The diagnostic performance of leak-plugging automated segmentation versus manual tracing of breast lesions on ultrasound images. (May 2017)
- Record Type:
- Journal Article
- Title:
- The diagnostic performance of leak-plugging automated segmentation versus manual tracing of breast lesions on ultrasound images. (May 2017)
- Main Title:
- The diagnostic performance of leak-plugging automated segmentation versus manual tracing of breast lesions on ultrasound images
- Authors:
- Xiong, Hui
Sultan, Laith R
Cary, Theodore W
Schultz, Susan M
Bouzghar, Ghizlane
Sehgal, Chandra M - Abstract:
- Purpose: To assess the diagnostic performance of a leak-plugging segmentation method that we have developed for delineating breast masses on ultrasound images. Materials and methods: Fifty-two biopsy-proven breast lesion images were analyzed by three observers using the leak-plugging and manual segmentation methods. From each segmentation method, grayscale and morphological features were extracted and classified as malignant or benign by logistic regression analysis. The performance of leak-plugging and manual segmentations was compared by: size of the lesion, overlap area ( Oa ) between the margins, and area under the ROC curves ( Az ). Results: The lesion size from leak-plugging segmentation correlated closely with that from manual tracing ( R 2 of 0.91). Oa was higher for leak plugging, 0.92 ± 0.01 and 0.86 ± 0.06 for benign and malignant masses, respectively, compared to 0.80 ± 0.04 and 0.73 ± 0.02 for manual tracings. Overall Oa between leak-plugging and manual segmentations was 0.79 ± 0.14 for benign and 0.73 ± 0.14 for malignant lesions. Az for leak plugging was consistently higher (0.910 ± 0.003) compared to 0.888 ± 0.012 for manual tracings. The coefficient of variation of Az between three observers was 0.29% for leak plugging compared to 1.3% for manual tracings. Conclusion: The diagnostic performance, size measurements, and observer variability for automated leak-plugging segmentations were either comparable to or better than those of manual tracings.
- Is Part Of:
- Ultrasound. Volume 25:Number 2(2017:May)
- Journal:
- Ultrasound
- Issue:
- Volume 25:Number 2(2017:May)
- Issue Display:
- Volume 25, Issue 2 (2017)
- Year:
- 2017
- Volume:
- 25
- Issue:
- 2
- Issue Sort Value:
- 2017-0025-0002-0000
- Page Start:
- 98
- Page End:
- 106
- Publication Date:
- 2017-05
- Subjects:
- Breast cancer -- ultrasonography -- lesion segmentation -- computer-aided analysis
Ultrasonic imaging -- Periodicals
Ultrasonography -- Periodicals
616.0754305 - Journal URLs:
- http://ult.sagepub.com/ ↗
http://www.maney.co.uk/search?fwaction=show&fwid=440 ↗
http://www.maney.co.uk/search?fwaction=show&fwid=440&fwprint=yes ↗
http://www.uk.sagepub.com/home.nav ↗ - DOI:
- 10.1177/1742271X17690425 ↗
- Languages:
- English
- ISSNs:
- 1742-271X
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 7955.xml