprint,
diagnostic-quality, and browser-based applications are feasible. These developments have eliminated the need for highend workstations and have also reduced networking throughput requirements. Because image rendering occurs at the
server side, fewer data must be transmitted to the client.”
“Medical image computing (MIC) is an interdisciplinary field at the intersection of computer science, information engineering, electrical engineering, physics, mathematics and medicine.
Segmentation is the process of partitioning an image into different meaningful segments. “
- Atlas-Based Segmentation:
- Shape-Based Segmentation:
- Image-Based segmentation
- Interactive Segmentation:
- Subjective surface Segmentation:
Image Registration is a process that searches for the correct alignment of images
Visualization
Atlases:
Single Template
Multiple Templates
Statisitcal Analysis
Group Analysis
Classification
Custering
Shape Analysis
Longitudinal Studies:
Multi-modal Image Processing for Imaging and Diagnosis
“Multi-modal imaging refers to (i) different measurements at a single tomographic system (e.g., MRI and functional MRI), (ii) measurements at different tomographic systems (e.g., computed tomography (CT), positron emission tomography (PET), and single photon emission computed tomography (SPECT)), and (iii) measurements at integrated tomographic systems (PET/CT, PET/MR). “
ROADMAPS TO THE FUTURE:
Scanning the Future of Medical Imaging: Journal of the American College of Radiology 16(4) · December 2018
Hot Market Trend 1: AI and ML
Hot Market Trend 2: Blockchain
3-D Visualization, Virtual Reality, and Image-GuidedIntervention.
Intra-operative Technologies
Nuclear Imaging.
https://www.researchgate.net/publication/329380035_Scanning_the_Future_of_Medical_Imaging
Rdiology Publishes Roadmap for AI in Medical Imaging
ITN: Imaging Technology News – April 16, 2019
Research priorities:
- New image reconstruction methods that efficiently produce images suitable for human interpretation from source data;
- Automated image labeling and annotation methods, including information extraction from the imaging report, electronic phenotyping and prospective structured image reporting;
- New machine learning methods for clinical imaging data, such as tailored, pre-trained model architectures and distributed machine learning methods;
- Machine learning methods that can explain the advice they provide to human users (so-called explainable artificial intelligence); and
- Validated methods for image de-identification and data sharing to facilitate wide availability of clinical imaging data sets.
https://www.itnonline.com/content/radiology-publishes-roadmap-ai-medical-imaging
REFERENCES:
https://en.wikipedia.org/wiki/Medical_image_computing
https://pdfs.semanticscholar.org/07b1/4c6e4f1ba9c9b1e7a9205d16c8588e137453.pdf
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3782694/
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4532640/
Click to access 2008-09-procAmerPhilSoc_Bradley-MedicalImagingHistory.pdf