Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography
According to the Health Promotion Administration in the Ministry of Health and Welfare statistics in Taiwan, over ten thousand women have breast cancer every year. Mammography is widely used to detect breast cancer. However, it is limited by the operator’s technique, the cooperation of the subjects,...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/10/12/2382 |
| _version_ | 1797457617759502336 |
|---|---|
| author | Shih-Yen Hsu Chi-Yuan Wang Yi-Kai Kao Kuo-Ying Liu Ming-Chia Lin Li-Ren Yeh Yi-Ming Wang Chih-I Chen Feng-Chen Kao |
| author_facet | Shih-Yen Hsu Chi-Yuan Wang Yi-Kai Kao Kuo-Ying Liu Ming-Chia Lin Li-Ren Yeh Yi-Ming Wang Chih-I Chen Feng-Chen Kao |
| author_sort | Shih-Yen Hsu |
| collection | DOAJ |
| description | According to the Health Promotion Administration in the Ministry of Health and Welfare statistics in Taiwan, over ten thousand women have breast cancer every year. Mammography is widely used to detect breast cancer. However, it is limited by the operator’s technique, the cooperation of the subjects, and the subjective interpretation by the physician. It results in inconsistent identification. Therefore, this study explores the use of a deep neural network algorithm for the classification of mammography images. In the experimental design, a retrospective study was used to collect imaging data from actual clinical cases. The mammography images were collected and classified according to the breast image reporting and data-analyzing system (BI-RADS). In terms of model building, a fully convolutional dense connection network (FC-DCN) is used for the network backbone. All the images were obtained through image preprocessing, a data augmentation method, and transfer learning technology to build a mammography image classification model. The research results show the model’s accuracy, sensitivity, and specificity were 86.37%, 100%, and 72.73%, respectively. Based on the FC-DCN model framework, it can effectively reduce the number of training parameters and successfully obtain a reasonable image classification model for mammography. |
| first_indexed | 2024-03-09T16:24:35Z |
| format | Article |
| id | doaj.art-6ad85d26f4ab4bf2aed7063c55ffe1d6 |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-09T16:24:35Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-6ad85d26f4ab4bf2aed7063c55ffe1d62023-11-24T15:09:01ZengMDPI AGHealthcare2227-90322022-11-011012238210.3390/healthcare10122382Using Deep Neural Network Approach for Multiple-Class Assessment of Digital MammographyShih-Yen Hsu0Chi-Yuan Wang1Yi-Kai Kao2Kuo-Ying Liu3Ming-Chia Lin4Li-Ren Yeh5Yi-Ming Wang6Chih-I Chen7Feng-Chen Kao8Department of Information Engineering, I-Shou University, Kaohsiung City 84001, TaiwanDepartment of Medical Imaging and Radiological Science, I-Shou University, Kaohsiung City 82445, TaiwanDivision of Colorectal Surgery, Department of Surgery, E-DA Hospital, Kaohsiung City 82445, TaiwanDepartment of Radiology, E-DA Cancer Hospital, I-Shou University, Kaohsiung City 82445, TaiwanDepartment of Nuclear Medicine, E-DA Hospital, I-Shou University, Kaohsiung City 82445, TaiwanDepartment of Anesthesiology, E-DA Cancer Hospital, I-Shou University, Kaohsiung City 82445, TaiwanDepartment of Information Engineering, I-Shou University, Kaohsiung City 84001, TaiwanDivision of Colon and Rectal Surgery, Department of Surgery, E-DA Hospital, Kaohsiung City 82445, TaiwanSchool of Medicine, College of Medicine, I-Shou University, Kaohsiung City 82445, TaiwanAccording to the Health Promotion Administration in the Ministry of Health and Welfare statistics in Taiwan, over ten thousand women have breast cancer every year. Mammography is widely used to detect breast cancer. However, it is limited by the operator’s technique, the cooperation of the subjects, and the subjective interpretation by the physician. It results in inconsistent identification. Therefore, this study explores the use of a deep neural network algorithm for the classification of mammography images. In the experimental design, a retrospective study was used to collect imaging data from actual clinical cases. The mammography images were collected and classified according to the breast image reporting and data-analyzing system (BI-RADS). In terms of model building, a fully convolutional dense connection network (FC-DCN) is used for the network backbone. All the images were obtained through image preprocessing, a data augmentation method, and transfer learning technology to build a mammography image classification model. The research results show the model’s accuracy, sensitivity, and specificity were 86.37%, 100%, and 72.73%, respectively. Based on the FC-DCN model framework, it can effectively reduce the number of training parameters and successfully obtain a reasonable image classification model for mammography.https://www.mdpi.com/2227-9032/10/12/2382mammographydeep neural networkclassification |
| spellingShingle | Shih-Yen Hsu Chi-Yuan Wang Yi-Kai Kao Kuo-Ying Liu Ming-Chia Lin Li-Ren Yeh Yi-Ming Wang Chih-I Chen Feng-Chen Kao Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography Healthcare mammography deep neural network classification |
| title | Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography |
| title_full | Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography |
| title_fullStr | Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography |
| title_full_unstemmed | Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography |
| title_short | Using Deep Neural Network Approach for Multiple-Class Assessment of Digital Mammography |
| title_sort | using deep neural network approach for multiple class assessment of digital mammography |
| topic | mammography deep neural network classification |
| url | https://www.mdpi.com/2227-9032/10/12/2382 |
| work_keys_str_mv | AT shihyenhsu usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT chiyuanwang usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT yikaikao usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT kuoyingliu usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT mingchialin usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT lirenyeh usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT yimingwang usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT chihichen usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography AT fengchenkao usingdeepneuralnetworkapproachformultipleclassassessmentofdigitalmammography |