Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter?
Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter?
复制标题
DOI：
10.1002/mp.12320
复制
发表时间：
2017-09
期刊：
影响因子：
3.8
通讯作者：
Silva IDS
中科院分区：
文献类型：
--
作者：
Doran SJ;Hipwell JH;Denholm R;Eiben B;Busana M;Hawkes DJ;Leach MO;Silva IDS
在大型受试者队列中比较两种自动乳房分割方法以及与手动分割方法。讨论选择最合适的自动分割算法所涉及的因素，特别是研究重叠度量（例如 Dice 和 Jaccard 系数）作为算法选择的主要决定因素的适当性。两种乳房分割方法被应用于计算 MRI 乳腺密度的任务，该任务从雅芳父母和儿童纵向研究（一项包含 MRI 成分的大型队列研究）中抽取了 200 名受试者。半自动、偏差校正、模糊 C 均值 (BC-FCM) 方法与形态学操作相结合，从同相 Dixon 图像中分割整个乳房体积。该方法利用新颖的、针对具体问题的见解。然后将所得分割掩模应用于相应的 Dixon 水和脂肪图像，将其组合以给出 Dixon MRI 密度值。使用一种新颖的全自动算法对同时采集的 T1 和 T2 加权图像数据集进行分析，该算法涉及图像过滤、地标识别和胸肌边界的显式定位。在发现的区域内，使用期望最大化-马尔可夫随机场技术进行脂肪-水区分，产生 MRI 密度的第二个独立估计。展示了两名女性的图像，展示了问题的难度是如何高度特定于主题的。介绍了对 Dixon 源数据操作的半自动 BC-FCM 方法与专家手动分割进行比较的 Dice 和 Jaccard 系数。在所示的个别案例中，基于 T1 和 T2 加权数据的方法的相应结果略低，但整个队列的散点图和类间相关性表明，两种方法在乳腺组织的分割和分类方面都表现出色。流行病学结果表明，这两种自动分割方法都适合所选的应用，并且在选择分割算法时考虑一系列因素非常重要，而不是狭隘地关注 Dice 系数等单一指标。
To 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. Two 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. Images 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. Epidemiological 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.
登录
查看更多内容
影响因子：
3.8
作者：
Ertas, Gokhan;Gulcur, H. Ozcan;Ucan, Osman Nuri
通讯作者：
Ucan, Osman Nuri
影响因子：
10.6
作者：
Khalvati, Farzad;Gallego-Ortiz, Cristina;Martel, Anne L.
通讯作者：
Martel, Anne L.
影响因子：
3.8
作者：
Ortiz, C. Gallego;Martel, A. L.
通讯作者：
Martel, A. L.
影响因子：
3.8
作者：
Lin, Muqing;Chan, Siwa;Su, Min-Ying
通讯作者：
Su, Min-Ying
影响因子：
3.7
作者：
Ledger AE;Scurr ED;Hughes J;Macdonald A;Wallace T;Thomas K;Wilson R;Leach MO;Schmidt MA
通讯作者：
Schmidt MA