Abstract | ||
---|---|---|
Recent advances in imaging have lead to increases in the number of images/study. Automated methods to select relevant images are critical to effectively convey study results. The proposed method combines natural language processing (NLP) and automatic structure localization to identify relevant images of a MR brain study. NLP extracts relevant locations of findings. Two algorithms were implemented and evaluated for structure localization. The first method involves registration of patient dataset to a labeled atlas. The second method involves an eigenimage search using a training set of images. A prototype was developed and tested on MR brain studies of nine patients. With the registration method, slices containing the relevant structure agreed with expert selection in 98% of cases. Structure localization by eigenimage search was able to locate the lateral ventricles correctly in all the test cases. The proposed method provides an accurate method for identifying relevant slices of an imaging study. |
Year | Venue | Keywords |
---|---|---|
2001 | JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION | natural language processing,algorithms,magnetic resonance imaging |
Field | DocType | Issue |
Training set,Computer vision,Computer science,Test case,Artificial intelligence,Image selection | Conference | SUPnan |
ISSN | Citations | PageRank |
1067-5027 | 1 | 0.37 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Usha Sinha | 1 | 158 | 16.11 |
Ricky K. Taira | 2 | 459 | 240.06 |
Hooshang Kangarloo | 3 | 104 | 17.48 |