PubMed Health⌕ Search

Biomedical subjects

A Ton

Publications and source records attributed to A Ton.

3 recordsLinked to original sources
PubMedDate not supplied

Image content extraction: application to MR images of the brain.

A system for automatically extracting image content features was developed that combines registration to a labeled atlas with natural language processing of free-text radiology reports. The system was then tested with T1-weighted, spoiled gradient-echo magnetic resonance (MR) imaging studies of the brain performed in nine patients. The locations of 599 structures were visually assessed by an experienced radiologist and compared with the locations indicated by automated output. The in-plane accuracy of the contours was subjectively evaluated as either good, moderate, or poor. The criterion for classifying a structure as correctly located was that 90% or more of all the images containing the structure had to be correctly identified. For 98% of the structures, the images identified by the automated algorithm agreed with those identified by the radiologist, and in 83% of cases, image contours showed a good in-plane overlap. The results of this validation study demonstrate that this combination of registration and natural language processing is accurate in identifying relevant images from brain MR imaging studies. However, the range of applicability of this technique has yet to be determined by applying the technique to a large number of studies.

Algorithms↗
PubMedDate not supplied

Dynamic contrast-enhanced T2*-weighted MR imaging of tumefactive demyelinating lesions.

PURPOSE: Dynamic contrast-enhanced T2*-weighted MR imaging has been helpful in characterizing intracranial mass lesions by providing information on vascularity. Tumefactive demyelinating lesions (TDLs) can mimic intracranial neoplasms on conventional MR images, can be difficult to diagnose, and often result in surgical biopsy for suspected tumor. The purpose of this study was to determine whether dynamic contrast-enhanced T2*-weighted MR imaging can be used to distinguish between TDLs and intracranial neoplasms that share common features on conventional MR images. METHODS: We retrospectively reviewed the conventional and dynamic contrast-enhanced T2*-weighted MR images and medical records of 10 patients with tumefactive demyelinating disease that was diagnosed by either biopsy or strong clinical suspicion supported by laboratory evaluation that included CSF analysis and evoked potential tests. Twelve TDLs in 10 patients and 11 brain tumors that appeared similar on conventional MR images were studied. Relative cerebral blood volume (rCBV) was calculated from dynamic MR data and was expressed as a ratio to contralateral normal white matter. rCBV values from 11 patients with intracranial neoplasms with very similar conventional MR imaging features were used for comparison. RESULTS: The rCBV values of TDLs ranged from 0.22 to 1.79 (n = 12), with a mean of 0.88 +/- 0.46 (SD). The rCBV values of intracranial neoplasms ranged from 1.55 to 19.20 (n = 11), with a mean of 6.47 +/- 6.52. The difference in rCBV values between the two groups was statistically significant (P =.009). The difference in rCBV values between TDLs and primary cerebral lymphomas (n = 4) was less pronounced but was statistically significant (P =.005). CONCLUSION: Dynamic contrast-enhanced T2*-weighted MR imaging is a useful diagnostic tool in differentiating TDLs from intracranial neoplasms and may therefore obviate unnecessary surgical biopsy.

Adolescent↗