Relationship between computer segmentation performance and computer classification performance in breast CT: A simulation study using RGI segmentation and LDA classification.
Saved in:
| Title: | Relationship between computer segmentation performance and computer classification performance in breast CT: A simulation study using RGI segmentation and LDA classification. |
|---|---|
| Authors: | Lee, Juhun1 leej15@upmc.edu, Nishikawa, Robert M.1, Reiser, Ingrid2, Boone, John M.3 |
| Source: | Medical Physics. Aug2018, Vol. 45 Issue 8, p3650-3656. 7p. |
| Subjects: | Breast cancer treatment, Computer-aided diagnosis, Image segmentation, Breast cancer diagnosis, Computer simulation |
| Abstract: | Purpose: Many computer aided diagnosis (CADx) tools for breast cancer begin by fully or semiautomatically segmenting a given breast lesion and then classifying the lesion's likelihood of malignancy using quantitative features extracted from the image. It is often assumed that better segmentation will result in better classification. However, this has not been thoroughly evaluated. The purpose of this study is to evaluate the relationship between computer segmentation performance and computer classification performance. Method: We used 85 breast lesions (32 benign, 56 malignant) from breast computed tomography (CT) cases of 82 women. We prepared one smooth and one sharp iterative image reconstructions (IIR) and a clinical reconstruction for each of the 82 breast CT scans. For each reconstruction, we created 15 segmentation outcomes by applying 15 different segmentation algorithms. Specifically, we simulated 15 segmentation algorithms by changing parameters in a single segmentation algorithm. We then created 15 classification outcomes by conducting quantitative image feature analysis on the segmented image results. Using a 10‐fold cross‐validation, we evaluated the relationship between segmentation and classification performances. Result: We found a low positive correlation between segmentation and classification performances for the smooth IIR (median Pearson's rho = 0.18), while a moderate positive correlation (median Pearson's rho = 0.4−0.43) was found between the two performances for the sharp IIR and clinical reconstruction. However, we found large variations in both segmentation and classification performances for the sharp IIR and clinical reconstruction. There were cases where segmentation algorithms resulted in similar segmentation performances, but the corresponding classification performances were different. These results indicate that an improvement in segmentation performance does not guarantee an improvement in the corresponding classification performance. Conclusion: Computer segmentation is an indirect variable affecting the computer classification. As better segmentation does not guarantee better classification, we should report both segmentation and classification performances when comparing segmentation algorithms. [ABSTRACT FROM AUTHOR] |
| Copyright of Medical Physics is the property of Wiley-Blackwell 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 |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 131206267 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Relationship between computer segmentation performance and computer classification performance in breast CT: A simulation study using RGI segmentation and LDA classification. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Lee%2C+Juhun%22">Lee, Juhun</searchLink><relatesTo>1</relatesTo><i> leej15@upmc.edu</i><br /><searchLink fieldCode="AR" term="%22Nishikawa%2C+Robert+M%2E%22">Nishikawa, Robert M.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Reiser%2C+Ingrid%22">Reiser, Ingrid</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Boone%2C+John+M%2E%22">Boone, John M.</searchLink><relatesTo>3</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Medical+Physics%22">Medical Physics</searchLink>. Aug2018, Vol. 45 Issue 8, p3650-3656. 7p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Breast+cancer+treatment%22">Breast cancer treatment</searchLink><br /><searchLink fieldCode="DE" term="%22Computer-aided+diagnosis%22">Computer-aided diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Image+segmentation%22">Image segmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Breast+cancer+diagnosis%22">Breast cancer diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+simulation%22">Computer simulation</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Purpose: Many computer aided diagnosis (CADx) tools for breast cancer begin by fully or semiautomatically segmenting a given breast lesion and then classifying the lesion's likelihood of malignancy using quantitative features extracted from the image. It is often assumed that better segmentation will result in better classification. However, this has not been thoroughly evaluated. The purpose of this study is to evaluate the relationship between computer segmentation performance and computer classification performance. Method: We used 85 breast lesions (32 benign, 56 malignant) from breast computed tomography (CT) cases of 82 women. We prepared one smooth and one sharp iterative image reconstructions (IIR) and a clinical reconstruction for each of the 82 breast CT scans. For each reconstruction, we created 15 segmentation outcomes by applying 15 different segmentation algorithms. Specifically, we simulated 15 segmentation algorithms by changing parameters in a single segmentation algorithm. We then created 15 classification outcomes by conducting quantitative image feature analysis on the segmented image results. Using a 10‐fold cross‐validation, we evaluated the relationship between segmentation and classification performances. Result: We found a low positive correlation between segmentation and classification performances for the smooth IIR (median Pearson's rho = 0.18), while a moderate positive correlation (median Pearson's rho = 0.4−0.43) was found between the two performances for the sharp IIR and clinical reconstruction. However, we found large variations in both segmentation and classification performances for the sharp IIR and clinical reconstruction. There were cases where segmentation algorithms resulted in similar segmentation performances, but the corresponding classification performances were different. These results indicate that an improvement in segmentation performance does not guarantee an improvement in the corresponding classification performance. Conclusion: Computer segmentation is an indirect variable affecting the computer classification. As better segmentation does not guarantee better classification, we should report both segmentation and classification performances when comparing segmentation algorithms. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Medical Physics is the property of Wiley-Blackwell 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=131206267 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1002/mp.13054 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 7 StartPage: 3650 Subjects: – SubjectFull: Breast cancer treatment Type: general – SubjectFull: Computer-aided diagnosis Type: general – SubjectFull: Image segmentation Type: general – SubjectFull: Breast cancer diagnosis Type: general – SubjectFull: Computer simulation Type: general Titles: – TitleFull: Relationship between computer segmentation performance and computer classification performance in breast CT: A simulation study using RGI segmentation and LDA classification. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Lee, Juhun – PersonEntity: Name: NameFull: Nishikawa, Robert M. – PersonEntity: Name: NameFull: Reiser, Ingrid – PersonEntity: Name: NameFull: Boone, John M. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 08 Text: Aug2018 Type: published Y: 2018 Identifiers: – Type: issn-print Value: 00942405 Numbering: – Type: volume Value: 45 – Type: issue Value: 8 Titles: – TitleFull: Medical Physics Type: main |
| ResultId | 1 |
