Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images
Mammography images are the most commonly used tool for breast cancer screening. The presence of pectoral muscle in images for the mediolateral oblique view makes designing a robust automated breast cancer detection system more challenging. Most of the current methods for removing the pectoral muscle...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/10/12/331 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846104201767157760 |
|---|---|
| author | Parvaneh Aliniya Mircea Nicolescu Monica Nicolescu George Bebis |
| author_facet | Parvaneh Aliniya Mircea Nicolescu Monica Nicolescu George Bebis |
| author_sort | Parvaneh Aliniya |
| collection | DOAJ |
| description | Mammography images are the most commonly used tool for breast cancer screening. The presence of pectoral muscle in images for the mediolateral oblique view makes designing a robust automated breast cancer detection system more challenging. Most of the current methods for removing the pectoral muscle are based on traditional machine learning approaches. This is partly due to the lack of segmentation masks of pectoral muscle in available datasets. In this paper, we provide the segmentation masks of the pectoral muscle for the INbreast, MIAS, and CBIS-DDSM datasets, which will enable the development of supervised methods and the utilization of deep learning. Training deep learning-based models using segmentation masks will also be a powerful tool for removing pectoral muscle for unseen data. To test the validity of this idea, we trained AU-Net separately on the INbreast and CBIS-DDSM for the segmentation of the pectoral muscle. We used cross-dataset testing to evaluate the performance of the models on an unseen dataset. In addition, the models were tested on all of the images in the MIAS dataset. The experimental results show that cross-dataset testing achieves a comparable performance to the same-dataset experiments. |
| format | Article |
| id | doaj-art-34b426dde6b14dc9a40e4f7fe6c3399f |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-34b426dde6b14dc9a40e4f7fe6c3399f2024-12-27T14:32:36ZengMDPI AGJournal of Imaging2313-433X2024-12-01101233110.3390/jimaging10120331Towards Robust Supervised Pectoral Muscle Segmentation in Mammography ImagesParvaneh Aliniya0Mircea Nicolescu1Monica Nicolescu2George Bebis3Computer Science and Engineering Department, College of Engineering, University of Nevada, Reno, Main Campus, Reno, NV 89557, USAComputer Science and Engineering Department, College of Engineering, University of Nevada, Reno, Main Campus, Reno, NV 89557, USAComputer Science and Engineering Department, College of Engineering, University of Nevada, Reno, Main Campus, Reno, NV 89557, USAComputer Science and Engineering Department, College of Engineering, University of Nevada, Reno, Main Campus, Reno, NV 89557, USAMammography images are the most commonly used tool for breast cancer screening. The presence of pectoral muscle in images for the mediolateral oblique view makes designing a robust automated breast cancer detection system more challenging. Most of the current methods for removing the pectoral muscle are based on traditional machine learning approaches. This is partly due to the lack of segmentation masks of pectoral muscle in available datasets. In this paper, we provide the segmentation masks of the pectoral muscle for the INbreast, MIAS, and CBIS-DDSM datasets, which will enable the development of supervised methods and the utilization of deep learning. Training deep learning-based models using segmentation masks will also be a powerful tool for removing pectoral muscle for unseen data. To test the validity of this idea, we trained AU-Net separately on the INbreast and CBIS-DDSM for the segmentation of the pectoral muscle. We used cross-dataset testing to evaluate the performance of the models on an unseen dataset. In addition, the models were tested on all of the images in the MIAS dataset. The experimental results show that cross-dataset testing achieves a comparable performance to the same-dataset experiments.https://www.mdpi.com/2313-433X/10/12/331breast cancer mammographypectoral muscleINbreastCBIS-DDSMMIASdeep learning |
| spellingShingle | Parvaneh Aliniya Mircea Nicolescu Monica Nicolescu George Bebis Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images Journal of Imaging breast cancer mammography pectoral muscle INbreast CBIS-DDSM MIAS deep learning |
| title | Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images |
| title_full | Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images |
| title_fullStr | Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images |
| title_full_unstemmed | Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images |
| title_short | Towards Robust Supervised Pectoral Muscle Segmentation in Mammography Images |
| title_sort | towards robust supervised pectoral muscle segmentation in mammography images |
| topic | breast cancer mammography pectoral muscle INbreast CBIS-DDSM MIAS deep learning |
| url | https://www.mdpi.com/2313-433X/10/12/331 |
| work_keys_str_mv | AT parvanehaliniya towardsrobustsupervisedpectoralmusclesegmentationinmammographyimages AT mirceanicolescu towardsrobustsupervisedpectoralmusclesegmentationinmammographyimages AT monicanicolescu towardsrobustsupervisedpectoralmusclesegmentationinmammographyimages AT georgebebis towardsrobustsupervisedpectoralmusclesegmentationinmammographyimages |