A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

Al-Ameen, Zohair; Sulong, Ghazali

doi:10.1002/sca.21187

Cited by 27 publications

(14 citation statements)

References 37 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This comparison excludes any insufficient and small, segmented brain tissue that has an area smaller than the fixed threshold. Due to the low contrast of brain CT slices, multiple image contrast enhancement techniques have been proposed, particularly for medical images [31], [32], [33], [34]. These techniques are used to boost the interior details within brain tissues for visibility, classification, and ultimately interpretation.…”

Section: Proposed Methodsmentioning

confidence: 99%

Deep Learning-enabled Detection of Acute Ischemic Stroke using Brain Computed Tomography Images

Babutain¹,

Hussain²,

Aboalsamh³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Stroke is the second leading cause of death globally. Computed Tomography plays a significant role in the initial diagnosis of suspected stroke patients. Currently, stroke is subjectively interpreted on CT scans by domain experts, and significant inter-and intra-observer variation has been documented. Several methods have been proposed to detect ischemic brain stroke automatically on CT scans using machine learning and deep learning, but they are not robust and their performance is not ready for clinical practice. We propose a fully automatic method for acute ischemic stroke detection on brain CT scans. The system's first component is a brain slice classification module that eliminates the CT scan's upper and lower slices, which do not usually include brain tissue. In turn, a brain tissue segmentation module segments brain tissue from CT slices, followed by tissue contrast enhancement using the Extreme-Level Eliminating Histogram Equalization technique. Finally, the processed brain tissue is classified as either normal or ischemic stroke using a classification module, to determine whether the patient is suffering from an ischemic stroke. We leveraged the use of the pre-trained ResNet50 model for slice classification and tissue segmentation, while we propose an efficient lightweight multi-scale CNN model (5S-CNN), which outperformed state-of-the-art models for brain tissue classification. Evaluation included the use of more than 130 patient brain CT scans curated from King Fahad Medical City (KFMC). The proposed method, using 5-fold cross-validation to validate generalization and susceptibility to overfitting, achieved accuracies of 99.21% in brain slice classification, 99.70% in brain tissue segmentation, 87.20% in patient-wise brain tissue classification, and 90.51% in slice-wise brain tissue classification. The system can assist both expert and non-expert radiologists in the early identification of ischemic stroke on brain CT scans.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Deep Learning-enabled Detection of Acute Ischemic Stroke using Brain Computed Tomography Images

Babutain¹,

Hussain²,

Aboalsamh³

et al. 2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…We introduce a scale map as a competent representation to explicitly model derivative-level confidence and propose new functions and a numerical solver to effectively infer it following new structural observations. The novelties of the proposed algorithm consist of tuning the standard single-scale Retinex, [7] adding a normalizedameliorated Sigmoid function and adapting some parameters to improve its enhancement ability. The proposed algorithm is tested with synthetically and naturally degraded low-contrast CT images, and its performance is also verified with contemporary enhancement techniques using two prevalent quality evaluation metrics-SSIM and UIQI.…”

Section: Related Workmentioning

confidence: 99%

Two-Stage Contrast Enhancement Method for Liver Tumor Segmentation

Journal¹

2022

IJSREM

View full text Add to dashboard Cite

Tumor segmentation in Computed Tomography (CT) images is a crucial step in image-guided surgery. However, low-contrast CT images impede the performance of subsequent segmentation tasks. Contrast enhancement is then used as a preprocessing step to highlight the relevant structures, thus facilitating not only medical diagnosis but also image segmentation with higher accuracy. The proposed method is based on two concepts, namely adaptive gamma correction using DWT-SVD and OPTimized Guided Contrast Enhancement (OPTGCE). In the proposed DWT-SVD scheme, the technique decomposes the input medical image into four frequency sub-bands by using DWT and then estimates the singular value matrix of the LL sub-band image. An enhanced LL component is generated using an adequate correction factor and inverse SVD. The proposed OPTimized Guided Contrast Enhancement (OPTGCE) scheme exploits both contextual information from the guidance image and structural information from the input image. Tumor segmentation algorithm is applied on the enhanced images to analyze the performance of the proposed method in facilitating tumor segmentation. The qualitative and quantitative analysis using metrics including entropy, MCCEE, and MIGLCM shows the superiority of the proposed method in comparison with the existing methods that do not include guidance mechanism Keywords—: 2D-DWT, Gamma Correction, SSIM, Gradient.

show abstract

“…An improved version of the single-scale Retinex algorithm is developed in order to enhance the low contrast of CT medical images [12]. This version incorporated a scheme for tuning the standard single-scale Retinex in order to improve its enhancement ability.…”

Section: Related Workmentioning

confidence: 99%

A comprehensive study of a similarity criterion in cardiac computerized tomography images enhancement

Valero¹,

Vera²,

Maldonado³

et al. 2020

Rev.Fac.Ing.Univ.Antioquia

View full text Add to dashboard Cite

This research focuses on the study of a particular filter based on a similarity criterion that has been applied to improve the information contained in images acquired using different cardiac imaging modalities. The primary attention of this study is to examine which component of the similarity criterion generates more relevant information useful to increase the medical image quality. In this sense, four case studies are established, first a complete formulation of the similarity criterion is considered, and then three additional cases, representing each component of the criterion; such cases are referred to as full, main, residual1, and residual2, respectively. A score function is used for quantifying and then assessing the impact of each component of the similarity criterion. Such measure is a relation between some full–reference and blind–reference image enhancement measures. A computer generated phantom and a representative clinical dataset (1270 three–dimensional images from 126 patients) are used in a thorough evaluation of the similarity criterion. In general terms of performance of the image enhancement technique, the results of the study reveal that the component residual1 outperforms than the other two components of similarity criterion or its complete formulation.

show abstract

A new algorithm for improving the low contrast of computed tomography images using tuned brightness controlled single-scale Retinex

Cited by 27 publications

References 37 publications

Deep Learning-enabled Detection of Acute Ischemic Stroke using Brain Computed Tomography Images

Deep Learning-enabled Detection of Acute Ischemic Stroke using Brain Computed Tomography Images

Two-Stage Contrast Enhancement Method for Liver Tumor Segmentation

A comprehensive study of a similarity criterion in cardiac computerized tomography images enhancement

Contact Info

Product

Resources

About