Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter?

Abstract

PurposeTo compare two methods of automatic breast segmentation with each other and with manual segmentation in a large subject cohort. To discuss the factors involved in selecting the most appropriate algorithm for automatic segmentation and, in particular, to investigate the appropriateness of overlap measures (e.g., Dice and Jaccard coefficients) as the primary determinant in algorithm selection.MethodsTwo methods of breast segmentation were applied to the task of calculating MRI breast density in 200 subjects drawn from the Avon Longitudinal Study of Parents and Children, a large cohort study with an MRI component. A semiautomated, bias‐corrected, fuzzy C‐means (BC‐FCM) method was combined with morphological operations to segment the overall breast volume from in‐phase Dixon images. The method makes use of novel, problem‐specific insights. The resulting segmentation mask was then applied to the corresponding Dixon water and fat images, which were combined to give Dixon MRI density values. Contemporaneously acquired T1‐ and T2‐weighted image datasets were analyzed using a novel and fully automated algorithm involving image filtering, landmark identification, and explicit location of the pectoral muscle boundary. Within the region found, fat‐water discrimination was performed using an Expectation Maximization–Markov Random Field technique, yielding a second independent estimate of MRI density.ResultsImages are presented for two individual women, demonstrating how the difficulty of the problem is highly subject‐specific. Dice and Jaccard coefficients comparing the semiautomated BC‐FCM method, operating on Dixon source data, with expert manual segmentation are presented. The corresponding results for the method based on T1‐ and T2‐weighted data are slightly lower in the individual cases shown, but scatter plots and interclass correlations for the cohort as a whole show that both methods do an excellent job in segmenting and classifying breast tissue.ConclusionsEpidemiological results demonstrate that both methods of automated segmentation are suitable for the chosen application and that it is important to consider a range of factors when choosing a segmentation algorithm, rather than focus narrowly on a single metric such as the Dice coefficient.

Breast density: why all the fuss?

“…The for FGV estimation. Recent work from the UCL group suggests that the optimal automatic segmentation is highly subject-specific and one size may not fit all (153).…”

Circulating Growth and Sex Hormone Levels and Breast Tissue Composition in Young Nulliparous Women

“…Of the 500 participants who had an MRI examination, valid breast parameters were produced for 491. A full description of the methodology, and of its validity, is given in Doran and colleagues (28).…”

“…To our knowledge, this is the first study to examine breast tissue composition in young women prior to it being affected by reproductive-related events (e.g., pregnancies, breastfeeding). Other strengths of the study include the use of objective, and previously validated, methods of assessing volumetric breast tissue composition (28). The unique prebirth cohort design meant that prospective standardized data on a wide range of childhood and adolescence variables, including certain adolescent hormone measurements, could be used alongside hormone measurements performed when participants were aged 21.5.…”

An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U‐nets

“…They also defined groupings of the measures and recommended selecting metrics from different groups to avoid biased results. Moreover, Doran et al . recommend choosing the best model based on more than one metric.…”

“…Breast-air boundary is determined by a region growing method recommended selecting metrics from different groups to avoid biased results. Moreover, Doran et al 6 recommend choosing the best model based on more than one metric. Table II shows the error measures reported in the breast MRI segmentation papers and provides the definition of each metric.…”