Index Link

  • RootNode
    • Co-operative College, Mandalay
    • Cooperative College, Phaunggyi
    • Co-operative University, Sagaing
    • Co-operative University, Thanlyin
    • Dagon University
    • Kyaukse University
    • Laquarware Technological college
    • Mandalay Technological University
    • Mandalay University of Distance Education
    • Mandalay University of Foreign Languages
    • Maubin University
    • Mawlamyine University
    • Meiktila University
    • Mohnyin University
    • Myanmar Institute of Information Technology
    • Myanmar Maritime University
    • National Management Degree College
    • Naypyitaw State Academy
    • Pathein University
    • Sagaing University
    • Sagaing University of Education
    • Taunggyi University
    • Technological University, Hmawbi
    • Technological University (Kyaukse)
    • Technological University Mandalay
    • University of Computer Studies, Mandalay
    • University of Computer Studies Maubin
    • University of Computer Studies, Meikhtila
    • University of Computer Studies Pathein
    • University of Computer Studies, Taungoo
    • University of Computer Studies, Yangon
    • University of Dental Medicine Mandalay
    • University of Dental Medicine, Yangon
    • University of Information Technology
    • University of Mandalay
    • University of Medicine 1
    • University of Medicine 2
    • University of Medicine Mandalay
    • University of Myitkyina
    • University of Public Health, Yangon
    • University of Veterinary Science
    • University of Yangon
    • West Yangon University
    • Yadanabon University
    • Yangon Technological University
    • Yangon University of Distance Education
    • Yangon University of Economics
    • Yangon University of Education
    • Yangon University of Foreign Languages
    • Yezin Agricultural University
    • New Index

Item

{"_buckets": {"deposit": "b9d102f9-c13d-4662-8931-8be720d035f7"}, "_deposit": {"created_by": 45, "id": "5414", "owner": "45", "owners": [45], "owners_ext": {"displayname": "", "username": ""}, "pid": {"revision_id": 0, "type": "recid", "value": "5414"}, "status": "published"}, "_oai": {"id": "oai:meral.edu.mm:recid/5414", "sets": ["user-uit"]}, "communities": ["uit"], "item_1583103067471": {"attribute_name": "Title", "attribute_value_mlt": [{"subitem_1551255647225": "Segmentation and Classification of Skin Cancer Melanoma from Skin Lesion Images", "subitem_1551255648112": "en"}]}, "item_1583103085720": {"attribute_name": "Description", "attribute_value_mlt": [{"interim": "Melanoma classification on dermoscopy skin images is a demanding task because of the low contrast of the lesion images, the intra-structural variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of hair and ruler marker artifacts. In this study, the malignant melanoma skin cancer classification system is proposed with the aid of correctly classify melanoma skin cancer. The system involves three main steps: segmentation, feature extraction and classification. Ahead of the segmentation step, the preprocessing skin lesion images is processed for getting rid of the covered hair artifacts. In the segmentation step, the input preprocessed lesion image is segmented by using the proposed texture filter-based segmentation method. Then, the features according to the underlying ABCD (Asymmetry, Border, Color, Differential Texture) dermatology rules using shape, edge, color and texture features are extracted from the segmented region. Finally, the extracted features are classified to identify whether the skin image is malignant melanoma or non-melanoma with the use of bag tree ensemble classifier. The system performance is evaluated with the use of the benchmarking datasets: PH2 dataset, ISBI2016 dataset and ISIC2017 dataset. According to the experimental results, the proposed design allows for both reliable classification of real world dermoscopy images and feasible operation time with today’s standard PC computing platforms. To address the class imbalance in the dataset and to yield the improved classification performance, the experiments are also analyzed not only on original imbalanced dataset but also on balancing datasets: undersampled and oversampled datasets. The system works well and provides both high sensitivity and specificity according to the experimental results on the oversampled dataset with bag tree ensemble classifier to leading to statistically better performance compared to original imbalanced dataset."}]}, "item_1583103108160": {"attribute_name": "Keywords", "attribute_value_mlt": [{"interim": "Melanoma"}, {"interim": "Dermoscopy Skin Image"}, {"interim": "Segmentation"}, {"interim": "Feature Extraction"}, {"interim": "Ensemble Classification"}]}, "item_1583103120197": {"attribute_name": "Files", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_no", "licensefree": "© IEEE", "licensetype": "license_free"}]}, "item_1583103147082": {"attribute_name": "Conference papers", "attribute_value_mlt": [{"subitem_acronym": "ICAIT", "subitem_c_date": "6-7 November, 2019", "subitem_conference_title": "3rd International Conference on Advanced Information Technologie", "subitem_place": "Yangon, Myanmar", "subitem_website": "https://www.uit.edu.mm/icait-2019/"}]}, "item_1583105942107": {"attribute_name": "Authors", "attribute_value_mlt": [{"subitem_authors": [{"subitem_authors_fullname": "Nay Chi Lynn"}, {"subitem_authors_fullname": "Nu War"}]}]}, "item_1583108359239": {"attribute_name": "Upload type", "attribute_value_mlt": [{"interim": "Publication"}]}, "item_1583108428133": {"attribute_name": "Publication type", "attribute_value_mlt": [{"interim": "Conference paper"}]}, "item_1583159729339": {"attribute_name": "Publication date", "attribute_value": "2019-11-07"}, "item_1583159847033": {"attribute_name": "Identifier", "attribute_value": "10.1109/aitc.2019.8920908"}, "item_title": "Segmentation and Classification of Skin Cancer Melanoma from Skin Lesion Images", "item_type_id": "21", "owner": "45", "path": ["1596102391527"], "permalink_uri": "http://hdl.handle.net/20.500.12678/0000005414", "pubdate": {"attribute_name": "Deposited date", "attribute_value": "2020-09-16"}, "publish_date": "2020-09-16", "publish_status": "0", "recid": "5414", "relation": {}, "relation_version_is_last": true, "title": ["Segmentation and Classification of Skin Cancer Melanoma from Skin Lesion Images"], "weko_shared_id": -1}

Segmentation and Classification of Skin Cancer Melanoma from Skin Lesion Images

http://hdl.handle.net/20.500.12678/0000005414
524ee749-7388-4555-bb9b-c2d6f23674c3
b9d102f9-c13d-4662-8931-8be720d035f7
Publication type
Conference paper
Upload type
Publication
Title
Title Segmentation and Classification of Skin Cancer Melanoma from Skin Lesion Images
Language en
Publication date 2019-11-07
Authors
Nay Chi Lynn
Nu War
Description
Melanoma classification on dermoscopy skin images is a demanding task because of the low contrast of the lesion images, the intra-structural variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of hair and ruler marker artifacts. In this study, the malignant melanoma skin cancer classification system is proposed with the aid of correctly classify melanoma skin cancer. The system involves three main steps: segmentation, feature extraction and classification. Ahead of the segmentation step, the preprocessing skin lesion images is processed for getting rid of the covered hair artifacts. In the segmentation step, the input preprocessed lesion image is segmented by using the proposed texture filter-based segmentation method. Then, the features according to the underlying ABCD (Asymmetry, Border, Color, Differential Texture) dermatology rules using shape, edge, color and texture features are extracted from the segmented region. Finally, the extracted features are classified to identify whether the skin image is malignant melanoma or non-melanoma with the use of bag tree ensemble classifier. The system performance is evaluated with the use of the benchmarking datasets: PH2 dataset, ISBI2016 dataset and ISIC2017 dataset. According to the experimental results, the proposed design allows for both reliable classification of real world dermoscopy images and feasible operation time with today’s standard PC computing platforms. To address the class imbalance in the dataset and to yield the improved classification performance, the experiments are also analyzed not only on original imbalanced dataset but also on balancing datasets: undersampled and oversampled datasets. The system works well and provides both high sensitivity and specificity according to the experimental results on the oversampled dataset with bag tree ensemble classifier to leading to statistically better performance compared to original imbalanced dataset.
Keywords
Melanoma, Dermoscopy Skin Image, Segmentation, Feature Extraction, Ensemble Classification
Identifier 10.1109/aitc.2019.8920908
Conference papers
ICAIT
6-7 November, 2019
3rd International Conference on Advanced Information Technologie
Yangon, Myanmar
https://www.uit.edu.mm/icait-2019/
0
0
views
downloads
Views Downloads

Export

OAI-PMH
  • OAI-PMH DublinCore
Other Formats