A deep learning approach for the analysis of masses in mammograms with minimal user intervention
A deep learning approach for the analysis of masses in mammograms with minimal user intervention
复制标题
DOI：
10.1016/j.media.2017.01.009
复制
发表时间：
2017-04-01
影响因子：
10.9
通讯作者：
Bradley, Andrew P.
中科院分区：
文献类型：
--
作者：
Dhungel, Neeraj;Carneiro, Gustavo;Bradley, Andrew P.
我们提出了一个集成的方法，用于检测，分割和分类乳房肿块从乳房X光片与最小的用户干预。这是一个长期存在的问题，因为在乳房肿块的可视化中信号-噪声比低，加上它们在形状、大小、外观和位置方面的巨大变化。我们将问题分为三个阶段：质量检测，质量分割和质量分类。对于检测，我们提出了一系列深度学习方法来选择基于贝叶斯优化的假设。对于分割，我们建议使用深度结构化输出学习，随后通过水平集方法进行优化。最后，对于分类，我们建议使用深度学习分类器，该分类器通过回归手工制作的特征值进行预训练，并根据乳腺肿块分类数据集的注释进行微调。我们在公开的INbreast数据集上测试了我们提出的系统，并将结果与当前最先进的方法进行了比较。该评估表明，我们的系统在每幅图像1个假阳性时检测到90%的肿块，在正确检测到的肿块上具有约0.85的分割准确度（Dice指数），并且总体上将肿块分类为恶性或良性，灵敏度（Se）为0.98，特异性（Sp）为0.7。(C)2017爱思唯尔B. V.保留所有权利。
We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal-tonoise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down into three stages: mass detection, mass segmentation, and mass classification. For the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimisation. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose the use of a deep learning classifier, which is pre-trained with a regression to hand-crafted feature values and fine-tuned based on the annotations of the breast mass classification dataset. We test our proposed system on the publicly available INbreast dataset and compare the results with the current state-of-the-art methodologies. This evaluation shows that our system detects 90% of masses at 1 false positive per image, has a segmentation accuracy of around 0.85 (Dice index) on the correctly detected masses, and overall classifies masses as malignant or benign with sensitivity (Se) of 0.98 and specificity (Sp) of 0.7. (C) 2017 Elsevier B.V. All rights reserved.