PyHIVE, a health-related image visualization and engineering system using Python

Ruochi Zhang,Xin Feng,Fengfeng Zhou,Weiwei Zheng,Ruixue Zhao,Xinyang Zhao,Di Wu

doi:10.1186/s12859-018-2477-7

Abstract

BackgroundImaging is one of the major biomedical technologies to investigate the status of a living object. But the biomedical image based data mining problem requires extensive knowledge across multiple disciplinaries, e.g. biology, mathematics and computer science, etc.ResultspyHIVE (a Health-related Image Visualization and Engineering system using Python) was implemented as an image processing system, providing five widely used image feature engineering algorithms. A standard binary classification pipeline was also provided to help researchers build data models immediately after the data is collected. pyHIVE may calculate five widely-used image feature engineering algorithms efficiently using multiple computing cores, and also featured the modules of Principal Component Analysis (PCA) based preprocessing and normalization.ConclusionsThe demonstrative example shows that the image features generated by pyHIVE achieved very good classification performances based on the gastrointestinal endoscopic images. This system pyHIVE and the demonstrative example are freely available and maintained at http://www.healthinformaticslab.org/supp/resources.php.

Highlights

Imaging is one of the major biomedical technologies to investigate the status of a living object
Dataset details We demonstrated how to use Python-based Health-related Image Visualization and Engineering system (pyHIVE) by a public dataset of gastrointestinal endoscopic images
In order to avoid the over-fitting problem, the Principal Component Analysis (PCA) module provided by pyHIVE was applied to the feature matrix

Summary

Introduction

Imaging is one of the major biomedical technologies to investigate the status of a living object. Besides OMIC data, imaging is another major source of biomedical information for the biomedical modeling [1]. Imaging has its inherent nature of non-invasively and instantly monitoring the health status inside the body [2], while the OMIC data is produced hours or longer later after the sample is collected. Imaging and OMIC data represent different modalities and resolution of a biological system [3]. Biomedical images have already been widely used in the diagnosis and prognosis modeling [4–6]. The image histogram of oriented gradients (HOG) feature was used for the predictions of lung cancers [7]. Other image features like the gray-level co-occurrence matrix (GLCM) were frequently utilized in predicting the tumor outcomes and other phenotypes [11].

Methods

Results

Discussion

Conclusion