Please use this identifier to cite or link to this item:
Title: Automatic Annotation, Classification and Retrieval of Traumatic Brain Injury CT Images
Keywords: image annotation, image classification, image retrieval,
Issue Date: 10-Aug-2011
Citation: GONG TIANXIA (2011-08-10). Automatic Annotation, Classification and Retrieval of Traumatic Brain Injury CT Images. ScholarBank@NUS Repository.
Abstract: Due to the advances in medical imaging technology and wider adoption of electronic medical record systems in recent years, medical imaging has become a major tool in clinical trials and a huge amount of medical images are proliferated in hospitals and medical institutions every day. Current research works mainly focus on modality/anatomy classification, or simple abnormality detection. However, the needs to efficiently retrieve the images by pathology classes are great. The lack of large training data makes it difficult for pathology based image classification. To solve problems, we propose two approaches to use both the medical images and associated radiology reports to automatically generate a large training corpus and classify brain CT image into different pathological classes. In the first approach, we extract the pathology terms from the text and annotate the images associated with the text with the extracted pathology terms. The resulting annotated images are used as training data set. We use probabilistic models to derive the correlations between the hematoma regions and the annotations. We also propose a semantic similarity language model to use the intra-annotation correlation to enhance the performance. In testing, we use both the trained probabilistic model and language model to automatically assign pathological annotations to the new cases. In the second approach, we use deeper semantics from both images and text and map the hematoma regions in the images and pathology terms from the text explicitly by extracting and matching anatomical information from both resource. We explore hematoma visual features in both 3D and 2D and classify the images into different classes of pathological changes, so that the images can be searched and retrieved by pathological annotation.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
GongTX.pdf8.34 MBAdobe PDF



Page view(s)

checked on Apr 8, 2019


checked on Apr 8, 2019

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.