Classification of chest radiographs using novel anomalous saliency map and deep convolutional neural network

Md. Ali, Mohd. Adli and Abidin, Mohd Radhwan and Nik Muhamad Affendi, Nik Arsyad and Abdullah, Hafidzul and Rosman, Daaniyal Reesha and Badrud'din, Nu'man and Kemi, Faiz and Hayati, Farid (2021) Classification of chest radiographs using novel anomalous saliency map and deep convolutional neural network. IIUM Engineering Journal, 22 (2). pp. 234-248. ISSN 1511-758X E-ISSN 2289-7860

	PDF - Published Version Restricted to Registered users only Download (1MB) | Request a copy
	PDF (SCOPUS) - Supplemental Material Restricted to Registered users only Download (411kB) | Request a copy

Abstract

The rapid advancement in pattern recognition via the deep learning method has made it possible to develop an autonomous medical image classification system. This system has proven robust and accurate in classifying most pathological features found in a medical image, such as airspace opacity, mass, and broken bone. Conventionally, this system takes routine medical images with minimum pre-processing as the model's input; in this research, we investigate if saliency maps can be an alternative model input. Recent research has shown that saliency maps' application increases deep learning model performance in image classification, object localization, and segmentation. However, conventional bottom-up saliency map algorithms regularly failed to localize salient or pathological anomalies in medical images. This failure is because most medical images are homogenous, lacking color, and contrast variant. Therefore, we also introduce the Xenafas algorithm in this paper. The algorithm creates a new kind of anomalous saliency map called the Intensity Probability Mapping and Weighted Intensity Probability Mapping. We tested the proposed saliency maps on five deep learning models based on common convolutional neural network architecture. The result of this experiment showed that using the proposed saliency map over regular radiograph chest images increases the sensitivity of most models in identifying images with air space opacities. Using the Grad- CAM algorithm, we showed how the proposed saliency map shifted the model attention to the relevant region in chest radiograph images. While in the qualitative study, it was found that the proposed saliency map regularly highlights anomalous features, including foreign objects and cardiomegaly. However, it is inconsistent in highlighting masses and nodules.

Item Type:	Article (Journal)
Uncontrolled Keywords:	saliency mapping; chest radiograph; convolutional neural network
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Medicine Kulliyyah of Medicine > Department of Internal Medicine Kulliyyah of Medicine > Department of Radiology Kulliyyah of Science Kulliyyah of Science > Department of Physics
Depositing User:	Dr Mohd Adli MD Ali
Date Deposited:	22 Jul 2021 15:32
Last Modified:	15 Jul 2022 11:23
URI:	http://irep.iium.edu.my/id/eprint/90919

Actions (login required)

View Item