Clinical radiology
-
Artificial intelligence (AI) has been present in some guise within the field of radiology for over 50 years. The first studies investigating computer-aided diagnosis in thoracic radiology date back to the 1960s, and in the subsequent years, the main application of these techniques has been the detection and classification of pulmonary nodules. ⋯ The article reviews current state-of-the-art applications of AI and in detection, classification, and follow-up of pulmonary nodules and how deep-learning techniques might influence these going forward. Finally, we postulate the impact of these advancements on the role of radiologists and the importance of radiologists in the development and evaluation of these techniques.
-
This article reviews current limitations and future opportunities for the application of computer-aided detection (CAD) systems and artificial intelligence in breast imaging. Traditional CAD systems in mammography screening have followed a rules-based approach, incorporating domain knowledge into hand-crafted features before using classical machine learning techniques as a classifier. The first commercial CAD system, ImageChecker M1000, relies on computer vision techniques for pattern recognition. ⋯ This requires a large and representative dataset for testing and assessment of the reader's interaction with the tools. A cost-effectiveness assessment should be undertaken, with a large feasibility study carried out to ensure there are no unintended consequences. AI-CAD systems should incorporate explainable AI in accordance with the European Union General Data Protection Regulation (GDPR).
-
Imaging of middle-ear cholesteatoma with diffusion-weighted imaging (DWI) magnetic resonance imaging (MRI), and inner-ear endolymphatic hydrops (in Ménière's disease) with post-gadolinium high-resolution MRI, are reviewed. DWI MRI provides for a more specific diagnosis of tympano-mastoid cholesteatoma. There is an established and increasing role of DWI MRI in detecting both primary and postoperative cholesteatoma, localising disease, and planning surgery. ⋯ There is now increasing data to validate the application of three-dimensional (3D)-fluid attenuated inversion recovery (FLAIR) sequences, performed at 4 hours post-intravenous gadolinium, in the setting of potential Ménière's disease. The clinical context and the evolution of these MRI techniques are discussed. Current MRI-based grading schemes for endolymphatic hydrops are described, together with the available data on their clinical implications.
-
There are multiple emerging advanced computed tomography (CT) applications for the evaluation of the neck, many based on dual-energy CT (DECT). DECT is an advanced form of CT in which scan acquisition is performed at two different energies, enabling spectral tissue characterisation beyond what is possible with conventional single-energy CT and potentially providing a new horizon for quantitative analysis and tissue characterisation, particularly in oncological imaging. ⋯ This will then be followed by a review of different clinical applications. The focus will be on oncological imaging, but artefact reduction and other miscellaneous applications will also be discussed.
-
Maxillofacial imaging encompasses radiology of the teeth and jaws, including the temporomandibular joints. Modalities used include intra-oral radiographs, panoramic tomography, cephalograms, cone-beam computed tomography, computed tomography, magnetic resonance imaging, ultrasound, and radionuclide imaging. ⋯ Osteonecrosis of the jaws may follow radiotherapy or the use of bisphosphonates and other drugs. Imaging of the temporomandibular joints and the potential role of imaging in obstructive sleep apnoea are also discussed.