A representation and classification scheme for tree-like structures in medical images : Analyzing the branching pattern of ductal trees in x-ray galactograms
(2009) In IEEE Transactions on Medical Imaging 28(4). p.487-493- Abstract
We propose a multistep approach for representing and classifying tree-like structures in medical images. Tree-like structures are frequently encountered in biomedical contexts; examples are the bronchial system, the vascular topology, and the breast ductal network. We use tree encoding techniques, such as the depth-first string encoding and the Prüfer encoding, to obtain a symbolic string representation of the tree's branching topology; the problem of classifying trees is then reduced to string classification. We use the tf-idf text mining technique to assign a weight of significance to each string term (i.e., tree node label). Similarity searches and k-nearest neighbor classification of the trees is performed using the tf-idf weight... (More)
We propose a multistep approach for representing and classifying tree-like structures in medical images. Tree-like structures are frequently encountered in biomedical contexts; examples are the bronchial system, the vascular topology, and the breast ductal network. We use tree encoding techniques, such as the depth-first string encoding and the Prüfer encoding, to obtain a symbolic string representation of the tree's branching topology; the problem of classifying trees is then reduced to string classification. We use the tf-idf text mining technique to assign a weight of significance to each string term (i.e., tree node label). Similarity searches and k-nearest neighbor classification of the trees is performed using the tf-idf weight vectors and the cosine similarity metric. We applied our approach to characterize the ductal tree-like parenchymal structure in X-ray galactograms, in order to distinguish among different radiological findings. Experimental results demonstrate the effectiveness of the proposed approach with classification accuracy reaching up to 86%, and also indicate that our method can potentially aid in providing insight to the relationship between branching patterns and function or pathology.
(Less)
- author
- Megalooikonomou, Vasileios ; Barnathan, Michael ; Kontos, Despina ; Bakic, Predrag R. LU and Maidment, Andrew D.A.
- publishing date
- 2009-04
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Branching pattern analysis, Characterization, Classification, Tree-like structures, X-ray galactography
- in
- IEEE Transactions on Medical Imaging
- volume
- 28
- issue
- 4
- article number
- 4591399
- pages
- 7 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- pmid:19272984
- scopus:63849260743
- ISSN
- 0278-0062
- DOI
- 10.1109/TMI.2008.929102
- language
- English
- LU publication?
- no
- id
- 9c7dc836-84c3-4517-91ac-26abb3202c90
- date added to LUP
- 2020-11-07 13:18:31
- date last changed
- 2024-01-02 21:16:00
@article{9c7dc836-84c3-4517-91ac-26abb3202c90, abstract = {{<p>We propose a multistep approach for representing and classifying tree-like structures in medical images. Tree-like structures are frequently encountered in biomedical contexts; examples are the bronchial system, the vascular topology, and the breast ductal network. We use tree encoding techniques, such as the depth-first string encoding and the Prüfer encoding, to obtain a symbolic string representation of the tree's branching topology; the problem of classifying trees is then reduced to string classification. We use the tf-idf text mining technique to assign a weight of significance to each string term (i.e., tree node label). Similarity searches and k-nearest neighbor classification of the trees is performed using the tf-idf weight vectors and the cosine similarity metric. We applied our approach to characterize the ductal tree-like parenchymal structure in X-ray galactograms, in order to distinguish among different radiological findings. Experimental results demonstrate the effectiveness of the proposed approach with classification accuracy reaching up to 86%, and also indicate that our method can potentially aid in providing insight to the relationship between branching patterns and function or pathology.</p>}}, author = {{Megalooikonomou, Vasileios and Barnathan, Michael and Kontos, Despina and Bakic, Predrag R. and Maidment, Andrew D.A.}}, issn = {{0278-0062}}, keywords = {{Branching pattern analysis; Characterization; Classification; Tree-like structures; X-ray galactography}}, language = {{eng}}, number = {{4}}, pages = {{487--493}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Transactions on Medical Imaging}}, title = {{A representation and classification scheme for tree-like structures in medical images : Analyzing the branching pattern of ductal trees in x-ray galactograms}}, url = {{http://dx.doi.org/10.1109/TMI.2008.929102}}, doi = {{10.1109/TMI.2008.929102}}, volume = {{28}}, year = {{2009}}, }