Evaluation of Metamorphic Testing for Edge Detection in MRI Brain Diagnostics

Abstract

Magnetic resonance imaging (MRI) is an information-rich research tool used in diagnostics using image processing applications (IPAs), and the results are utilized in machine learning. Therefore, testing of IPAs for credible results is vital. A deficient IPA would cause the related taxonomies of the machine learning to be defective as well and diagnosis will not be perfect. Accurate disease detection by IPA, without surgical intervention, leads to improved quality of treatment. Current challenges for testing of IPA include an absence of a test oracle. One way to alleviate the test oracle problem is metamorphic testing which identifies the specific properties called metamorphic relations of the system under test. Previously metamorphic testing approaches have been applied and evaluated on IPAs, but there is no previous work on evaluation of metamorphic testing on MRI images. In this work, we have evaluated effectiveness of metamorphic testing on edge detection of MRI images. The aim of this study is to determine which metamorphic relations are more effective for metamorphic testing of edge detection in MRI images such as T1, T2 and flair images. Our results show that the fault detection rate of MR4 is highest and MR2 is the lowest among all type of MRI images at the threshold of 0.95.

Measuring Effectiveness of Metamorphic Relations for Image Processing Using Mutation Testing

“…We have used the MRs of edge detection proposed by Sim et al [12]. The complete details of these MRs are given in [12,15]. The MRs are shown in Table 2.…”

“…In equivalence class testing, we have considered the attributes of images and grouped them into five distinct classes such as horizontal dimension, vertical dimension, resolution, bit depth, and image type. The details of the formation of source test cases are given in [15]. We have used the same (95) test cases for our experiments.…”

“…We have selected 95 source test cases through black box testing technique (strong equivalence class testing) and coverage criteria (statement coverage and branch coverage); a criterion proposed in our previous paper [15].…”

“…After the selection and identification of MRs, we generated the source test cases through a criterion proposed by Jafari et al [15]. In the paper, we (the authors) have discussed in detail how source test cases are generated using the black box testing technique (equivalence class testing) and the white box testing technique (coverage criterion).…”

Dual Task Semi-supervised Pancreatic Segmentation Based on Prior Information and Multiple Regularization

“…Traditional image segmentation is a method based on pixel color, brightness and other features, by dividing the image into different areas to achieve image segmentation. Common algorithms used in this method include threshold segmentation [2,3], edge detection [4,5], region growth [6,7], etc. Traditional image segmentation is sensitive to noise, and is not effective for complex images or images with multiple objects.…”