Impact of Image Contrast Enhancement on Stability of Radiomics Feature Quantification on a 2D Mammogram Radiograph

Siti Fairuz Mat Radzi,Nurul Huda Osman,Mohd Amiruddin Abd Rahman,Entesar Zawam Dalah,M Iqbal Saripan,Noramaliza Mohd Noor,Muhammad Khalis Abdul Karim

doi:10.1109/access.2020.3008927

Siti Fairuz Mat Radzi, Nurul Huda Osman + Show 5 more

Open Access

https://doi.org/10.1109/access.2020.3008927

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 49	License type: CC BY 4.0

Affiliation: Universiti Putra Malaysia, Dubai Health Authority

Abstract

The present work aimed to evaluate the reproducibility of radiomics features derived from manual delineation and semiautomatic segmentation after enhancement using the Contrast Limited Adaptive Histogram Equalization (CLAHE) and Adaptive Histogram Equalization (AHE) techniques on a benign tumor of two-dimensional (2D) mammography images. Thirty mammogram images with known benign tumors were obtained from The Cancer Imaging Archive (TCIA) datasets and were randomly selected as subjects. The samples were enhanced for semiautomatic segmentation sets using the Active Contour Model in MATLAB 2019a before analysis by two independent observers. Meanwhile, the images without any enhancement were segmented manually. The samples were divided into three categories: (1) CLAHE images, (2) AHE images, and (3) manual segmented images. Radiomics features were extracted using algorithms provided by MATLAB 2019a software and were assessed with a reliable intra-class correlation coefficient (ICC) score. Radiomics features for the CLAHE group (ICC = 0.890 ± 0.554, p 0.05). Features in all three categories were more robust for the CLAHE compared to the AHE and manual groups. This study shows the existence in variation for the radiomics features extracted from tumor region that are segmented using various image enhancement techniques. Semiautomatic segmentation with image enhancement using CLAHE algorithm gave the best result and was a better alternative than manual delineation as the first two techniques yielded reproducible descriptors. This method should be applicable for predicting outcomes in patient with breast cancer.

Highlights

Breast cancer has been acknowledged as the most prevalent and common cause of death among Malaysian woman over the age of 40 [1]
The intra-class correlation coefficient (ICC) of Contrast Limited Adaptive Histogram Equalization (CLAHE) image data segmentation (ICC = 0.890 ± 0.554, p < 0.05) was higher when compared to features extracted from Adaptive Histogram Equalization (AHE) image data segmentation (ICC = 0.850 ± 0.933, p < 0.05) and manual delineation segmentation (ICC = 0.673 ± 0.807, p > 0.05)
36 = radiomic features showed higher ICC for image data-enhancement using CLAHE and 35 showed higher ICC values for image data-enhanced using AHE segmentation sets compared to the manual method

Summary

Introduction

Breast cancer has been acknowledged as the most prevalent and common cause of death among Malaysian woman over the age of 40 [1]. Several studies emphasize the need and urgency for early detection in reducing breast cancer morbidity and mortality [2]–[4]. As mammography, play an important role in non-invasively assessing breast tissues for detection, diagnostic, staging, and management purposes [2]. In an attempt to improve the mortality rate among the population, a mammography screening program was proven to be the most cost-effective program for providing useful details about the presence of abnormal breast tissues [2]. Studies have shown the potential of radiomics feature extraction in providing consistent and unbiased descriptions.

Objectives

Methods

Results

Conclusion