Hemorrhage detection and segmentation in traumatic pelvic injuries.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2012;
2012:898430. [PMID:
22919433 PMCID:
PMC3418697 DOI:
10.1155/2012/898430]
[Citation(s) in RCA: 11] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/30/2012] [Accepted: 06/14/2012] [Indexed: 12/27/2022]
Abstract
Automated hemorrhage detection and segmentation in traumatic pelvic injuries is vital for fast and accurate treatment decision making. Hemorrhage is the main cause of deaths in patients within first 24 hours after the injury. It is very time consuming for physicians to analyze all Computed Tomography (CT) images manually. As time is crucial in emergence medicine, analyzing medical images manually delays the decision-making process. Automated hemorrhage detection and segmentation can significantly help physicians to analyze these images and make fast and accurate decisions. Hemorrhage segmentation is a crucial step in the accurate diagnosis and treatment decision-making process. This paper presents a novel rule-based hemorrhage segmentation technique that utilizes pelvic anatomical information to segment hemorrhage accurately. An evaluation measure is used to quantify the accuracy of hemorrhage segmentation. The results show that the proposed method is able to segment hemorrhage very well, and the results are promising.
Collapse