Prediction of locations in medical images using orthogonal neural networks
Background/Purpose: An orthogonal neural network (ONN), a new deep-learning structure for medical image localization, is developed and presented in this paper. This method is simple, efficient, and completely different from a convolution neural network (CNN). Materials and methods: The diagnostic pe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-01-01
|
| Series: | European Journal of Radiology Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235204772100068X |
| _version_ | 1819174793981722624 |
|---|---|
| author | Jong Soo Kim Yongil Cho Tae Ho Lim |
| author_facet | Jong Soo Kim Yongil Cho Tae Ho Lim |
| author_sort | Jong Soo Kim |
| collection | DOAJ |
| description | Background/Purpose: An orthogonal neural network (ONN), a new deep-learning structure for medical image localization, is developed and presented in this paper. This method is simple, efficient, and completely different from a convolution neural network (CNN). Materials and methods: The diagnostic performance of ONN for detecting the location of pneumothorax in chest X-rays was assessed and compared to that of CNN. In addition, ONN and CNN were applied to predict the location of the glottis in laryngeal images. Results: An area under the receiver operating characteristic (ROC) curve (AUC) of 0.870, an accuracy of 85.3%, a sensitivity of 75.0%, and a specificity of 86.5% were achieved by applying ONN to detect the location of pneumothorax in chest X-rays; the ONN outperformed the CNN. By applying ONN to predict the location of the glottis in laryngeal images, we achieved the accurate prediction rate of 70.5% and the adjacent prediction rate of 20.5%. Conclusions: This study demonstrated that an ONN can be used as a quick selection criterion to compare fully-connected small artificial neural network (ANN) models for image localization. The time it took to train an ONN was about 10% of the time using a CNN on images of a given input resolution. Our approach could accurately predict locations in medical images, reduce the time delay in diagnosing urgent diseases, and increase the effectiveness of clinical practice and patient care. |
| first_indexed | 2024-12-22T20:44:38Z |
| format | Article |
| id | doaj.art-af5f88bacf6942aaa8b69e1c90fccb40 |
| institution | Directory Open Access Journal |
| issn | 2352-0477 |
| language | English |
| last_indexed | 2024-12-22T20:44:38Z |
| publishDate | 2021-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | European Journal of Radiology Open |
| spelling | doaj.art-af5f88bacf6942aaa8b69e1c90fccb402022-12-21T18:13:15ZengElsevierEuropean Journal of Radiology Open2352-04772021-01-018100388Prediction of locations in medical images using orthogonal neural networksJong Soo Kim0Yongil Cho1Tae Ho Lim2Institute for Software Convergence, Hanyang University, Seoul, Republic of Korea; Correspondence to: Institute for Software Convergence, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea.Department of Emergency Medicine, College of Medicine, Hanyang University, Seoul, Republic of KoreaDepartment of Emergency Medicine, College of Medicine, Hanyang University, Seoul, Republic of Korea; Correspondence to: Department of Emergency Medicine, College of Medicine, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, Republic of Korea.Background/Purpose: An orthogonal neural network (ONN), a new deep-learning structure for medical image localization, is developed and presented in this paper. This method is simple, efficient, and completely different from a convolution neural network (CNN). Materials and methods: The diagnostic performance of ONN for detecting the location of pneumothorax in chest X-rays was assessed and compared to that of CNN. In addition, ONN and CNN were applied to predict the location of the glottis in laryngeal images. Results: An area under the receiver operating characteristic (ROC) curve (AUC) of 0.870, an accuracy of 85.3%, a sensitivity of 75.0%, and a specificity of 86.5% were achieved by applying ONN to detect the location of pneumothorax in chest X-rays; the ONN outperformed the CNN. By applying ONN to predict the location of the glottis in laryngeal images, we achieved the accurate prediction rate of 70.5% and the adjacent prediction rate of 20.5%. Conclusions: This study demonstrated that an ONN can be used as a quick selection criterion to compare fully-connected small artificial neural network (ANN) models for image localization. The time it took to train an ONN was about 10% of the time using a CNN on images of a given input resolution. Our approach could accurately predict locations in medical images, reduce the time delay in diagnosing urgent diseases, and increase the effectiveness of clinical practice and patient care.http://www.sciencedirect.com/science/article/pii/S235204772100068XDeep learningGlottisLocalizationOrthogonal neural networkPneumothorax |
| spellingShingle | Jong Soo Kim Yongil Cho Tae Ho Lim Prediction of locations in medical images using orthogonal neural networks European Journal of Radiology Open Deep learning Glottis Localization Orthogonal neural network Pneumothorax |
| title | Prediction of locations in medical images using orthogonal neural networks |
| title_full | Prediction of locations in medical images using orthogonal neural networks |
| title_fullStr | Prediction of locations in medical images using orthogonal neural networks |
| title_full_unstemmed | Prediction of locations in medical images using orthogonal neural networks |
| title_short | Prediction of locations in medical images using orthogonal neural networks |
| title_sort | prediction of locations in medical images using orthogonal neural networks |
| topic | Deep learning Glottis Localization Orthogonal neural network Pneumothorax |
| url | http://www.sciencedirect.com/science/article/pii/S235204772100068X |
| work_keys_str_mv | AT jongsookim predictionoflocationsinmedicalimagesusingorthogonalneuralnetworks AT yongilcho predictionoflocationsinmedicalimagesusingorthogonalneuralnetworks AT taeholim predictionoflocationsinmedicalimagesusingorthogonalneuralnetworks |