A deep learning method for classifying mammographic breast density categories.
A deep learning method for classifying mammographic breast density categories.
复制标题
一种用于分类乳房乳房密度类别的深度学习方法。
DOI：
10.1002/mp.12683
复制
发表时间：
2018-01
期刊：
影响因子：
3.8
通讯作者：
Wu S
中科院分区：
文献类型：
--
作者：
Mohamed AA;Berg WA;Peng H;Luo Y;Jankowitz RC;Wu S
乳房X线摄影乳腺密度是乳腺癌的既定风险标志物，由放射科医生在常规乳房X线摄影图像阅读中使用四种定性乳腺成像和报告数据系统（BI-RADS）乳腺密度类别进行目视评估。放射科医师特别难以一致地区分两个最常见和最容易分配的BI-RADS类别，即，“分散密度”和“非均匀致密”。这项工作的目的是研究一种基于深度学习的乳腺密度分类器，以始终区分这两个类别，旨在提供一种潜在的计算机化工具，以帮助放射科医生在当前的临床工作流程中分配BI-RADS类别。在这项研究中，我们构建了一个基于卷积神经网络（CNN）的模型，22，000张图像）数字乳房X线摄影成像数据集，以评估上述两种乳腺密度类别之间的分类性能。所有图像均收集自2005年至2016年在我们机构接受标准数字乳腺X射线摄影筛查的1，427名女性。密度类别的真实性是基于由委员会认证的乳腺成像放射科医生进行的标准临床评估。针对乳腺密度分类的特定任务，评估了仅使用数字乳腺X线照片图像从头开始直接训练和对大型非医学成像数据集进行预训练模型的迁移学习的效果。为了测量分类性能，CNN分类器还通过删除一些可能不准确标记的图像，在乳房X光照片图像数据集的改进版本上进行了测试。使用受试者工作特征（ROC）曲线和曲线下面积（AUC）来衡量分类器的准确性。当CNN模型在我们自己的乳房X线照片图像上从头开始训练时，AUC为0.9421，并且准确性随着训练样本大小的增加而沿着逐渐增加。使用预训练的模型，然后使用少至500张乳房X光照片进行微调，导致AUC为0.9265。在去除可能不准确标记的图像后，AUC分别增加到0.9882和0.9857，这两个值都显著高于（p<0.001）使用完整成像数据集时的值。我们的研究证明了两个难以区分的乳腺密度类别之间的高分类准确性，这是由放射科医生常规评估的。我们预计，我们的方法将有助于提高目前的乳腺密度的临床评估，并更好地支持一致的密度通知乳腺癌筛查患者。
Mammographic breast density is an established risk marker for breast cancer and is visually assessed by radiologists in routine mammogram image reading, using four qualitative Breast Imaging and Reporting Data System (BI-RADS) breast density categories. It is particularly difficult for radiologists to consistently distinguish the two most common and most variably assigned BI-RADS categories, i.e., “scattered density” and “heterogeneously dense”. The aim of this work was to investigate a deep learning-based breast density classifier to consistently distinguish these two categories, aiming at providing a potential computerized tool to assist radiologists in assigning a BI-RADS category in current clinical workflow. In this study, we constructed a convolutional neural network (CNN)-based model coupled with a large (i.e., 22,000 images) digital mammogram imaging dataset to evaluate the classification performance between the two aforementioned breast density categories. All images were collected from a cohort of 1,427 women who underwent standard digital mammography screening from 2005 to 2016 at our institution. The truths of the density categories were based on standard clinical assessment made by board-certified breast imaging radiologists. Effects of direct training from scratch solely using digital mammogram images and transfer learning of a pre-trained model on a large non-medical imaging dataset were evaluated for the specific task of breast density classification. In order to measure the classification performance, the CNN classifier was also tested on a refined version of the mammogram image dataset by removing some potentially inaccurately labeled images. Receiver operating characteristic (ROC) curves and the area under the curve (AUC) were used to measure the accuracy of the classifier. The AUC was 0.9421 when the CNN-model was trained from scratch on our own mammogram images, and the accuracy increased gradually along with an increased size of training samples. Using the pre-trained model followed by a fine-tuning process with as few as 500 mammogram images led to an AUC of 0.9265. After removing the potentially inaccurately labeled images, AUC was increased to 0.9882 and 0.9857 for without and with the pre-trained model, respectively, both significantly higher (p<0.001) than when using the full imaging dataset. Our study demonstrated high classification accuracies between two difficult to distinguish breast density categories that are routinely assessed by radiologists. We anticipate that our approach will help enhance current clinical assessment of breast density and better support consistent density notification to patients in breast cancer screening.
登录
查看更多内容
影响因子：
3.3
作者：
Gram, IT;Funkhouser, E;Tabar, L
通讯作者：
Tabar, L
影响因子：
3.8
作者：
Maskarinec, G;Pagano, I;Kolonel, LN
通讯作者：
Kolonel, LN
影响因子：
--
作者：
Janowczyk A;Madabhushi A
通讯作者：
Madabhushi A
影响因子：
3.5
作者：
BYNG, JW;BOYD, NF;YAFFE, MJ
通讯作者：
YAFFE, MJ
DOI：
10.1097/gme.0b013e318032569c
发表时间：
2007-09-01
影响因子：
2.7
作者：
Habel, Laurel A.;Capra, Angela M.;Sternfeld, Barbara
通讯作者：
Sternfeld, Barbara