Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations
Generalised Dice Overlap as a Deep Learning Loss Function for Highly Unbalanced Segmentations
复制标题
DOI：
10.1007/978-3-319-67558-9_28
复制
发表时间：
2017-09-09
期刊：
影响因子：
--
通讯作者：
Jorge Cardoso M
中科院分区：
文献类型：
--
作者：
Sudre CH;Li W;Vercauteren T;Ourselin S;Jorge Cardoso M
近年来，深度学习已被证明是一种强大的图像分析工具，现在被广泛用于分割2D和3D医学图像。深度学习分割框架不仅依赖于网络架构的选择，还依赖于损失函数的选择。当分割过程针对罕见的观察结果时，候选标签之间可能会出现严重的类别不平衡，从而导致次优性能。为了缓解这个问题，已经提出了诸如加权交叉熵函数、灵敏度函数或Dice损失函数之类的策略。在这项工作中，我们研究了这些损失函数的行为及其对学习率调整的敏感性，在2D和3D分割任务中存在不同的标签不平衡率。我们还建议使用广义骰子重叠（一种已知的分割评估指标）的类重新平衡属性，作为不平衡任务的鲁棒且准确的深度学习损失函数。
Deep-learning has proved in recent years to be a powerful tool for image analysis and is now widely used to segment both 2D and 3D medical images. Deep-learning segmentation frameworks rely not only on the choice of network architecture but also on the choice of loss function. When the segmentation process targets rare observations, a severe class imbalance is likely to occur between candidate labels, thus resulting in sub-optimal performance. In order to mitigate this issue, strategies such as the weighted cross-entropy function, the sensitivity function or the Dice loss function, have been proposed. In this work, we investigate the behavior of these loss functions and their sensitivity to learning rate tuning in the presence of different rates of label imbalance across 2D and 3D segmentation tasks. We also propose to use the class re-balancing properties of the Generalized Dice overlap, a known metric for segmentation assessment, as a robust and accurate deep-learning loss function for unbalanced tasks.
登录
查看更多内容
影响因子：
10.9
作者：
Havaei, Mohammad;Davy, Axel;Larochelle, Hugo
通讯作者：
Larochelle, Hugo
影响因子：
10.6
作者：
Crum, William R.;Camara, Oscar;Hill, Derek L. G.
通讯作者：
Hill, Derek L. G.
多模式的脑肿瘤图像分割基准（Brats）。
影响因子：
10.6
作者：
Menze BH;Jakab A;Bauer S;Kalpathy-Cramer J;Farahani K;Kirby J;Burren Y;Porz N;Slotboom J;Wiest R;Lanczi L;Gerstner E;Weber MA;Arbel T;Avants BB;Ayache N;Buendia P;Collins DL;Cordier N;Corso JJ;Criminisi A;Das T;Delingette H;Demiralp Ç;Durst CR;Dojat M;Doyle S;Festa J;Forbes F;Geremia E;Glocker B;Golland P;Guo X;Hamamci A;Iftekharuddin KM;Jena R;John NM;Konukoglu E;Lashkari D;Mariz JA;Meier R;Pereira S;Precup D;Price SJ;Raviv TR;Reza SM;Ryan M;Sarikaya D;Schwartz L;Shin HC;Shotton J;Silva CA;Sousa N;Subbanna NK;Szekely G;Taylor TJ;Thomas OM;Tustison NJ;Unal G;Vasseur F;Wintermark M;Ye DH;Zhao L;Zhao B;Zikic D;Prastawa M;Reyes M;Van Leemput K
通讯作者：
Van Leemput K
影响因子：
10.9
作者：
Kamnitsas, Konstantinos;Ledig, Christian;Glocker, Ben
通讯作者：
Glocker, Ben