Reliability of the Percent Density in Digital Mammography with a Semi-Automated Thresholding Method.
10.4048/jbc.2014.17.2.174
- Author:
Guiyun SOHN
1
;
Jong Won LEE
;
Sung Won PARK
;
Jihoon PARK
;
Jiyoung WOO
;
Hwa Jung KIM
;
Hee Jung SHIN
;
Hak Hee KIM
;
Kyung Hae JUNG
;
Joohon SUNG
;
Seung Wook LEE
;
Byung Ho SON
;
Sei Hyun AHN
Author Information
1. Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea. asanbreastcenter@gmail.com
- Publication Type:Original Article
- Keywords:
Breast;
Mammography;
Observer variation
- MeSH:
Body Mass Index;
Breast;
Breast Feeding;
Breast Neoplasms;
Humans;
Information Systems;
Mammography*;
Observer Variation
- From:Journal of Breast Cancer
2014;17(2):174-179
- CountryRepublic of Korea
- Language:English
-
Abstract:
PURPOSE: The reliability of the quantitative measurement of breast density with a semi-automated thresholding method (Cumulus(TM)) has mainly been investigated with film mammograms. This study aimed to evaluate the intrarater reproducibility of percent density (PD) by Cumulus(TM) with digital mammograms. METHODS: This study included 1,496 craniocaudal digital mammograms from the unaffected breast of breast cancer patients. One rater reviewed each mammogram and estimated the PD using the Cumulus(TM) method. All images were reassessed by the same rater 1 month later without reference to the previously assigned values. The repeatability of the PD was evaluated by an intraclass correlation coefficient (ICC). All patients were grouped based on their body mass index (BMI), age, family history of breast cancer, breastfeeding history and breast area (calculated with Cumulus(TM)), and subgroup analysis for the ICC of each group was performed. All patients were categorized by their Breast Imaging Reporting and Data System (BI-RADS) density pattern, and the mean and standard deviation of the PD by each BI-RADS categories were compared. RESULTS: The ICC for the PD was 0.94, indicating excellent repeatability. The discrepancy between the paired PD values ranged from 0 to 23.93, with an average of 3.90 (standard deviation=3.39). The subgroup ICCs for the PD ranged from 0.88 to 0.96, indicating excellent reliability in all subgroups regardless of patient variables. The ICCs of the PD for the high-risk (BI-RADS 3 and 4) and low-risk (BI-RADS 1 and 2) groups were 0.90 and 0.88, respectively. CONCLUSION: This study suggests that PD calculated with digital mammograms has an acceptable reliability regardless of patient age, BMI, family history of breast cancer, breastfeeding history, breast size, and BI-RADS density pattern.
