HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Hokkaido University Hospital >
Peer-reviewed Journal Articles, etc >

Automatic Estimation of Volumetric Breast Density Using Artificial Neural Network-Based Calibration of Full-Field Digital Mammography : Feasibility on Japanese Women With and Without Breast Cancer

Files in This Item:
Wang_et_al_2017_JDI.pdf642.64 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/68664

Title: Automatic Estimation of Volumetric Breast Density Using Artificial Neural Network-Based Calibration of Full-Field Digital Mammography : Feasibility on Japanese Women With and Without Breast Cancer
Authors: Wang, Jeff Browse this author
Kato, Fumi Browse this author →KAKEN DB
Yamashita, Hiroko Browse this author →KAKEN DB
Baba, Motoi Browse this author
Cui, Yi Browse this author
Li, Ruijiang Browse this author
Oyama-Manabe, Noriko Browse this author →KAKEN DB
Shirato, Hiroki Browse this author →KAKEN DB
Keywords: Artificial neural networks (ANN)
Breast tissue density
Computer analysis
Full-field digital mammography (FFDM)
Magnetic resonance imaging
Image processing
Machine learning
Imaging phantoms
Issue Date: Apr-2017
Publisher: Springer
Journal Title: Journal of digital imaging
Volume: 30
Issue: 2
Start Page: 215
End Page: 227
Publisher DOI: 10.1007/s10278-016-9922-9
Abstract: Background: Breast cancer is the most common invasive cancer among women and its incidence is increasing. Risk assessment is valuable and recent methods are incorporating novel biomarkers such as mammographic density. Artificial neural networks (ANN) are adaptive algorithms capable of performing pattern-to-pattern learning and are well suited for medical applications. They are potentially useful for calibrating Full-Field Digital Mammography (FFDM) for quantitative analysis. This study uses ANN modeling to estimate volumetric breast density (VBD) from FFDM on Japanese women with and without breast cancer. Methods: ANN calibration of VBD was performed using phantom data for one FFDM system. Mammograms of 46 Japanese women diagnosed with invasive carcinoma and 53 with negative findings were analyzed using ANN models learned. ANN-estimated VBD was validated against phantom data, compared intra-patient, with qualitative composition scoring, with MRI VBD, and inter-patient with classical risk factors of breast cancer as well as cancer status. Results: Phantom validations reached an R2 of 0.993. Intra-patient validations ranged from R2 of 0.789 with VBD to 0.908 with breast volume. ANN VBD agreed well with BI-RADS scoring and MRI VBD with R2 ranging from 0.665 with VBD to 0.852 with breast volume. VBD was significantly higher in women with cancer. Associations with age, BMI, menopause, and cancer status previously reported were also confirmed. Conclusions: ANN modeling appears to produce reasonable measures of mammographic density validated with phantoms, with existing measures of breast density, and with classical biomarkers of breast cancer. FFDM VBD is significantly higher in Japanese women with cancer.
Rights: The original publication is available at www.springerlink.com
Type: article (author version)
URI: http://hdl.handle.net/2115/68664
Appears in Collections:北海道大学病院 (Hokkaido University Hospital) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 加藤 扶美

Export metadata:

OAI-PMH ( junii2 , jpcoar )


 

Feedback - Hokkaido University