FeAture Explorer (FAE): A tool for developing and comparing radiomics models

• Published in: PloS one Vol. 15; no. 8; p. e0237587
• Main Authors: Song, Yang, Zhang, Jing, Zhang, Yu-dong, Hou, Ying, Yan, Xu, Wang, Yida, Zhou, Minxiong, Yao, Ye-feng, Yang, Guang
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 17.08.2020; Public Library of Science (PLoS)
• Subjects: Algorithms; Classifiers; Computer and Information Sciences; Datasets; Diagnostic imaging; Discriminant analysis; Engineering and Technology; Equipment and supplies; Evaluation; Feature extraction; Feature selection; Graphical user interface; Laboratories; Learning algorithms; Machine learning; Medical imaging; Medical radiography; Medical research; Medicine and Health Sciences; Model testing; Open source software; People and Places; Physical Sciences; Pipelines; Prostate cancer; Radiomics; Research and Analysis Methods; Researchers; Science Policy; Selectors; Source code; Statistical analysis; Technology application; Variance analysis; Wavelet transforms; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0237587

In radiomics studies, researchers usually need to develop a supervised machine learning model to map image features onto the clinical conclusion. A classical machine learning pipeline consists of several steps, including normalization, feature selection, and classification. It is often tedious to find an optimal pipeline with appropriate combinations. We designed an open-source software package named FeAture Explorer (FAE). It was programmed with Python and used NumPy, pandas, and scikit-learning modules. FAE can be used to extract image features, preprocess the feature matrix, develop different models automatically, and evaluate them with common clinical statistics. FAE features a user-friendly graphical user interface that can be used by radiologists and researchers to build many different pipelines, and to compare their results visually. To prove the effectiveness of FAE, we developed a candidate model to classify the clinical-significant prostate cancer (CS PCa) and non-CS PCa using the PROSTATEx dataset. We used FAE to try out different combinations of feature selectors and classifiers, compare the area under the receiver operating characteristic curve of different models on the validation dataset, and evaluate the model using independent test data. The final model with the analysis of variance as the feature selector and linear discriminate analysis as the classifier was selected and evaluated conveniently by FAE. The area under the receiver operating characteristic curve on the training, validation, and test dataset achieved results of 0.838, 0.814, and 0.824, respectively. FAE allows researchers to build radiomics models and evaluate them using an independent testing dataset. It also provides easy model comparison and result visualization. We believe FAE can be a convenient tool for radiomics studies and other medical studies involving supervised machine learning.