Deep Image Segmentation for Breast Keypoint Detection
The main aim of breast cancer conservative treatment is the optimisation of the aesthetic outcome and, implicitly, women’s quality of life, without jeopardising local cancer control and overall survival. Moreover, there has been an effort to try to define an optimal tool capable of performing the ae...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-3900/54/1/35 |
| _version_ | 1797556590340997120 |
|---|---|
| author | Tiago Gonçalves Wilson Silva Maria J. Cardoso Jaime S. Cardoso |
| author_facet | Tiago Gonçalves Wilson Silva Maria J. Cardoso Jaime S. Cardoso |
| author_sort | Tiago Gonçalves |
| collection | DOAJ |
| description | The main aim of breast cancer conservative treatment is the optimisation of the aesthetic outcome and, implicitly, women’s quality of life, without jeopardising local cancer control and overall survival. Moreover, there has been an effort to try to define an optimal tool capable of performing the aesthetic evaluation of breast cancer conservative treatment outcomes. Recently, a deep learning algorithm that integrates the learning of keypoints’ probability maps in the loss function as a regularisation term for the robust learning of the keypoint localisation has been proposed. However, it achieves the best results when used in cooperation with a shortest-path algorithm that models images as graphs. In this work, we analysed a novel algorithm based on the interaction of deep image segmentation and deep keypoint detection models capable of improving both state-of-the-art performance and execution-time on the breast keypoint detection task. |
| first_indexed | 2024-03-10T17:05:01Z |
| format | Article |
| id | doaj.art-8524c18505474ae4a2e3fa5a746cf752 |
| institution | Directory Open Access Journal |
| issn | 2504-3900 |
| language | English |
| last_indexed | 2024-03-10T17:05:01Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Proceedings |
| spelling | doaj.art-8524c18505474ae4a2e3fa5a746cf7522023-11-20T10:51:19ZengMDPI AGProceedings2504-39002020-08-015413510.3390/proceedings2020054035Deep Image Segmentation for Breast Keypoint DetectionTiago Gonçalves0Wilson Silva1Maria J. Cardoso2Jaime S. Cardoso3INESC TEC and Faculdade de Engenharia, Universidade do Porto, 4200-465 Porto, PortugalINESC TEC and Faculdade de Engenharia, Universidade do Porto, 4200-465 Porto, PortugalChampalimaud Foundation and Nova Medical School, 1400-038 Lisboa, PortugalINESC TEC and Faculdade de Engenharia, Universidade do Porto, 4200-465 Porto, PortugalThe main aim of breast cancer conservative treatment is the optimisation of the aesthetic outcome and, implicitly, women’s quality of life, without jeopardising local cancer control and overall survival. Moreover, there has been an effort to try to define an optimal tool capable of performing the aesthetic evaluation of breast cancer conservative treatment outcomes. Recently, a deep learning algorithm that integrates the learning of keypoints’ probability maps in the loss function as a regularisation term for the robust learning of the keypoint localisation has been proposed. However, it achieves the best results when used in cooperation with a shortest-path algorithm that models images as graphs. In this work, we analysed a novel algorithm based on the interaction of deep image segmentation and deep keypoint detection models capable of improving both state-of-the-art performance and execution-time on the breast keypoint detection task.https://www.mdpi.com/2504-3900/54/1/35aesthetic assessment of breast cancer surgery outcomesartificial intelligencebreast cancerbreast cancer conservative treatmentcomputer visiondeep learning |
| spellingShingle | Tiago Gonçalves Wilson Silva Maria J. Cardoso Jaime S. Cardoso Deep Image Segmentation for Breast Keypoint Detection Proceedings aesthetic assessment of breast cancer surgery outcomes artificial intelligence breast cancer breast cancer conservative treatment computer vision deep learning |
| title | Deep Image Segmentation for Breast Keypoint Detection |
| title_full | Deep Image Segmentation for Breast Keypoint Detection |
| title_fullStr | Deep Image Segmentation for Breast Keypoint Detection |
| title_full_unstemmed | Deep Image Segmentation for Breast Keypoint Detection |
| title_short | Deep Image Segmentation for Breast Keypoint Detection |
| title_sort | deep image segmentation for breast keypoint detection |
| topic | aesthetic assessment of breast cancer surgery outcomes artificial intelligence breast cancer breast cancer conservative treatment computer vision deep learning |
| url | https://www.mdpi.com/2504-3900/54/1/35 |
| work_keys_str_mv | AT tiagogoncalves deepimagesegmentationforbreastkeypointdetection AT wilsonsilva deepimagesegmentationforbreastkeypointdetection AT mariajcardoso deepimagesegmentationforbreastkeypointdetection AT jaimescardoso deepimagesegmentationforbreastkeypointdetection |