# 影像组学学习笔记(24)-文献导读:了解88种降维、分类器组合

literature0.JPG

##### 1. feature extraction

(1) First-order statistics of hematoma intensity (n = 18),
(2) shape (n = 16),
(3) texture (n = 22, derived from GLCM),
(4) texture (n = 16, derived from GLRLM),
(5) wavelet-based features (n = 448),
(6) Laplacian of Gaussian-filtered image features (n = 56).

##### 2. feature selection
###### 2.1 降维（11种过滤式特征筛选）:

`gini index (GINI)`, `relief (RELF)`, `information gain (IFGN)`, `gain ratio (GNRO)`, `Euclidean distance (EUDT)`, `F-ANOVA (FAOV)`, `t test-score (TSCR)`, `Wilcoxon rank sum (WLCR)`, and `fisher score (FSCR)`

`mutual information (MUIF)` and `MRMR`

###### 2.2 实现方法：

FS methods including GINI, RELF, IFGN, GNRO, and EUDT were performed by R software package “CORElearn” by the “attrEval” function.
FAOV and MUIF were conducted using the feature_selection module in sklearn (f_classif and mutual_info_classif), MRMR by the “pymrmr” package in Python.

We selected features according to rankings in their own group instead of rankings among all features since this enabled a systematic description of different aspects of the hematomas and avoided selecting features from a certain feature group.

##### 3. machine learning and evaluation of the model

Eight supervised machine learning algorithms: `neural network (NN)`, `decision tree (Decision Tree)`, `Adaboost classifier (AD)`, `naïve Bayes (NB)`, `random forest (RF)`, `logistic regression (LG)`, `support vector machines (SVM)`, and `k nearest neighbors (KNN)`. ( through `sklearn` package in Python)

RSD = (sdAUC/meanAUC) *100
The lower the RSD value, the more stable the predicting model.

##### 4. 结果
1. Boxplot of ICC of features extracted from 6 feature groups

5-Figure2-1.png
2. Heatmaps illustrating the predictive performance (AUC) of different combinations of feature selection methods (rows) and classification algorithms (columns).
(a) Cross-validated AUC values of 88 models on the train and validation datasets.
(b) RSD values of 88 models on the train and validation datasets.
330_2018_5747_Fig3_HTML.png
1. The model of RELF_Ada showed a best performance.
(a) Illustration of the threefold cross-validated ROC curve of model RELF_Ada.
(b) ROC curve of RELF_Ada on the test dataset.
(c) Confusion matrix with normalization of RELF_Ada

6-Figure4-1.png
2. Comparison of prediction performance between the model and radiologists.

6-Table2-1.png

### 推荐阅读更多精彩内容

• 久违的晴天，家长会。 家长大会开好到教室时，离放学已经没多少时间了。班主任说已经安排了三个家长分享经验。 放学铃声...
飘雪儿5阅读 5,004评论 16 21
• 创业是很多人的梦想，多少人为了理想和不甘选择了创业来实现自我价值，我就是其中一个。 创业后，我由女人变成了超人，什...
亦宝宝阅读 821评论 1 0
• 今天感恩节哎，感谢一直在我身边的亲朋好友。感恩相遇！感恩不离不弃。 中午开了第一次的党会，身份的转变要...
迷月闪星情阅读 7,624评论 1 9
• 哈里·基恩想和新教练何塞·穆里尼奥建立一种“牢固的关系”，这将有助于托特纳姆更上一层楼。 凯恩在4-2战胜奥林匹亚...
疯狂SPORTS阅读 6,324评论 0 5
• 可爱进取，孤独成精。努力飞翔，天堂翱翔。战争美好，孤独进取。胆大飞翔，成就辉煌。努力进取，遥望，和谐家园。可爱游走...
赵原野阅读 1,204评论 1 1