[vc_empty_space][vc_empty_space]
Automated classification of urinary stones based on microcomputed tomography images using convolutional neural network
Fitri L.A.a,b, Haryanto F.b, Arimura H.c, YunHao C.d, Ninomiya K.d, Nakano R.d, Haekal M.e, Warty Y.b, Fauzi U.b
a Department of Radiology, Baiturrahmah University, Padang, 25172, Indonesia
b Department of Physics, Institut Teknologi Bandung, Bandung, 40132, Indonesia
c Faculty of Medical Sciences, Kyushu University, Fukuoka, 812-8582, Japan
d Graduate School of Medical Sciences, Kyushu University, Fukuoka, 812-8582, Japan
e Department of Physics, Faculty of Sciences and Data Analytics, Institut Teknologi Sepuluh Nopember, Kampus ITS Sukolilo, Surabaya, 60111, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2020 Associazione Italiana di Fisica MedicaPurpose: The classification of urinary stones is important prior to treatment because the treatments depend on three types of urinary stones, i.e., calcium, uric acid, and mixture stones. We have developed an automatic approach for the classification of urinary stones into the three types based on microcomputed tomography (micro-CT) images using a convolutional neural network (CNN). Materials and methods: Thirty urinary stones from different patients were scanned in vitro using micro-CT (pixel size: 14.96 μm; slice thickness: 15 μm); a total of 2,430 images (micro-CT slices) were produced. The slices (227 × 227 pixels) were classified into the three categories based on their energy dispersive X-ray (EDX) spectra obtained via scanning electron microscopy (SEM). The images of urinary stones from each category were divided into three parts; 66%, 17%, and 17% of the dataset were assigned to the training, validation, and test datasets, respectively. The CNN model with 15 layers was assessed based on validation accuracy for the optimization of hyperparameters such as batch size, learning rate, and number of epochs with different optimizers. Then, the model with the optimized hyperparameters was evaluated for the test dataset to obtain classification accuracy and error. Results: The validation accuracy of the developed approach with CNN with optimized hyperparameters was 0.9852. The trained CNN model achieved a test accuracy of 0.9959 with a classification error of 1.2%. Conclusions: The proposed automated CNN-based approach could successfully classify urinary stones into three types, namely calcium, uric acid, and mixture stones, using micro-CT images.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Convolutional neural network,Energy dispersive X-ray spectra,Micro-CT,Urinary stones[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][{‘$’: ‘The authors are grateful for the support of Hasan Sadikin Hospital, Indonesia. We would also like to thank Kyushu University , Japan (Arimura Laboratory) for allowing us to use their Deep Learning server for this study. This study was financially supported by the Indonesia Endowment Fund for Education (LPDP), Enhancing International Publication Program (EIP) (T/1226/D3.2/KD.02.00/2019), and DIKTI (2/E1/KP.PTNBH/2020), Indonesia.’}, {‘$’: ‘The authors are grateful for the support of Hasan Sadikin Hospital, Indonesia. We would also like to thank Kyushu University, Japan (Arimura Laboratory) for allowing us to use their Deep Learning server for this study. This study was financially supported by the Indonesia Endowment Fund for Education (LPDP), Enhancing International Publication Program (EIP) (T/1226/D3.2/KD.02.00/2019), and DIKTI (2/E1/KP.PTNBH/2020), Indonesia.’}][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1016/j.ejmp.2020.09.007[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]