Stable and discriminating features are predictive of cancer presence and Gleason grade in radical prostatectomy specimens: a multi-site study.
Stable and discriminating features are predictive of cancer presence and Gleason grade in radical prostatectomy specimens: a multi-site study.
复制标题
DOI：
10.1038/s41598-018-33026-5
复制
发表时间：
2018-10-08
影响因子：
4.6
通讯作者：
Madabhushi A
中科院分区：
文献类型：
--
作者：
Leo P;Elliott R;Shih NNC;Gupta S;Feldman M;Madabhushi A
固定、染色和扫描的部位变化会混淆基于组织的自动图像分类器对疾病特征的描述。在这项研究中，我们将稳定性纳入四种特征选择方法，以确定两种前列腺组织病理学分类任务中最稳健和最具区别性的特征。我们评估了来自四个部位N = 212例前列腺切除术标本的242个形态学特征，用于自动癌症检测和分级。我们将不稳定性量化为显著的跨位点特征差异率。我们使用188个非癌区和210个癌区，通过3倍交叉验证绘制了特征稳定性和可判别性，然后保留了一个站点，创建了独立的训练和测试集。在训练中，一个特征集仅用于判别性，另一个特征集用于判别性和稳定性。我们用每个特征集训练了一个分类器，在hold out站点上进行测试。117个Gleason 3级区和112个Gleason 4级区重复实验。在非癌区计算稳定性。腺体形状特征在接收工作曲线（AUC）权衡下的稳定性和面积最好，而共出现的纹理特征通常不稳定。我们的稳定性通知方法产生的癌症检测AUC为0.98±0.05，将平均Gleason分级AUC提高了4.38%。图像的颜色归一化容易加剧特征的不稳定性。
Site variation in fixation, staining, and scanning can confound automated tissue based image classifiers for disease characterization. In this study we incorporated stability into four feature selection methods for identifying the most robust and discriminating features for two prostate histopathology classification tasks. We evaluated 242 morphology features from N = 212 prostatectomy specimens from four sites for automated cancer detection and grading. We quantified instability as the rate of significant cross-site feature differences. We mapped feature stability and discriminability using 188 non-cancerous and 210 cancerous regions via 3-fold cross validation, then held one site out, creating independent training and testing sets. In training, one feature set was selected only for discriminability, another for discriminability and stability. We trained a classifier with each feature set, testing on the hold out site. Experiments were repeated with 117 Gleason grade 3 and 112 grade 4 regions. Stability was calculated across non-cancerous regions. Gland shape features yielded the best stability and area under the receiver operating curve (AUC) trade-off while co-occurrence texture features were generally unstable. Our stability-informed method produced a cancer detection AUC of 0.98 ± 0.05 and increased average Gleason grading AUC by 4.38%. Color normalization of the images tended to exacerbate feature instability.
登录
查看更多内容
影响因子：
2.4
作者：
Leo, Patrick;Lee, George;Madabhushi, Anant
通讯作者：
Madabhushi, Anant
影响因子：
4.6
作者：
Parmar C;Grossmann P;Bussink J;Lambin P;Aerts HJWL
通讯作者：
Aerts HJWL
影响因子：
4.6
作者：
Khan, Adnan Mujahid;Rajpoot, Nasir;Magee, Derek
通讯作者：
Magee, Derek
DOI：
10.1093/bioinformatics/btp191
发表时间：
2009-06-15
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Abeel T;Van de Peer Y;Saeys Y
通讯作者：
Saeys Y
DOI：
10.1109/tsmc.1973.4309314
发表时间：
1973-01-01
期刊：
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS
影响因子：
--
作者：
HARALICK, RM;SHANMUGAM, K;DINSTEIN, I
通讯作者：
DINSTEIN, I