Artificial intelligence technology promises to redefine the practice of radiology. However, it exists in a nascent phase and remains largely untested in the clinical space. This nature is both a…
Natural language processing (NLP) is a subfield of computer science and linguistics that can be applied to extract meaningful information from radiology reports. Symbolic NLP is rule based and well…
Key points • With the rapidly expanding use cases for AI, there is a growing need for proper evaluation of developed algorithms. • Although the external test set is the…
Machine learning is an important tool for extracting information from medical images. Deep learning has made this more efficient by not requiring an explicit feature extraction step and in some…
Chest CT Pathology Segments of the Lung It is especially important to be able to identify the segments of the lungs in CT images if bronchioscopy is planned for biopsy…
Abdominal CT In general, all soft-tissue organs should appear uniform and be well defined, except when partial volume effects occur (cf. p.14) or during the early arterial phase of CM…
CT Angiography Bringing out the information contained in images of CT angiography requires a review using different perspectives (MIP = maximum intensity projection), different reconstruction planes (MPR = multiplanar reconstruction)…
PET/CT: Introduction A PET/CT diagnostic study combines functional biochemical imaging (PET = Positron Emission Tomography) with morphologic imaging (CT) in a single examination. The examination makes it possible to simultaneously…
Spinal Column: Skeletal Pathology The occipital condyles at the base of the skull articulate with the first vertebra, the atlas (50a), which is the only vertebra to lack a body….
Contrast Injectors Indications In contrast-enhanced CT and MRI, it is desirable to have a homogeneous intravascular distribution of the contrast medium (CM) for the duration of the contrast study to…
