Publication:
Understanding Domain Knowledge in Initialization Method for K-Mean Clustering Algorithm in Medical Images
Understanding Domain Knowledge in Initialization Method for K-Mean Clustering Algorithm in Medical Images
| cris.author.scopus-author-id | 57204510554 | |
| cris.author.scopus-author-id | 36656186800 | |
| cris.author.scopus-author-id | 6603280096 | |
| cris.author.scopus-author-id | 56764435700 | |
| cris.author.scopus-author-id | 55860800560 | |
| cris.author.scopus-author-id | 56178375200 | |
| cris.author.scopus-author-id | 56464318100 | |
| cris.author.scopus-author-id | 56405592700 | |
| cris.virtual.department | Universiti Malaysia Perlis | |
| cris.virtual.department | Universiti Malaysia Perlis | |
| cris.virtual.department | Universiti Malaysia Perlis | |
| cris.virtual.department | Universiti Malaysia Perlis | |
| cris.virtualsource.department | 86103f6c-1c6a-4a49-a699-87dc2124b229 | |
| cris.virtualsource.department | f706deee-19e1-46a5-a4e8-25c727ea8dbc | |
| cris.virtualsource.department | 7d1ed5ce-c97b-4775-b51c-ce3dcc32f6b9 | |
| cris.virtualsource.department | e284768e-e25f-42bb-a739-df05abb78f40 | |
| dc.contributor.author | Tan X.J. | |
| dc.contributor.author | Nazahah Mustafa | |
| dc.contributor.author | Mohd Yusoff Mashor | |
| dc.contributor.author | Ab Rahman K.S. | |
| dc.contributor.author | Wan Zuki Azman Wan Muhamad | |
| dc.contributor.author | Leow Wai Zhe | |
| dc.contributor.author | Cheor Wai Loon | |
| dc.contributor.author | Oung Qi Wei | |
| dc.date.accessioned | 2024-09-27T08:31:06Z | |
| dc.date.available | 2024-09-27T08:31:06Z | |
| dc.date.issued | 2022-01-01 | |
| dc.description.abstract | This work serves as a preliminary study to investigate and identify the applicability of domain knowledge as an initialization method for K-Mean (KM), typically in medical images. For this purpose, 20 breast histopathology images were used as data set and the evaluations are focused on the clustering of the hyperchromatic nucleus. The iteration numbers and clustering results (i.e., accuracy, over-segmentation, and under-segmentation) are benchmarked with KM++ and the conventional random initialization method. The domain knowledge initialization method is found promising by achieving lower iteration numbers (<9), higher percentage in accuracy (85.5% (±2.27)), and lower percentages in over-segmentation (8.25% (±2.23)), and under-segmentation (7.00% (±2.14)). From this study, we hypothesize that the domain knowledge initialization method has the potential to be implemented as an initialization method and is posited to overperform some established initialization methods, typically for clustering tasks in medical images. | |
| dc.identifier.doi | 10.1007/978-981-16-8690-0_71 | |
| dc.identifier.isbn | [9789811686894] | |
| dc.identifier.scopus | 2-s2.0-85126965697 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14170/4822 | |
| dc.relation.grantno | NMRR-17-281-34236 | |
| dc.relation.ispartof | Lecture Notes in Electrical Engineering | |
| dc.relation.ispartofseries | Lecture Notes in Electrical Engineering | |
| dc.relation.issn | 18761100 | |
| dc.subject | Clustering | Data analysis | Image processing | Initialization method | K-Mean (KM) | Medical image | |
| dc.title | Understanding Domain Knowledge in Initialization Method for K-Mean Clustering Algorithm in Medical Images | |
| dc.type | Book Series | |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 817 | |
| oaire.citation.startPage | 805 | |
| oaire.citation.volume | 842 | |
| oairecerif.affiliation.orgunit | Tunku Abdul Rahman University of Management and Technology | |
| oairecerif.affiliation.orgunit | Universiti Malaysia Perlis | |
| oairecerif.affiliation.orgunit | Universiti Malaysia Perlis | |
| oairecerif.affiliation.orgunit | Hospital Tuanku Fauziah | |
| oairecerif.affiliation.orgunit | Universiti Malaysia Perlis | |
| oairecerif.affiliation.orgunit | Universiti Malaysia Perlis | |
| oairecerif.affiliation.orgunit | Universiti Malaysia Perlis | |
| oairecerif.affiliation.orgunit | Universiti Malaysia Perlis | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| oairecerif.author.affiliation | Universiti Malaysia Perlis | |
| oairecerif.author.affiliation | Universiti Malaysia Perlis | |
| oairecerif.author.affiliation | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| oairecerif.author.affiliation | Universiti Malaysia Perlis | |
| oairecerif.author.affiliation | Universiti Malaysia Perlis | |
| oairecerif.author.affiliation | Universiti Malaysia Perlis | |
| oairecerif.author.affiliation | Universiti Malaysia Perlis | |
| person.identifier.orcid | 0000-0003-1038-3933 | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.scopus-author-id | 57204510554 | |
| person.identifier.scopus-author-id | 36656186800 | |
| person.identifier.scopus-author-id | 6603280096 | |
| person.identifier.scopus-author-id | 56764435700 | |
| person.identifier.scopus-author-id | 55860800560 | |
| person.identifier.scopus-author-id | 56178375200 | |
| person.identifier.scopus-author-id | 56464318100 | |
| person.identifier.scopus-author-id | 56405592700 |
Files
Original bundle
1 - 1 of 1
- Name:
- research repository notification.pdf
- Size:
- 4.4 MB
- Format:
- Adobe Portable Document Format
- Description: