Search

In the previous chapter we discussed imaging methods that use relatively standard techniques available on most clinical MRI scanners. In this chapter we focus on cutting edge techniques for spinal MRI.

Image exams are a fundamental tool in health care for decision making. A challenge in Content-based image retrieval CBIR is to provide a timely answer that complies with the specialist's expectation. There are different systems with different techniques to CBIR in literature. However, even with so much research, there are still particular challenges to be overcame, such as the semantic gap. In this paper, we presented a new spinal-image comparison method based on the perception of specialists during his/her analysis of spine lesions. We take advantage of a color extractor and propose a shape descriptor considering the visual patterns that the radiologists use to recognize anomalies in images. The experiments shown that our approach achieved promising results, testifying that the automatic comparison of images should consider all relevant visual aspects and comparisons' criteria, which are defined by the specialists.

Segmentation of bony structures plays an important role in image-guided surgery of the spine. In this paper we give a first approach to the segmentation of vertebral bodies from 2D sagittal MR images of the spine using the normalized cuts (Ncut) segmentation technique [1], and the Nystrom approximation method [2].

MRI of the brain in 18 patients (9 boys, 9 girls, mean age 9.4 years) with medulloblastomas were reviewed for signal intensity, contrast enhancement, presence of cyst and necrosis, and subarachnoid dissemination. In 14 patients, post-operative spinal MRI was reviewed for staging and therapeutic planning. Medulloblastomas showed low-to-intermediate signal intensity on T1-weighted images and moderately high signal intensity on T2-weighted images, compared to cerebellar white matter. Inhomogenous contrast enhancement was noted in 13 patients (72.2%). Cyst and necrosis within tumours were seen in 15 patients (83.3%). Subarachnoid dissemination was noted in 11 patients (61.1%), 6 demonstrated intracranial and 2 intraspinal disseminations. Three had both intracranial and intraspinal disseminations. Other associated findings included intratumoral haemorrhage (11.1%), peritumoral oedema (44.4%), tonsillar herniation (44.4%), hydrocephalus (88.9%) anc calcification (44.4%). Gd-DTPA-enhanced MRI of brain and spine was a useful diagnostic modality in pre-operative diagnosis and in post-operative staging of medulloblastomas.

We have examined 80 patients with systemic lupus erythematosus. Of 127 head MRI studies 75 showed parenchymal changes. Brain MRI findings were classified roughly into six groups: multiple high-intensity spots on T2-weighted images, 28 studies; infarction, 33 studies; transient high-intensity lesions on T2-weighted images, 8 studies; sinus thrombosis, 3 studies (1 patient); diffuse intracranial calcification, 2 studies; inflammation, 1 study. Significant differences were noted between MRI positive and MRI negative patients with regard to age and duration of the disease. Patients with MRI lesions were significantly older than MRI negative patients, and had a longer duration of the disease. There was no significant difference in the two groups with regard to lupus anticoagulant and the level of anticardiolipin antibody.