A hybrid approach for mammary gland segmentation on CT images by embedding visual explanations from a deep learning classifier into a Bayesian inference
A hybrid approach for mammary gland segmentation on CT images by embedding visual explanations from a deep learning classifier into a Bayesian inference
复制标题
通过将深度学习分类器的视觉解释嵌入到贝叶斯推理中，对 CT 图像进行乳腺分割的混合方法
DOI：
10.1117/12.2581924
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Fujita Hiroshi
中科院分区：
文献类型：
--
作者：
Zhou Xiangrong;Yamagishi Seiya;Hara Takeshi;Fujita Hiroshi
我们提出了一种自动分割乳腺区域的三维CT图像的方法，旨在实现乳腺癌的风险评估，通过在临床医学中获得的各种诊断目的的CT扫描。该方法使用一种混合方法，将基于深度学习的注意力机制作为一个模块嵌入到传统框架中，该框架最初使用概率图谱来完成贝叶斯推理，以估计CT图像上乳腺区域的像素概率。在这项工作中，我们取代了建设和应用的概率地图集，这是耗时和复杂的实现，从通过弱监督学习的分类器的注意力机制的视觉解释。在实验中，我们应用所提出的方法分割的乳腺区域的基础上，174躯干CT扫描，并评估其性能，通过比较分割结果，人体素描14例CT。实验结果表明，该分类器的注意力图能够成功地聚焦于CT图像上的乳腺区域，可以代替图谱支持乳腺分割。对14个测试CT扫描的初步结果表明，乳腺区域被成功分割与人类草图的Dice相似系数的平均值为50.6%。我们证实，所提出的方法结合了深度学习和传统方法，比我们以前基于概率图谱的方法具有更高的计算效率，更好的鲁棒性和更容易实现。
We propose an approach for the automatic segmentation of mammary gland regions on 3D CT images, aiming to accomplish breast cancer risk assessment through CT scans acquired in clinical medicine for various diagnostic purposes. The proposed approach uses a hybrid method that embeds a deep-learning-based attention mechanism as a module into a conventional framework, which originally uses a probabilistic atlas to accomplish Bayesian inference to estimate the pixelwise probability of mammary gland regions on CT images. In this work, we replace both the construction and application of a probabilistic atlas, which is time-consuming and complicated to realize, by a visual explanation from the attention mechanism of a classifier learned through weak supervision. In the experiments, we applied the proposed approach to the segmentation of mammary gland regions based on 174 torso CT scans and evaluated its performance by comparing the segmentation results to human sketches on 14 CT cases. The experimental results showed that the attention maps of the classifier successfully focused on the mammary gland regions on the CT images and could replace the atlas for supporting mammary gland segmentation. The preliminary results on 14 test CT scans showed that the mammary gland regions were segmented successfully with a mean value of 50.6% on the Dice similarity coefficient against the human sketches. We confirmed that the proposed approach, combining deep learning and conventional methods, shows a higher computing efficiency, much better robustness, and easier implementation than our previous approach based on a probabilistic atlas.
登录
查看更多内容
DOI：
10.1016/j.compmedimag.2008.08.007
发表时间：
2008-12
期刊：
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
影响因子：
--
作者：
Xiangrong Zhou;Mingxu Han;T. Hara;H. Fujita;K. Sugisaki;Huayue Chen;Gobert N. Lee;R. Yokoyama;M. Kanematsu;H. Hoshi
通讯作者：
Xiangrong Zhou;Mingxu Han;T. Hara;H. Fujita;K. Sugisaki;Huayue Chen;Gobert N. Lee;R. Yokoyama;M. Kanematsu;H. Hoshi
从低剂量胸部 CT 图像中分割整个乳房
影响因子：
--
作者：
Shuang Liu;M. Salvatore;D. Yankelevitz;C. Henschke;A. Reeves
通讯作者：
A. Reeves
通过低剂量胸部 CT 进行全自动乳腺密度评估
DOI：
--
发表时间：
2017
期刊：
Medical Imaging
影响因子：
--
作者：
Shuang Liu;L. Margolies;Yiting Xie;D. Yankelevitz;C. Henschke;A. Reeves
通讯作者：
A. Reeves
影响因子：
5
作者：
WOLFE, JN;SAFTLAS, AF;SALANE, M
通讯作者：
SALANE, M