Effect of image sharpening on radiographic image quality

Clark, Jefferson L.; Wadhwani, Chandur; Abramovitch, Kenneth; Rice, Dwight; Kattadiyil, Mathew T.

doi:10.1016/j.prosdent.2018.03.034

Cited by 39 publications

(17 citation statements)

References 18 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is important to emphasize that this study tested existing sharpening levels without the possibility of fine-tuning. Most of the current dicom viewers have built-in capabilities to apply and modify filters without the possibility of fine-tuning of the basic characteristics of the filter [ 3 ]. In our study, special importance was given to clinical use and not just to theoretical testing of automatic detection capability.…”

Section: Discussionmentioning

confidence: 99%

“…Certain psychophysical experiments show that edge-enhanced images, including the field of radiology, are often more pleasing to the human visual system [ 2 ]. However, the application of this modification algorithm leads to several artifacts [ 3 ]. The presence of artifacts in the radiological images can lead to misdiagnosis and, consequently, to improper treatment [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic detection of image sharpening in maxillofacial radiology

2021

View full text Add to dashboard Cite

Background Improvement of image quality in radiology, including the maxillofacial region, is important for diagnosis by enhancing the visual perception of the original image. One of the most used modification methods is sharpening, in which simultaneously with the improvement, due to edge enhancement, several artifacts appear. These might lead to misdiagnosis and, as a consequence, to improper treatment. The purpose of this study was to prove the feasibility and effectiveness of automatic sharpening detection based on neural networks. Methods The in-house created dataset contained 4290 X-ray slices from different datasets of cone beam computed tomography images were taken on 2 different devices: Ortophos 3D SL (Sirona Dental Systems GmbH, Bensheim, Germany) and Planmeca ProMax 3D (Planmeca, Helsinki, Finland). The selected slices were modified using the sharpening filter available in the software RadiAnt Dicom Viewer software (Medixant, Poland), version 5.5. The neural network known as "ResNet-50" was used, which has been previously trained on the ImageNet dataset. The input images and their corresponding sharpening maps were used to train the network. For the implementation, Keras with Tensorflow backend was used. The model was trained using NVIDIA GeForce GTX 1080 Ti GPU. Receiver Operating Characteristic (ROC) analysis was performed to calculate the detection accuracy using MedCalc Statistical Software version 14.8.1 (MedCalc Software Ltd, Ostend, Belgium). The study was approved by the Ethical Committee. Results For the test, 1200 different images with the filter and without modification were used. An analysis of the detection of three different levels of sharpening (1, 2, 3) showed sensitivity of 53%, 93.33%, 93% and specificity of 72.33%, 84%, 85.33%, respectively with an accuracy of 62.17%, 88.67% and 89% (p < 0.0001). The ROC analysis in all tests showed an Area Under Curve (AUC) different from 0.5 (null hypothesis). Conclusions This study showed a high performance in automatic sharpening detection of radiological images based on neural network technology. Further investigation of these capabilities, including their application to different types of radiological images, will significantly improve the level of diagnosis and appropriate treatment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic detection of image sharpening in maxillofacial radiology

2021

View full text Add to dashboard Cite

show abstract

“…Image optimization methods improve the quality of the image, but significantly increase the number of artifacts that negatively affect the diagnosis [23].…”

Section: Discussionmentioning

confidence: 99%

Contributions to the study of common artifacts and errors in conventional and three-dimensional radio-imaging used in the evaluation of odontal, endodontic and periodontal pathology.

Kulcsar

Stoica

Monea

et al. 2020

Acta Stomatologica Marisiensis Journal

View full text Add to dashboard Cite

Introduction: X-ray radio imaging is commonly used because most diseases in the oral area can only be diagnosed by using this method. Proper identification of elements on a radiological image may also be difficult due to errors that may occur before, during or after the X-ray. These errors are called artifacts.Aim of the study: The aim of our study is to distinguish the artifacts that can occur on two-dimensional and three-dimensional dental X-rays (intraoral or extraoral) from the actual pathology of the investigated area, by performing control X-rays.Material and Methods: In our study we viewed, assessed and compared a number of 80 retroalveolar X-rays, 45 orthopantomographs (OPG) and 35 Cone Beam Computer Tomography (CBCT). In case of artifacts or errors, X-rays were repeated within 5 days or a CBCT was performed. In the case of OPGs, another option was to perform retroalveolar X-rays to establish the final diagnosis.Results: From a total of 80 retroalveolar X-rays, in 13 cases (16.25%) we found artifacts. Of these, in only 4 cases (5%) diagnosis and treatment plan were changed following a clinical examination or a CBCT. In the case of OPGs, out of a total of 45 OPGs, 17 (37.7%) presented artifacts, but only in a percentage of 17.7% (8 cases) they affected the diagnosis. Of the 35 CBCTs, in 10 of them (28.57%) prosthetic works with a metal component or implants were present, with specific artifacts found, but their presence did not influence the diagnosis.Conclusion: It is necessary for doctors to know the anatomy of the oral region, the most fervent appearance of the components and the different types of artifacts that may occur. Control X-ray is a very commonly used possibility, but there are cases where radiation exposure needs to be minimized.

show abstract

“…Among the existing techniques, the unsharp mask filter has received significant attention from researchers in the past decade due to its simplicity in processing various types of images. Still, it is known that this filter can cause artifacts and reduce the true value of different images [28]. Among such artifacts, the overshoot effect is often introduced to the processed image [16,30].…”

Section: Introductionmentioning

confidence: 99%

Improving the Sharpness of Digital Image Using an Amended Unsharp Mask Filter

Al-Ameen¹,

Muttar²,

Al-Badrani³

2019

IJIGSP

View full text Add to dashboard Cite

Many of the existing imaging systems produce images with blurry appearance due to various existing limitations. Thus, a proper sharpening technique is usually used to increase the acutance of the obtained images. The unsharp mask filter is a well-known sharpening technique that is used to recover acceptable quality results from their blurry counterparts. However, this filter often introduces an overshoot effect, which is an undesirable effect that makes the recovered edges appear with visible white shades around them. In this article, an amended unsharp mask filter is developed to sharpen different digital images without introducing the overshoot effect. In the developed filter, the image is smoothed by using the traditional bilateral filter and then blurred using a modified Butterworth filter instead of blurring it with a Gaussian low-pass filter only as in the traditional unsharp mask filter. Using this approach allowed to eliminate the overshoot effect and to recover better quality results. The proposed filter is assessed by using two modern image quality assessment metrics, real and synthetic-blurred images, and is compared with three renowned image sharpening techniques. Various experiments and comparisons showed that the proposed filter produced promising results with both real and synthetic-blurred images.

show abstract

Effect of image sharpening on radiographic image quality

Abstract: Image sharpening improves visual image quality but significantly increases overshoot artifacts that adversely affect radiographic diagnosis. Data from this study indicate that image sharpening causes artifacts that could negatively affect accurate diagnosis.

Cited by 39 publications

References 18 publications

Automatic detection of image sharpening in maxillofacial radiology

Automatic detection of image sharpening in maxillofacial radiology

Contributions to the study of common artifacts and errors in conventional and three-dimensional radio-imaging used in the evaluation of odontal, endodontic and periodontal pathology.

Improving the Sharpness of Digital Image Using an Amended Unsharp Mask Filter

Contact Info

Product

Resources

About