Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+
In this study, an advanced semantic segmentation method and deep convolutional neural network was applied to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images, thereby facilitating image interpretation and diagnosis by providing radiologists an obje...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5352 |
| _version_ | 1797415923826556928 |
|---|---|
| author | Wei-Chung Shia Fang-Rong Hsu Seng-Tong Dai Shih-Lin Guo Dar-Ren Chen |
| author_facet | Wei-Chung Shia Fang-Rong Hsu Seng-Tong Dai Shih-Lin Guo Dar-Ren Chen |
| author_sort | Wei-Chung Shia |
| collection | DOAJ |
| description | In this study, an advanced semantic segmentation method and deep convolutional neural network was applied to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images, thereby facilitating image interpretation and diagnosis by providing radiologists an objective second opinion. A total of 684 images (380 benign and 308 malignant tumours) from 343 patients (190 benign and 153 malignant breast tumour patients) were analysed in this study. Six malignancy-related standardised BI-RADS features were selected after analysis. The DeepLab v3+ architecture and four decode networks were used, and their semantic segmentation performance was evaluated and compared. Subsequently, DeepLab v3+ with the ResNet-50 decoder showed the best performance in semantic segmentation, with a mean accuracy and mean intersection over union (IU) of 44.04% and 34.92%, respectively. The weighted IU was 84.36%. For the diagnostic performance, the area under the curve was 83.32%. This study aimed to automate identification of the malignant BI-RADS lexicon on breast ultrasound images to facilitate diagnosis and improve its quality. The evaluation showed that DeepLab v3+ with the ResNet-50 decoder was suitable for solving this problem, offering a better balance of performance and computational resource usage than a fully connected network and other decoders. |
| first_indexed | 2024-03-09T05:56:27Z |
| format | Article |
| id | doaj.art-9b45a4afb2f748a283a4924d178f315c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:56:27Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9b45a4afb2f748a283a4924d178f315c2023-12-03T12:13:19ZengMDPI AGSensors1424-82202022-07-012214535210.3390/s22145352Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+Wei-Chung Shia0Fang-Rong Hsu1Seng-Tong Dai2Shih-Lin Guo3Dar-Ren Chen4Molecular Medicine Laboratory, Department of Research, Changhua Christian Hospital, Changhua 500, TaiwanDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung 407, TaiwanDepartment of Information Engineering and Computer Science, Feng Chia University, Taichung 407, TaiwanComprehensive Breast Cancer Center, Changhua Christian Hospital, Changhua 500, TaiwanComprehensive Breast Cancer Center, Changhua Christian Hospital, Changhua 500, TaiwanIn this study, an advanced semantic segmentation method and deep convolutional neural network was applied to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images, thereby facilitating image interpretation and diagnosis by providing radiologists an objective second opinion. A total of 684 images (380 benign and 308 malignant tumours) from 343 patients (190 benign and 153 malignant breast tumour patients) were analysed in this study. Six malignancy-related standardised BI-RADS features were selected after analysis. The DeepLab v3+ architecture and four decode networks were used, and their semantic segmentation performance was evaluated and compared. Subsequently, DeepLab v3+ with the ResNet-50 decoder showed the best performance in semantic segmentation, with a mean accuracy and mean intersection over union (IU) of 44.04% and 34.92%, respectively. The weighted IU was 84.36%. For the diagnostic performance, the area under the curve was 83.32%. This study aimed to automate identification of the malignant BI-RADS lexicon on breast ultrasound images to facilitate diagnosis and improve its quality. The evaluation showed that DeepLab v3+ with the ResNet-50 decoder was suitable for solving this problem, offering a better balance of performance and computational resource usage than a fully connected network and other decoders.https://www.mdpi.com/1424-8220/22/14/5352breast cancerdeep convolutional neural networksemantic segmentationultrasonic imagingcomputer-aided diagnosis |
| spellingShingle | Wei-Chung Shia Fang-Rong Hsu Seng-Tong Dai Shih-Lin Guo Dar-Ren Chen Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+ Sensors breast cancer deep convolutional neural network semantic segmentation ultrasonic imaging computer-aided diagnosis |
| title | Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+ |
| title_full | Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+ |
| title_fullStr | Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+ |
| title_full_unstemmed | Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+ |
| title_short | Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3+ |
| title_sort | semantic segmentation of the malignant breast imaging reporting and data system lexicon on breast ultrasound images by using deeplab v3 |
| topic | breast cancer deep convolutional neural network semantic segmentation ultrasonic imaging computer-aided diagnosis |
| url | https://www.mdpi.com/1424-8220/22/14/5352 |
| work_keys_str_mv | AT weichungshia semanticsegmentationofthemalignantbreastimagingreportinganddatasystemlexicononbreastultrasoundimagesbyusingdeeplabv3 AT fangronghsu semanticsegmentationofthemalignantbreastimagingreportinganddatasystemlexicononbreastultrasoundimagesbyusingdeeplabv3 AT sengtongdai semanticsegmentationofthemalignantbreastimagingreportinganddatasystemlexicononbreastultrasoundimagesbyusingdeeplabv3 AT shihlinguo semanticsegmentationofthemalignantbreastimagingreportinganddatasystemlexicononbreastultrasoundimagesbyusingdeeplabv3 AT darrenchen semanticsegmentationofthemalignantbreastimagingreportinganddatasystemlexicononbreastultrasoundimagesbyusingdeeplabv3 |