학술논문
Automated lymph node detection and classification on breast and prostate cancer SPECT-CT images
Document Type
Conference
Author
Source
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE. :3431-3434 Aug, 2011
Subject
Language
ISSN
1557-170X
1094-687X
1558-4615
1094-687X
1558-4615
Abstract
We present a novel detection and classification method to process SPECT-CT images representing breast and prostate lymph nodes. Lymph nodes are those nodes that are near the primer tumor and may become cancerous in time, hence their early detection is a key factor for the successful treatment of the patient. Prior methods focus on the visual aid to manually detect the lymph nodes which still makes the process time-consuming. Other solutions segment the lymph nodes only on CT, where the small lymph nodes may not be located accurately. Our solution processed both SPECT and CT data to provide an accurate classification of all SPECT hot spots. The method has been validated on a huge amount of medical data. Results show that our method is a very effective tool to support physicians working with related images in the field of nuclear medicine.