Multiple-Instance Learning for Anomaly Detection in Digital Mammography.
Saved in:
| Title: | Multiple-Instance Learning for Anomaly Detection in Digital Mammography. |
|---|---|
| Authors: | Quellec, Gwenole1, Lamard, Mathieu1, Cozic, Michel2, Coatrieux, Gouenou1, Cazuguel, Guy1 |
| Source: | IEEE Transactions on Medical Imaging. Jul2016, Vol. 35 Issue 7, p1604-1614. 11p. |
| Subjects: | Mammograms, Breast cancer diagnosis, Breast cancer treatment, Cancer in women, Computer-assisted surgery, Image segmentation |
| Abstract: | This paper describes a computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, breasts are first partitioned adaptively into regions. Then, features derived from the detection of lesions (masses and microcalcifications) as well as textural features, are extracted from each region and combined in order to classify mammography examinations as “normal” or “abnormal”. Whenever an abnormal examination record is detected, the regions that induced that automated diagnosis can be highlighted. Two strategies are evaluated to define this anomaly detector. In a first scenario, manual segmentations of lesions are used to train an SVM that assigns an anomaly index to each region; local anomaly indices are then combined into a global anomaly index. In a second scenario, the local and global anomaly detectors are trained simultaneously, without manual segmentations, using various MIL algorithms (DD, APR, mi-SVM, MI-SVM and MILBoost). Experiments on the DDSM dataset show that the second approach, which is only weakly-supervised, surprisingly outperforms the first approach, even though it is strongly-supervised. This suggests that anomaly detectors can be advantageously trained on large medical image archives, without the need for manual segmentation. [ABSTRACT FROM AUTHOR] |
| Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 116525068 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Multiple-Instance Learning for Anomaly Detection in Digital Mammography. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Quellec%2C+Gwenole%22">Quellec, Gwenole</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Lamard%2C+Mathieu%22">Lamard, Mathieu</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Cozic%2C+Michel%22">Cozic, Michel</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Coatrieux%2C+Gouenou%22">Coatrieux, Gouenou</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Cazuguel%2C+Guy%22">Cazuguel, Guy</searchLink><relatesTo>1</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Medical+Imaging%22">IEEE Transactions on Medical Imaging</searchLink>. Jul2016, Vol. 35 Issue 7, p1604-1614. 11p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Mammograms%22">Mammograms</searchLink><br /><searchLink fieldCode="DE" term="%22Breast+cancer+diagnosis%22">Breast cancer diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Breast+cancer+treatment%22">Breast cancer treatment</searchLink><br /><searchLink fieldCode="DE" term="%22Cancer+in+women%22">Cancer in women</searchLink><br /><searchLink fieldCode="DE" term="%22Computer-assisted+surgery%22">Computer-assisted surgery</searchLink><br /><searchLink fieldCode="DE" term="%22Image+segmentation%22">Image segmentation</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: This paper describes a computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, breasts are first partitioned adaptively into regions. Then, features derived from the detection of lesions (masses and microcalcifications) as well as textural features, are extracted from each region and combined in order to classify mammography examinations as “normal” or “abnormal”. Whenever an abnormal examination record is detected, the regions that induced that automated diagnosis can be highlighted. Two strategies are evaluated to define this anomaly detector. In a first scenario, manual segmentations of lesions are used to train an SVM that assigns an anomaly index to each region; local anomaly indices are then combined into a global anomaly index. In a second scenario, the local and global anomaly detectors are trained simultaneously, without manual segmentations, using various MIL algorithms (DD, APR, mi-SVM, MI-SVM and MILBoost). Experiments on the DDSM dataset show that the second approach, which is only weakly-supervised, surprisingly outperforms the first approach, even though it is strongly-supervised. This suggests that anomaly detectors can be advantageously trained on large medical image archives, without the need for manual segmentation. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=116525068 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1109/TMI.2016.2521442 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 11 StartPage: 1604 Subjects: – SubjectFull: Mammograms Type: general – SubjectFull: Breast cancer diagnosis Type: general – SubjectFull: Breast cancer treatment Type: general – SubjectFull: Cancer in women Type: general – SubjectFull: Computer-assisted surgery Type: general – SubjectFull: Image segmentation Type: general Titles: – TitleFull: Multiple-Instance Learning for Anomaly Detection in Digital Mammography. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Quellec, Gwenole – PersonEntity: Name: NameFull: Lamard, Mathieu – PersonEntity: Name: NameFull: Cozic, Michel – PersonEntity: Name: NameFull: Coatrieux, Gouenou – PersonEntity: Name: NameFull: Cazuguel, Guy IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 07 Text: Jul2016 Type: published Y: 2016 Identifiers: – Type: issn-print Value: 02780062 Numbering: – Type: volume Value: 35 – Type: issue Value: 7 Titles: – TitleFull: IEEE Transactions on Medical Imaging Type: main |
| ResultId | 1 |
