ABSTRACT
The objective of this article was to evaluate the evidence currently available about the clinical value of artificial intelligence (AI) in breast imaging. Nine experts from the disciplines involved in breast disease management - including physicists and radiologists - convened a meeting on June 3, 2019 to discuss the evidence for the use of this technology in plenary and focused sessions. Prior to the meeting, the group performed a literature review on predefined topics. This paper presents the consensus reached by this working group on recommendations for the future use of AI in breast screening and related research topics.
Subject(s)
Artificial Intelligence , Breast Neoplasms/diagnostic imaging , Algorithms , Breast Density , Early Detection of Cancer , Female , France , Humans , Image Processing, Computer-Assisted , Mammography , Needs Assessment , Precision Medicine , Radiation DosageABSTRACT
The new diagnostic criteria for ankylosing spondylitis include MRI. MRI frequently allows early diagnosis of inflammatory lesions in patients with normal plain films. In addition, MRI is useful for the detection and quantification of inflammatory and structural lesions, and to assess disease activity.
Subject(s)
Image Enhancement , Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Spondylitis, Ankylosing/diagnosis , Adolescent , Adult , Diagnosis, Differential , Female , Humans , Lumbar Vertebrae/pathology , Male , Middle Aged , Sacroiliac Joint/pathology , Sacrum/pathology , Spondylitis, Ankylosing/etiology , Thoracic Vertebrae/pathology , Young AdultABSTRACT
It is becoming increasingly desirable to diagnose ankylosing spondyloarthropathy (AS) at its pre-radiographic stage (prior to the presence of sacro-iliitis on radiographs). MRI plays a key role for early diagnosis of AS, as illustrated by recently proposed international diagnostic criteria (ASAS). MRI of the SI joints is most helpful for early diagnosis; sequences using fat suppression and/or Gadolinium administration are necessary for the detection of inflammatory changes. However, the rate of false positive and false negative results of MR imaging of the SI joints, especially early in the course of the disease, is unknown and requires prudent interpretation of imaging findings. In patients with normal MRI examination of the SI joints and/or if symptoms are limited to the spine, MRI of the lumbar spine with STIR and/or Gadolinium administration may be helpful; again the positive and negative predictive values are unknown, especially early in the course of the disease. The demonstration of inflammatory changes on MRI, at the axial level, could be an indication for anti-TNF treatment, outside of WMA (national and international recommendations). The role of Doppler US, especially for peripheral entheses, remains hypothetical for early diagnosis. The role of MRI for structural evaluation is also being assessed even though radiographs remain the standard of reference. To date, no treatment, conventional or other, has been shown to have a structural effect (aside from limitations related to the methodology of available studies).
