Benjamin Hinton1,2, Lin Ma3, Amir Pasha Mahmoudzadeh2, Serghei Malkov4, Bo Fan1, Heather Greenwood2, Bonnie Joe2, Vivian Lee5, Fredrik Strand6,7, Karla Kerlikowske8, John Shepherd9. 1. Department of Bioengineering, UC-San Francisco & UC-Berkeley Joint Program, San Francisco, CA, 94143, USA. 2. Department of Radiology and Biomedical Imaging, UC-San Francisco, San Francisco, CA, 94143, USA. 3. Kaiser Permanente Division of Research, Oakland, CA, 94612, USA. 4. Applied Materials, Santa Clara, CA, 95054, USA. 5. Research Advocate, UCSF Breast Science Advocacy Core, San Francisco, CA, 94143, USA. 6. Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Solna, Sweden. 7. Department of Thoracic Radiology, Karolinska University Hospital, Solna, Sweden. 8. Department of Epidemiology and Biostatistics, UCSF, San Francisco, CA, 94143, USA. 9. University of Hawaii Cancer Center, Honolulu, HI, 96813, USA.
Abstract
PURPOSE: Women with radiographically dense or texturally complex breasts are at increased risk for interval cancer, defined as cancers diagnosed after a normal screening examination. The purpose of this study was to create masking measures and apply them to identify interval risk in a population of women who experienced either screen-detected or interval cancers after controlling for breast density. METHODS: We examined full-field digital screening mammograms acquired from 2006 to 2015. Examinations associated with 182 interval cancers were matched to 173 screen-detected cancers on age, race, exam date and time since last imaging examination. Local Image Quality Factor (IQF) values were calculated and used to create IQF maps that represented mammographic masking. We used various statistics to define global masking measures of these maps. Association of these masking measures with interval cancer vs screen-detected cancer was estimated using conditional logistic regression in a univariate and adjusted model for Breast Imaging-Reporting and Data System (BI-RADS) density. Receiver operator curves were calculated in each case to compare specificity vs sensitivity, and area under those curves were generated. Proportion of screen-detected cancer was estimated for stratifications of IQF features. RESULTS: Several masking features showed significant association with interval compared to screen-detected cancers after adjusting for BI-RADS density (up to P = 2.52E-6), and the 10th percentile of the IQF value (P = 1.72E-3) showed the strongest improvement in the area under the receiver operator curve, increasing from 0.65 using only BI-RADS density to 0.69. The highest masking group had a 32% proportion of screen-detected cancers while the low masking group had a 69% proportion. CONCLUSIONS: We conclude that computer vision methods using model observers may improve quantifying the probability of breast cancer detection beyond using breast density alone.
PURPOSE:Women with radiographically dense or texturally complex breasts are at increased risk for interval cancer, defined as cancers diagnosed after a normal screening examination. The purpose of this study was to create masking measures and apply them to identify interval risk in a population of women who experienced either screen-detected or interval cancers after controlling for breast density. METHODS: We examined full-field digital screening mammograms acquired from 2006 to 2015. Examinations associated with 182 interval cancers were matched to 173 screen-detected cancers on age, race, exam date and time since last imaging examination. Local Image Quality Factor (IQF) values were calculated and used to create IQF maps that represented mammographic masking. We used various statistics to define global masking measures of these maps. Association of these masking measures with interval cancer vs screen-detected cancer was estimated using conditional logistic regression in a univariate and adjusted model for Breast Imaging-Reporting and Data System (BI-RADS) density. Receiver operator curves were calculated in each case to compare specificity vs sensitivity, and area under those curves were generated. Proportion of screen-detected cancer was estimated for stratifications of IQF features. RESULTS: Several masking features showed significant association with interval compared to screen-detected cancers after adjusting for BI-RADS density (up to P = 2.52E-6), and the 10th percentile of the IQF value (P = 1.72E-3) showed the strongest improvement in the area under the receiver operator curve, increasing from 0.65 using only BI-RADS density to 0.69. The highest masking group had a 32% proportion of screen-detected cancers while the low masking group had a 69% proportion. CONCLUSIONS: We conclude that computer vision methods using model observers may improve quantifying the probability of breast cancer detection beyond using breast density alone.
Authors: Karla Kerlikowske; Rebecca A Hubbard; Diana L Miglioretti; Berta M Geller; Bonnie C Yankaskas; Constance D Lehman; Stephen H Taplin; Edward A Sickles Journal: Ann Intern Med Date: 2011-10-18 Impact factor: 25.391
Authors: Saskia van Engeland; Peter R Snoeren; Henkjan Huisman; Carla Boetes; Nico Karssemeijer Journal: IEEE Trans Med Imaging Date: 2006-03 Impact factor: 10.048
Authors: F D Gilliland; N Joste; P M Stauber; W C Hunt; R Rosenberg; G Redlich; C R Key Journal: J Natl Cancer Inst Date: 2000-05-03 Impact factor: 13.506