arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.08273cs.CV
收藏

使用对称信息和深度学习改进乳腺癌检测

Improving Breast Cancer Detection using Symmetry Information with Deep Learning

Radboud University Medical Center(拉德堡德大学医学中心);University of Burgundy(勃艮第大学);University of Cassino and Southern Lazio(卡西诺和南拉齐奥大学);University of Girona(赫罗纳大学);Delft University of Technology(代尔夫特理工大学)

Yeman Brhane Hagos, Albert Gubern Merida, Jonas Teuwen

摘要:

卷积神经网络(CNN)在计算机视觉和医学图像分析的许多领域都取得了巨大的成功。然而,通过整合放射科医生利用的所有信息,例如对称性和时间数据,在乳房X线摄影乳腺癌检测计算机辅助检测(CAD)系统中仍然存在巨大的性能改进潜力。在这项工作中,我们提出了一个补丁为基础的多输入CNN,学习对称差异检测乳腺肿块。该网络在28294张乳房X光照片的大规模数据集上进行了训练。使用ROC曲线下面积(AUC)和竞争性能度量(CPM)将性能与没有对称背景的基线架构进行比较。在候选水平下,当结合对称性信息时,获得的AUC值为0.933,95%置信区间为[0.920,0.954],与基线结构相比,基线结构产生的AUC值为0.929,置信区间为[0.919,0.947]。通过纳入对称信息,虽然没有显著的候选人水平的表现再次(p = 0.111),我们发现了一个令人信服的结果,在考试水平的CPM值为0.733(p = 0.001)。我们认为,包括时间数据,并添加良性类的数据集可以提高检测性能。

英文摘要:

Convolutional Neural Networks (CNN) have had a huge success in many areas of computer vision and medical image analysis. However, there is still an immense potential for performance improvement in mammogram breast cancer detection Computer-Aided Detection (CAD) systems by integrating all the information that the radiologist utilizes, such as symmetry and temporal data. In this work, we proposed a patch based multi-input CNN that learns symmetrical difference to detect breast masses. The network was trained on a large-scale dataset of 28294 mammogram images. The performance was compared to a baseline architecture without symmetry context using Area Under the ROC Curve (AUC) and Competition Performance Metric (CPM). At candidate level, AUC value of 0.933 with 95% confidence interval of [0.920, 0.954] was obtained when symmetry information is incorporated in comparison with baseline architecture which yielded AUC value of 0.929 with [0.919, 0.947] confidence interval. By incorporating symmetrical information, although there was no a significant candidate level performance again (p = 0.111), we have found a compelling result at exam level with CPM value of 0.733 (p = 0.001). We believe that including temporal data, and adding benign class to the dataset could improve the detection performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑