Multiple-level thresholding for breast mass detection
Detection of breast mass plays a very important role in making the diagnosis of breast cancer. For faster detection of breast cancer caused by breast mass, we developed a novel and efficient patch-based breast mass detection system for mammography images. The proposed framework is comprised of three...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-01-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157822004049 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849322697773809664 |
|---|---|
| author | Xiang Yu Shui-Hua Wang Yu-Dong Zhang |
| author_facet | Xiang Yu Shui-Hua Wang Yu-Dong Zhang |
| author_sort | Xiang Yu |
| collection | DOAJ |
| description | Detection of breast mass plays a very important role in making the diagnosis of breast cancer. For faster detection of breast cancer caused by breast mass, we developed a novel and efficient patch-based breast mass detection system for mammography images. The proposed framework is comprised of three modules, including pre-processing, multiple-level breast tissue segmentation, and final breast mass detection. An improved Deeplabv3+ model for pectoral muscle removal is deployed in pre-processing. We then proposed a multiple-level thresholding segmentation method to segment breast mass and obtained the connected components (ConCs), where the corresponding image patch to each ConC is extracted for mass detection. In the final detection stage, each image patch is classified into breast mass and breast tissue background by trained deep learning models. The patches that are classified as breast mass are then taken as the candidates for breast mass. To reduce the false positive rate in the detection results, we applied the non-maximum suppression algorithm to combine the overlapped detection results. Once an image patch is considered a breast mass, the accurate detection result can then be retrieved from the corresponding ConC in the segmented images. Moreover, a coarse segmentation result can be simultaneously retrieved after detection. Compared to the state-of-the-art methods, the proposed method achieved comparable performance. On CBIS-DDSM, the proposed method achieved a detection sensitivity of 0.87 at 2.86 FPI (False Positive rate per Image), while the sensitivity reached 0.96 on INbreast with an FPI of only 1.29. |
| format | Article |
| id | doaj-art-53fb85bd23d14074aede805afe7c41d7 |
| institution | Kabale University |
| issn | 1319-1578 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj-art-53fb85bd23d14074aede805afe7c41d72025-08-20T03:49:17ZengSpringerJournal of King Saud University: Computer and Information Sciences1319-15782023-01-0135111513010.1016/j.jksuci.2022.11.006Multiple-level thresholding for breast mass detectionXiang Yu0Shui-Hua Wang1Yu-Dong Zhang2School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, United KingdomSchool of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, United KingdomCorresponding author.; School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, United KingdomDetection of breast mass plays a very important role in making the diagnosis of breast cancer. For faster detection of breast cancer caused by breast mass, we developed a novel and efficient patch-based breast mass detection system for mammography images. The proposed framework is comprised of three modules, including pre-processing, multiple-level breast tissue segmentation, and final breast mass detection. An improved Deeplabv3+ model for pectoral muscle removal is deployed in pre-processing. We then proposed a multiple-level thresholding segmentation method to segment breast mass and obtained the connected components (ConCs), where the corresponding image patch to each ConC is extracted for mass detection. In the final detection stage, each image patch is classified into breast mass and breast tissue background by trained deep learning models. The patches that are classified as breast mass are then taken as the candidates for breast mass. To reduce the false positive rate in the detection results, we applied the non-maximum suppression algorithm to combine the overlapped detection results. Once an image patch is considered a breast mass, the accurate detection result can then be retrieved from the corresponding ConC in the segmented images. Moreover, a coarse segmentation result can be simultaneously retrieved after detection. Compared to the state-of-the-art methods, the proposed method achieved comparable performance. On CBIS-DDSM, the proposed method achieved a detection sensitivity of 0.87 at 2.86 FPI (False Positive rate per Image), while the sensitivity reached 0.96 on INbreast with an FPI of only 1.29.http://www.sciencedirect.com/science/article/pii/S1319157822004049Mass detectionMultiple-level thresholdingDeep CNNs |
| spellingShingle | Xiang Yu Shui-Hua Wang Yu-Dong Zhang Multiple-level thresholding for breast mass detection Journal of King Saud University: Computer and Information Sciences Mass detection Multiple-level thresholding Deep CNNs |
| title | Multiple-level thresholding for breast mass detection |
| title_full | Multiple-level thresholding for breast mass detection |
| title_fullStr | Multiple-level thresholding for breast mass detection |
| title_full_unstemmed | Multiple-level thresholding for breast mass detection |
| title_short | Multiple-level thresholding for breast mass detection |
| title_sort | multiple level thresholding for breast mass detection |
| topic | Mass detection Multiple-level thresholding Deep CNNs |
| url | http://www.sciencedirect.com/science/article/pii/S1319157822004049 |
| work_keys_str_mv | AT xiangyu multiplelevelthresholdingforbreastmassdetection AT shuihuawang multiplelevelthresholdingforbreastmassdetection AT yudongzhang multiplelevelthresholdingforbreastmassdetection |