A novel CNN algorithm for pathological complete response prediction using an I-SPY TRIAL breast MRI database.

A novel CNN algorithm for pathological complete response prediction using an I-SPY TRIAL breast MRI database.
复制标题

使用I-SPY试验乳腺MRI数据库的新型CNN算法用于病理完全反应预测。

DOI:
10.1016/j.mri.2020.08.021
复制
发表时间:
2020-11
影响因子:
2.5
通讯作者:
Ha R
Ha R
中科院分区:
医学4区
文献类型:
--
作者:
Liu MZ;Mutasa S;Chang P;Siddique M;Jambawalikar S;Ha R

文献摘要

参考文献

被引文献

相似文献

应用我们的卷积神经网络(CNN)算法,使用I-SPY TRIAL乳腺MRI数据集预测新辅助化疗(NAC)反应。从I-SPY TRIAL乳腺MRI数据库中,成功下载了来自9家机构的131例患者进行分析。使用3D切片器将第一对比后MRI图像用于3D分割。我们的CNN完全由3 × 3卷积核和线性层实现。卷积核由6个剩余层组成,总共12个卷积层。使用保留概率为0.5的脱落和L2归一化。训练是通过使用Adam优化器实施的。使用5倍交叉验证进行性能评价。软件代码是在带有一个NVidia Titan X GPU的Linux工作站上使用TensorFlow模块用Python编写的。在131名患者中,40名患者在NAC后达到pCR(第1组),91名患者在NAC后未达到pCR(第2组)。我们的CNN两分类模型区分pCR与非pCR患者的诊断准确性为72.5(SD ± 8.4),敏感性为65.5%(SD ± 28.1),特异性为78.9%(SD ± 15.2)。ROC曲线下面积(AUC)为0.72(SD ± 0.08)。使用我们的CNN算法来预测使用多机构数据集的患者的NAC反应是可行的。
To apply our convolutional neural network (CNN) algorithm to predict neoadjuvant chemotherapy (NAC) response using the I-SPY TRIAL breast MRI dataset. From the I-SPY TRIAL breast MRI database, 131 patients from 9 institutions were successfully downloaded for analysis. First post-contrast MRI images were used for 3D segmentation using 3D slicer. Our CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer. A 5-fold cross validation was used for performance evaluation. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. Of 131 patients, 40 patients achieved pCR following NAC (group 1) and 91 patients did not achieve pCR following NAC (group 2). Diagnostic accuracy of our CNN two classification model distinguishing patients with pCR vs non-pCR was 72.5 (SD ± 8.4), with sensitivity 65.5% (SD ± 28.1) and specificity of 78.9% (SD ± 15.2). The area under a ROC Curve (AUC) was 0.72 (SD ± 0.08). It is feasible to use our CNN algorithm to predict NAC response in patients using a multi-institution dataset.
DOI: 10.1007/s10278-018-0144-1
发表时间: 2019-10-01
影响因子: 4.4
作者:
Ha, Richard;Chin, Christine;Jambawalikar, Sachin
通讯作者: Jambawalikar, Sachin
DOI: 10.1002/jso.23439
发表时间: 2013-12-01
影响因子: 2.5
作者:
Cho, Jung Hoon;Park, Ji Min;Park, Byeong-Woo
通讯作者: Park, Byeong-Woo
DOI: 10.1016/j.cma.2016.08.024
发表时间: 2017-02-01
影响因子: 7.2
作者:
Weis JA;Miga MI;Yankeelov TE
通讯作者: Yankeelov TE
DOI: 10.1002/jmri.26244
发表时间: 2019-03
期刊: Journal of magnetic resonance imaging : JMRI
影响因子: --
作者:
Ha R;Chang P;Mutasa S;Karcich J;Goodman S;Blum E;Kalinsky K;Liu MZ;Jambawalikar S
通讯作者: Jambawalikar S
DOI: 10.1016/j.mri.2012.06.010
发表时间: 2012-11
影响因子: 2.5
作者:
Kumar V;Gu Y;Basu S;Berglund A;Eschrich SA;Schabath MB;Forster K;Aerts HJ;Dekker A;Fenstermacher D;Goldgof DB;Hall LO;Lambin P;Balagurunathan Y;Gatenby RA;Gillies RJ
通讯作者: Gillies RJ