scholarly journals The impact of the variation of imaging parameters on the robustness of Computed Tomography radiomic features: A review

2021 ◽  
Vol 133 ◽  
pp. 104400
Author(s):  
Reza Reiazi ◽  
Engy Abbas ◽  
Petra Famiyeh ◽  
Aria Rezaie ◽  
Jennifer Y.Y. Kwan ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Imaging Parameters ◽  
The Impact

scholarly journals The impact of the variation of imaging factors on the robustness of Computed Tomography Radiomic Features: A review

2020 ◽  
Author(s):  
Reza Reiazi ◽  
Engy Abbas ◽  
Petra Famiyeh ◽  
Aria Rezaie ◽  
Jennifer Y. Y. Kwan ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Feature Extraction ◽  
Predictive Models ◽  
Scientific Community ◽  
Reconstruction Algorithm ◽  
Extraction Techniques ◽  
Intensity Histogram ◽  
Imaging Parameters ◽  
Conducting Research ◽  
The Impact

ABSTRACTThe field of radiomics is at the forefront of personalized medicine. However, there are concerns regarding the robustness of its features against multiple medical imaging parameters and the performance of the predictive models built upon them. Therefore, our review aims to identify image perturbation factors (IPF) that most influence the robustness of radiomic features in biomedical research. We also provide insights into the validity and discrepancy of different methodologies applied to investigate the robustness of radiomic features. We selected 527 papers based on the primary criterion that the papers had imaging parameters that affected the reproducibility of radiomic features extracted from computed tomography (CT) images. We compared the reported performance of these parameters along with IPF in the eligible studies. We then proceeded to divide our studies into three groups based on the type of their IPF: (i) scanner parameters, (ii) acquisition parameters and (iii) reconstruction parameters. Our review highlighted that the reconstruction algorithm was the most reproducible factor and shape along with intensity histogram (IH) were the most robust radiomic features against variation in imaging parameters. This review identified substantial inconsistencies related to the methodology and the reporting style of the reviewed studies such as type of study performed, the metrics used for robustness, the feature extraction techniques, the image perturbation factors, the reporting style and their outcome inclusion. Finally, we hope the IPFs and the methodology inconsistencies identified will aid the scientific community in conducting research in a way that is more reproducible and avoids the pitfalls of previous analyses.

scholarly journals Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Malte Seemann ◽  
Lennart Bargsten ◽  
Alexander Schlaefer
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Computed Tomography Angiography ◽  
Data Augmentation ◽  
Domain Adaptation ◽  
Synthetic Image ◽  
Wide Range ◽  
The Impact

AbstractDeep learning methods produce promising results when applied to a wide range of medical imaging tasks, including segmentation of artery lumen in computed tomography angiography (CTA) data. However, to perform sufficiently, neural networks have to be trained on large amounts of high quality annotated data. In the realm of medical imaging, annotations are not only quite scarce but also often not entirely reliable. To tackle both challenges, we developed a two-step approach for generating realistic synthetic CTA data for the purpose of data augmentation. In the first step moderately realistic images are generated in a purely numerical fashion. In the second step these images are improved by applying neural domain adaptation. We evaluated the impact of synthetic data on lumen segmentation via convolutional neural networks (CNNs) by comparing resulting performances. Improvements of up to 5% in terms of Dice coefficient and 20% for Hausdorff distance represent a proof of concept that the proposed augmentation procedure can be used to enhance deep learning-based segmentation for artery lumen in CTA images.

scholarly journals Impact of the COVID-19 pandemic on neuroimaging scan volumes at a teaching hospital

2021 ◽  
pp. 197140092098866
Author(s):  
Daniel Thomas Ginat ◽  
James Kenniff
Keyword(s):  
Magnetic Resonance Imaging ◽  
Computed Tomography ◽  
Magnetic Resonance ◽  
The United States ◽  
Radiology Department ◽  
Magnetic Resonance Imaging Scan ◽  
Resonance Imaging ◽  
Academic Medical Centre ◽  
Academic Medical ◽  
The Impact

Background The COVID-19 pandemic led to a widespread socioeconomic shutdown, including medical facilities in many parts of the world. The purpose of this study was to assess the impact on neuroimaging utilisation at an academic medical centre in the United States caused by this shutdown. Methods Exam volumes from 1 February 2020 to 11 August 2020 were calculated based on patient location, including outpatient, inpatient and emergency, as well as modality type, including computed tomography and magnetic resonance imaging. 13 March 2020 was designated as the beginning of the shutdown period for the radiology department and 1 May 2020 was designated as the reopening date. The scan volumes during the pre-shutdown, shutdown and post-shutdown periods were compared using t-tests. Results Overall, neuroimaging scan volumes declined significantly by 41% during the shutdown period and returned to 98% of the pre-shutdown period levels after the shutdown, with an estimated 3231 missed scans. Outpatient scan volumes were more greatly affected than inpatient scan volumes, while emergency scan volumes declined the least during the shutdown. In addition, the magnetic resonance imaging scan volumes declined to a greater degree than the computed tomography scan volumes during the shutdown. Conclusion The shutdown from the COVID-19 pandemic had a substantial but transient impact on neuroimaging utilisation overall, with variable magnitude depending on patient location and modality type.

The Impact of Chest Computed Tomography in a COVID-19 Reference Hospital - First Wave - Distrito Federal - Brazil

2022 ◽  
Author(s):  
Gleim Dias de Souza ◽  
Luciana Rodrigues Queiroz de Souza ◽  
Gabriela Gomes de Souza ◽  
Thales Queiroz Souza ◽  
Ulysses Rodrigues Castro ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Chest Computed Tomography ◽  
Reference Hospital ◽  
Distrito Federal ◽  
The Impact

scholarly journals Impact of immediate evaluation of touch imprint cytology from computed tomography guided core needle biopsies of mass lesions: Single institution experience

CytoJournal ◽  
2014 ◽  
Vol 11 ◽  
pp. 15 ◽  
Author(s):  
Mana Moghadamfalahi ◽  
Mirna Podoll ◽  
Amy B. Frey ◽  
Houda Alatassi
Keyword(s):  
Computed Tomography ◽  
Imprint Cytology ◽  
Ct Guided ◽  
Core Needle ◽  
Touch Imprint Cytology ◽  
Effective Manner ◽  
First Pass ◽  
Site Evaluation ◽  
The Impact ◽  
Number Of Passes

Background: Computed tomography (CT) guided core needle biopsy (CT-guided CNB) is a minimally invasive, safe and effective manner of tissue sampling in many organs. The aim of our study is to determine the impact of on-site evaluation of touch imprint cytology (TIC) to minimize the number of passes required to obtain adequate tissue for diagnosis. Design: A retrospective review of all CT-guided CNBs performed during 4 year period, where pathologists were present for on-site TIC evaluation. Each case was evaluated for the number of passes required before TIC was interpreted as adequate for diagnosis. Results: A total of 140 CT-guided CNBs were included in the study (liver, lung, kidney, sacral, paraspinal, omental, splenic and adrenal masses). Of the 140 cases, 109 were diagnosed as malignant, 28 as benign and three insufficient. In 106 cases (75.7%), the biopsies were determined adequate by TIC on the first pass, 19 cases (13%) on the second pass and 7 cases (5%) on the third pass. Only in 5 cases (3.6%), more than three passes were required before diagnostic material was obtained. Three cases (2.14%) were interpreted as inadequate both on TIC and on the final diagnosis. Of the biopsies deemed adequate on the first pass, 71% resulted in either termination of the procedure, or only one additional pass was obtained. In five cases, based on the TIC evaluation, a portion of the sample was sent for either flow cytometric analysis or cytogenetic studies. Conclusions: In the majority of cases, adequate material was obtained in the first pass of CT-guided CNB and once this was obtained, either no additional passes, or one additional pass was performed. This study demonstrates the utility of on-site evaluation in minimizing the number of passes required for obtaining adequate diagnostic material and for proper specimen triage for ancillary studies, which in turn decreases the risk to the patient and costs. However, tumor exhaustion in the tissue as a result of TIC is an important pitfall of the procedure, which occurred in 9 (8.2%) of our malignant cases.

scholarly journals The impact of pre-operative computed tomography scan in patients underwent septoplasty on the postoperative complications

2021 ◽  
Author(s):  
Abdulwahid S. AlQahtani ◽  
Ramzi M. Dagriri ◽  
Radeif E. Shamakhi ◽  
Ahmad M. Alrasheed ◽  
Ahmed A. Etwadi ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Postoperative Complications ◽  
Paranasal Sinus ◽  
Nasal Obstruction ◽  
Computed Tomography Scan ◽  
Gold Standard Method ◽  
External Nose ◽  
Preoperative Ct ◽  
The Impact ◽  
Tomography Scan

<p class="abstract"><strong>Background:</strong> Deviated nasal septum (DNS) is one of the most frequent causes of nasal obstruction in adults. An anterior rhinoscopy (AR), which is usually the first diagnostic procedure in the evaluation of obstructive nasal pathologies, is often inadequate in the assessment of the posterior nasal cavity and the gold standard method for the evaluation of paranasal anatomy and inflammatory paranasal sinus pathologies is paranasal sinus computed tomography (PNS CT). Aim was to validate the recommendation of pre-operative computed tomography scan in minimizing post-septoplasty complications.</p><p class="abstract"><strong>Methods:</strong> A retrospective record based study was conducted including all patients with clinically diagnosed DNS and undergone surgical intervention at Khamis Mushayet General Hospital. Data extracted included patients demographic data, and post-operative recorded complications and history of preoperative CT scan for evaluating and grading DNS.  </p><p class="abstract"><strong>Results:</strong> A total sample of 60 patients’ undergone septoplasty for DNS. Patients who undergone preoperative CT were 30. The remaining 30 patients didn’t undergone pre-operative CT for evaluation of DNS. The most diagnosed complication was nasal obstruction (28.3%) followed by external nose deformity (20%). Exact of 47% of patients had postoperative nasal obstruction didn’t undergone pre-operative CT. About 42% of those who had postoperative nasal deformity didn’t undergone CT while 33% of patient who had post-operative bleeding and septal perforation didn’t undergone CT.</p><p class="abstract"><strong>Conclusions:</strong> In conclusion, the study revealed that preoperative CT showed insignificant efficacy in relieving nasal obstruction or minimizing postoperative complications.</p>

Sign in / Sign up

Export Citation Format

Share Document