ACADSTAFF UGM

CREATION
Title : Periapical Radiograph Texture Features for Osteoporosis Detection using Deep Convolutional Neural Network
Author :

KHASNUR HIDJAH (1) Prof. Drs. Agus Harjoko, M.Sc., Ph.D. (2) Moh. Edi Wibowo, S.Kom.,M.Kom., Ph.D. (3) Dr. drg. Rurie Ratna Shantiningsih, MDSc. (4)
Date : 0 2022
Keyword : Osteoporosis, Dental periapical radiograph, Convolutional neural network, texture features, Bone mineral density Osteoporosis, Dental periapical radiograph, Convolutional neural network, texture features, Bone mineral density
Abstract : Currently, research for osteoporosis examination using dental radiographic images is increasing rapidly. Many researchers have used various methods from subject data. It indicates that osteoporosis has become a widespread disease that should be studied more deeply. This study proposes a deep Convolutional Neural Network architecture as a texture feature in examining osteoporosis. The resulting features can be used as a pre-train model in image data with the same characteristics for different cases. The subject of this study is postmenopausal Javanese women aged over 40 and data measurement result of Bone Mineral Density. The proposed model is divided into stages: 1) stage image acquisition and ROI selection, 2) stage feature extraction and classification. The highest validation accuracy is achieved when the block size is 140pixel x 140pixel, the number of convolution layers is 5, and the size of the convolution kernel is 5x5 for the first layer and 3x3 for the other layers. Several hyper parameters include epochs=100, dropout=0.5, learning rate=0.0001. The validation accuracy achieved by the best model was 98.10%. The result shows that the bigger images provide additional information about trabecular patterns in normal, osteopenia and osteoporosis classes.
Group of Knowledge : Ilmu Komputer
Original Language : English
Level : Internasional
Status :
Published
Document
No Title Document Type Action
1 Paper_27-Periapical_Radiograph_Texture_Features.pdf
Document Type : Bukti Published
Bukti Published View
2 toc-IJACSA Volume 13 Issue 1 - thesai_org.pdf
Document Type : [PAK] Daftar Isi
[PAK] Daftar Isi View
3 front-Computer Science Journals _ IJACSA _ Scopus Indexed Journal.pdf
Document Type : [PAK] Halaman Cover
[PAK] Halaman Cover View
4 editors-IJACSA Editors.pdf
Document Type : [PAK] Halaman Editorial
[PAK] Halaman Editorial View
5 turnitin-Periapical Radiograph Texture Features for Osteoporosis Detection using Deep Convolutional Neural Network.pdf
Document Type : [PAK] Cek Similarity
[PAK] Cek Similarity View
6 IJACSA - Osteoporosis-lengkap-PAK-low.pdf
Document Type : [PAK] Full Dokumen
[PAK] Full Dokumen View
7 Periapical Radiograph Texture Features.pdf
Document Type : [PAK] Full Dokumen
[PAK] Full Dokumen View
8 PEER REVIEW_ Agus Harjoko 11.pdf
Document Type : [PAK] Peer Review
[PAK] Peer Review View