Impact of Window Setting Optimization on Accuracy of Computed Tomography and Computed Tomography Angiography Source Image-based Alberta Stroke Program Early Computed Tomography Score

doi:10.1016/j.jstrokecerebrovasdis.2012.05.012

Journal of Stroke and Cerebrovascular Diseases

Volume 23, Issue 1, January 2014, Pages 12-16

https://doi.org/10.1016/j.jstrokecerebrovasdis.2012.05.012 Get rights and content

The use of narrower window width settings on computed tomography (CT) improves sensitivity for detection of early ischemic changes in acute ischemic stroke. This study analyzed the effect of optimization of window settings on the accuracy of Alberta Stroke Program Early Computed Tomography Score (ASPECTS) performed on noncontrast CT (NCCT) and CT angiography source images (CTA-SI). ASPECTS was calculated on NCCT and CTA-SI with standard and optimized window width/center settings in a consecutive series of patients with acute ishcemic stroke. The difference between CT-based ASPECTS and ASPECTS performed on follow-up magnetic resonance imaging (MRI) were calculated to determine the disparity between initial estimates of the extent of ischemia on CT and follow-up lesion imaging by MRI. Forty-four patients were included into the study. The mean difference with respect to follow-up MRI-ASPECTS was 4.1 ± 2.2 for standard NCCT-ASPECTS, 3.7 ± 2.3 for optimized NCCT-ASPECTS, 3.0 ± 2.2 for standard CTA-SI-ASPECTS, and 2.7 ± 2.1 for optimized CTA-SI-ASPECTS. The improvement introduced by the optimization of window settings and use of CTA-SI was statistically significant (P < .01). Our data indicate that the accuracy of ASPECTS is improved with optimized window display settings. This improvement is irrespective of experience or specialty of the rater performing the assessment.

Section snippets

Methods

We retrospectively analyzed a consecutive series of ischemic stroke patients who received intravenous (IV) or intra-arterial thrombolysis over a 4-year period in our institution. All patients presenting with symptoms consistent with acute ischemic stroke routinely undergo NCCT and CTA in our center. The present study was restricted to patients who sustained a stroke within the middle cerebral artery territory and underwent magnetic resonance imaging (MRI) within 14 days after receiving

Results

A total of 44 patients met the inclusion criteria. Table 1 summarizes the clinical characteristics of the study cohort. The mean age of the study population was 62 ± 13 years. Thirty-two patients (73%) were treated with IV thrombolysis, 5 (11%) with intra-arterial thrombolysis, and 7 (16%) with combined IV and intra-arterial thrombolysis. The mean time from symptom onset to CT was 81 ± 33 minutes, and that to CTA was 90 ± 38 minutes. MRI was performed after a median delay of 1.2 days (IQR,

Discussion

The presence and extent of EIC on admission CT provide important information on the volume of ischemic territory, potential for hemorrhagic complications after thrombolysis, and long-term functional outcome.5, 6, 7 ASPECTS performed on NCCT is a reliable and valid grading system for assessing the extent of the ischemic injury.¹ Recent publications have shown that accuracy of ASPECTS can be improved by application of the grading system to CTA-SI.2, 3, 4 Our study, not only confirms this

References (14)

P.A. Barber et al.
Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke
Lancet
(2000)
R.I. Aviv et al.
Early stroke detection and extent: Impact of experience and the role of computed tomography angiography source images
Clin Radiol
(2007)
S.B. Coutts et al.
ASPECTS on CTA source images versus unenhanced CT: Added value in predicting final infarct extent and clinical outcome
Stroke
(2004)
E.C. Camargo et al.
Acute brain infarct: Detection and delineation with CT angiographic source images versus nonenhanced CT scans
Radiology
(2007)
R. von Kummer et al.
Acute stroke: Usefulness of early CT findings before thrombolytic therapy
Radiology
(1997)
V. Larrue et al.
Risk factors for severe hemorrhagic transformation in ischemic stroke patients treated with recombinant tissue plasminogen activator: A secondary analysis of the European-Australasian Acute Stroke Study (ECASS II)
Stroke
(2001)
A.M. Demchuk et al.
Importance of early ischemic computed tomography changes using ASPECTS in NINDS rtPA Stroke Study
Stroke
(2005)

There are more references available in the full text version of this article.

Cited by (14)

A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification
2022, IBRO Neuroscience Reports
Citation Excerpt :
Secondly, the window setting optimization (WSO) module, which has been tried in other fields of CT images, such as in identifying acute ischemic stroke and abdominal angiography, is utilized. Such implementation would be hypothesized to enhance the abnormal tumor tissues on MRI images (Arsava et al., 2014; Doerner et al., 2018). The final technique mentioned is data augmentation, a typical approach in deep learning networks that would help generate more data, particularly affine transformation (Nalepa et al., 2019).
Glioma grading is critical in treatment planning and prognosis. This study aims to address this issue through MRI-based classification to develop an accurate model for glioma diagnosis. Here, we employed a deep learning pipeline with three essential steps: (1) MRI images were segmented using preprocessing approaches and UNet architecture, (2) brain tumor regions were extracted using segmentation, then (3) high-grade gliomas and low-grade gliomas were classified using the VGG and GoogleNet implementations. Among the additional preprocessing techniques used in conjunction with the segmentation task, the combination of data augmentation and Window Setting Optimization was found to be the most effective tool, resulting in the Dice coefficient of 0.82, 0.91, and 0.72 for enhancing tumor, whole tumor, and tumor core, respectively. While most of the proposed models achieve comparable accuracies of about 93 % on the testing dataset, the pipeline of VGG combined with UNet segmentation obtains the highest accuracy of 97.44 %. In conclusion, the presented architecture illustrates a realistic model for detecting gliomas; moreover, it emphasizes the significance of data augmentation and segmentation in improving model performance.
Evaluation of frequency-selective non-linear blending technique on brain CT in postoperative children with Moyamoya disease
2021, Journal of Neuroradiology
Citation Excerpt :
Since the range of the HU spectrum of the brain is very small, it is important to maximize the contrast of brain parenchyma for optimal diagnosis. There have been various attempts to achieve improvements in imaging contrast, such as using low kVp or generating low keV virtual monoenergetic images using dual-energy CT techniques [10,13–19]. Using a lower tube voltage is advantageous as at lower kVp GM attenuation is higher than WM attenuation, thus improving GM-WM differentiation [13,16–18,20].
To evaluate whether a frequency-selective non-linear blending (BC) technique can improve tissue contrast and infarct detection on non-enhanced brain CT (NECT) in postoperative Moyamoya (MMD) patients.
From January 2010 to December 2017, 33 children (13 boys and 20 girls; mean age 9.1 ± 3.4 years) with MMD postoperatively underwent NECT followed by diffusion MRI. We compared the contrast-to-noise ratio (CNR) between gray matter (GM) and white matter (WM) in NECT and BC images and the CNR between the infarct lesion and adjacent normal-appearing brain in NECT and BC images using a paired t-test. We assessed image noise, GM-WM differentiation, artifacts, and overall quality using a Wilcoxon signed rank test. A McNemar two-tailed test was conducted to compare the diagnostic accuracy of infarct detection.
The CNR between GM and WM and the CNR of the infarct was better in BC images than in NECT images (3.9 ± 1.0 vs. 1.8 ± 0.6, P < 0.001 and 3.6 ± 0.3 vs. 1.9 ± 0.2, P < 0.001), with no difference in overall image quality observed. The sensitivity and specificity of infarct detection were 55.0% and 76.9% using NECT, and 70.0% and 69.2% using BC technique. The diagnostic accuracy of NECT and BC technique was 63.6% (21/33) and 69.7% (23/33), respectively.
This study showed that the BC technique improved CNR and maintained image quality. This technique may also be used to identify ischemic brain changes in postoperative MMD patients by improving the CNR of the infarct lesion.
CT window trainable neural network for improving intracranial hemorrhage detection by combining multiple settings
2020, Artificial Intelligence in Medicine
Citation Excerpt :
Using a stroke window (40/40 [WW/WL]) settings, subtle abnormalities that were not readily detected on the default brain window settings (100/40 or 100/50) have been confirmed on MRI or follow-up CT [6]. The approaches where standard window settings are optimized [7] and variable window settings are used [8] have been introduced to improve acute stroke detection; both of these approaches require manual intervention. Radiologists need to manually examine each radiographic image carefully by adjusting the settings in order to detect lesions.
Window settings to rescale and contrast stretch raw data from radiographic images such as Computed Tomography (CT), X-ray and Magnetic Resonance images is a crucial step as data pre-processing to examine abnormalities and diagnose diseases. We propose a distant-supervised method for determining automatically the best window settings by attaching a window estimator module (WEM) to a deep convolutional neural network (DCNN)-based lesion classifier and training them in conjunction. Aside from predicting a flexible window setting for each raw image, we statistically identify the top four window settings by calculating the mean and standard deviations for the entire dataset. Images are scaled on each of the top settings estimated by WEM and following lesion classifiers are subsequently trained. We study the effects of only using the flexible window, the single fixed window as either a known default window used by radiologists or an estimated mean value, and two different approaches to combine results from the top window settings to improve the detection of intracranial hemorrhage (ICH) from brain CT images. Experimental results showed that using the top four window settings identified from the window estimator module and combining the results had the best performance.
Region-specific interobserver agreement of the Alberta Stroke Program Early Computed Tomography Score: A meta-analysis
2024, Journal of Neuroimaging
CT perfusion based ASPECTS improves the diagnostic performance of early ischemic changes in large vessel occlusion
2021, BMC Medical Imaging
AGFA PACS software supported CT, MRI and PET windows impact on object appearances and size: Phantom study
2020, 2020 Advances in Science and Engineering Technology International Conferences, ASET 2020

View all citing articles on Scopus

: E.M.A. and J.T.S. share senior authorship.

View full text

Original ArticleImpact of Window Setting Optimization on Accuracy of Computed Tomography and Computed Tomography Angiography Source Image-based Alberta Stroke Program Early Computed Tomography Score

Section snippets

Methods

Results

Discussion

Lancet

Clin Radiol

ASPECTS on CTA source images versus unenhanced CT: Added value in predicting final infarct extent and clinical outcome

Stroke

Acute brain infarct: Detection and delineation with CT angiographic source images versus nonenhanced CT scans

Radiology

Acute stroke: Usefulness of early CT findings before thrombolytic therapy

Radiology

Risk factors for severe hemorrhagic transformation in ischemic stroke patients treated with recombinant tissue plasminogen activator: A secondary analysis of the European-Australasian Acute Stroke Study (ECASS II)

Stroke

Importance of early ischemic computed tomography changes using ASPECTS in NINDS rtPA Stroke Study

Stroke

Original Article
Impact of Window Setting Optimization on Accuracy of Computed Tomography and Computed Tomography Angiography Source Image-based Alberta Stroke Program Early Computed Tomography Score