Computer-aided detection (CAD) system for breast MRI in assessment of local tumor extent, nodal status, and multifocality of invasive breast cancers: preliminary study
- Authors
- Song, Sung Eun; Seo, Bo Kyoung; Cho, Kyu Ran; Woo, Ok Hee; Son, Gil Soo; Kim, Chulhan; Cho, Sung Bum; Kwon, Soon-Sun
- Issue Date
- 8-2월-2015
- Publisher
- E-MED
- Keywords
- Breast; Breast neoplasm; Tumor staging; Computer assisted diagnosis; Magnetic resonance imaging
- Citation
- CANCER IMAGING, v.15
- Indexed
- SCIE
SCOPUS
- Journal Title
- CANCER IMAGING
- Volume
- 15
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/94410
- DOI
- 10.1186/s40644-015-0036-2
- ISSN
- 1740-5025
- Abstract
- Background: We aimed to investigate the efficacy of computer-aided detection (CAD) for MRI in the assessment of tumor extent, lymph node status, and multifocality in invasive breast cancers in comparison with other breast imaging modalities. Methods: Two radiologists measured the maximum tumor size, as well as, analyzed lymph node status and multifocality in 86 patients with invasive breast cancers using mammography, ultrasound, CT, MRI with and without CAD, and 18-fludeoxyglucose positron emission tomography (FDG-PET). The assessed data were compared with pathology. Results: For tumor extent, there were no significant differences between pathological size and measured size using mammography, ultrasound, CT, or MRI with and without CAD (P > 0.05). For evaluation of lymph node status, ultrasound had the best kappa coefficients (0.522) for agreement between imaging and pathology, and diagnostic performance with 92.1% specificity and 90.0% positive predictive value. For multifocality, MRI with CAD had the highest area under the receiver operating characteristic curve (AUC = 0.888). Conclusions: CAD for MRI is feasible to assess tumor extent and multifocality in invasive breast cancer patients. However, CAD is not effective in evaluation of nodal status.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Medicine > Department of Medical Science > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.