Deep learning-based extended field of view computed tomography image reconstruction: influence of network design on image estimation outside the scan field of view

2022 ◽  
Author(s):  
Bhupinder Singh Khural ◽  
Matthias Baer-Beck ◽  
Eric Fournie ◽  
Karl Stierstorfer ◽  
Yixing Huang ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Absolute Error ◽  
Field Of View ◽  
Reconstruction Algorithms ◽  
Ct Scanner ◽  
Real Patient ◽  
Data Set ◽  
Order Reconstruction ◽  
The Impact

Abstract The problem of data truncation in Computed Tomography (CT) is caused by the missing data when the patient exceeds the Scan Field of View (SFOV) of a CT scanner. The reconstruction of a truncated scan produces severe truncation artifacts both inside and outside the SFOV. We have employed a deep learning-based approach to extend the field of view and suppress truncation artifacts. Thereby, our aim is to generate a good estimate of the real patient data and not to provide a perfect and diagnostic image even in regions beyond the SFOV of the CT scanner. This estimate could then be used as an input to higher order reconstruction algorithms [1]. To evaluate the influence of the network structure and layout on the results, three convolutional neural networks (CNNs), in particular a general CNN called ConvNet, an autoencoder, and the U-Net architecture have been investigated in this paper. Additionally, the impact of L1, L2, structural dissimilarity and perceptual loss functions on the neural network’s learning have been assessed and evaluated. The evaluation of data set comprising 12 truncated test patients demonstrated that the U-Net in combination with the structural dissimilarity loss showed the best performance in terms of image restoration in regions beyond the SFOV of the CT scanner. Moreover, this network produced the best mean absolute error, L1, L2, and structural dissimilarity evaluation measures on the test set compared to other applied networks. Therefore, it is possible to achieve truncation artifact removal using deep learning techniques.

scholarly journals Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yahya Albalawi ◽  
Jim Buckley ◽  
Nikola S. Nikolov
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Comprehensive Evaluation ◽  
Classification Problem ◽  
Data Sets ◽  
Word Embeddings ◽  
Data Set ◽  
Lower Accuracy ◽  
Health Related ◽  
The Impact

AbstractThis paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.

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.

Automatic Deep Learning-Based Consolidation/Collapse Classification in Lung Ultrasound Images for COVID-19 Induced Pneumonia

2022 ◽  
Author(s):  
Nabeel Durrani ◽  
Damjan Vukovic ◽  
Maria Antico ◽  
Jeroen van der Burgt ◽  
Ruud JG van van Sloun ◽  
...  
Keyword(s):  
Deep Learning ◽  
Class Imbalance ◽  
Ultrasound Images ◽  
Pleural Effusions ◽  
Data Set ◽  
Label Noise ◽  
Set Size ◽  
Video Frames ◽  
Two Factors ◽  
The Impact

<div>Our automated deep learning-based approach identifies consolidation/collapse in LUS images to aid in the diagnosis of late stages of COVID-19 induced pneumonia, where consolidation/collapse is one of the possible associated pathologies. A common challenge in training such models is that annotating each frame of an ultrasound video requires high labelling effort. This effort in practice becomes prohibitive for large ultrasound datasets. To understand the impact of various degrees of labelling precision, we compare labelling strategies to train fully supervised models (frame-based method, higher labelling effort) and inaccurately supervised models (video-based methods, lower labelling effort), both of which yield binary predictions for LUS videos on a frame-by-frame level. We moreover introduce a novel sampled quaternary method which randomly samples only 10% of the LUS video frames and subsequently assigns (ordinal) categorical labels to all frames in the video based on the fraction of positively annotated samples. This method outperformed the inaccurately supervised video-based method of our previous work on pleural effusions. More surprisingly, this method outperformed the supervised frame-based approach with respect to metrics such as precision-recall area under curve (PR-AUC) and F1 score that are suitable for the class imbalance scenario of our dataset despite being a form of inaccurate learning. This may be due to the combination of a significantly smaller data set size compared to our previous work and the higher complexity of consolidation/collapse compared to pleural effusion, two factors which contribute to label noise and overfitting; specifically, we argue that our video-based method is more robust with respect to label noise and mitigates overfitting in a manner similar to label smoothing. Using clinical expert feedback, separate criteria were developed to exclude data from the training and test sets respectively for our ten-fold cross validation results, which resulted in a PR-AUC score of 73% and an accuracy of 89%. While the efficacy of our classifier using the sampled quaternary method must be verified on a larger consolidation/collapse dataset, when considering the complexity of the pathology, our proposed classifier using the sampled quaternary video-based method is clinically comparable with trained experts and improves over the video-based method of our previous work on pleural effusions.</div>

scholarly journals Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study

10.2196/26151 ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. e26151
Author(s):  
Stanislav Nikolov ◽  
Sam Blackwell ◽  
Alexei Zverovitch ◽  
Ruheena Mendes ◽  
Michelle Livne ◽  
...  
Keyword(s):  
Computed Tomography ◽  
At Risk ◽  
Deep Learning ◽  
Clinical Practice ◽  
Head And Neck ◽  
Organs At Risk ◽  
Data Set ◽  
Computed Tomography Scans ◽  
Neck Anatomy ◽  
Organ At Risk

Background Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. Objective Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. Methods The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. Results We demonstrated the model’s clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model’s generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. Conclusions Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.

THE IMPACT OF HEAD POSITIONING ON THE IMAGE QUALITY OF MULTI-DETECTOR COMPUTED TOMOGRAPHY

2021 ◽  
pp. 2150050
Author(s):  
Yang-Ting Hsu ◽  
Jo-Chi Jao
Keyword(s):  
Computed Tomography ◽  
Image Quality ◽  
Control Group ◽  
Ct Scanner ◽  
Head Ct ◽  
Radiologic Technologists ◽  
Head Positioning ◽  
The Impact ◽  
Multi Detector Computed Tomography

Radiologic technologists face various types of patients during multi-detector computed tomography (CT) examinations. In emergency departments, it is common to have patients who cannot follow instructions for the examinations. The asymmetric axial view of the head CT might affect the correctness of the clinician’s diagnosis. This study aimed to assess the impact of head positioning on the image quality of head CT using two phantoms. All scans were performed on a 16-slice CT scanner. In the control group, the tilted angle of the phantoms was 0[Formula: see text], and no multiplanar reconstruction (MPR) was performed. In the experimental groups, the tilted angles of the phantoms were 5[Formula: see text], 10[Formula: see text] and 15[Formula: see text], respectively, and MPR was performed afterwards. The results showed that if the head was tilted during the head CT examinations, image asymmetry and artifacts appeared without MPR. After MPR, one phantom showed that there were significant differences and the other phantom showed no significant differences quantitatively in image symmetry and artifacts between experimental groups and the control group, while both phantoms showed no significant differences qualitatively in image symmetry and artifacts between experimental groups and the control group. Although MPR can correct the image asymmetry and artifacts caused by tilted head positioning to some extent, it consumes time. Therefore, technologists should position the head as exactly as possible when performing head CT examinations.

Radiography registration for mosaic tomography

2017 ◽  
Vol 24 (3) ◽  
pp. 686-694 ◽  
Author(s):  
R. F. C. Vescovi ◽  
M. B. Cardoso ◽  
E. X. Miqueles
Keyword(s):  
Computed Tomography ◽  
Phase Correlation ◽  
Field Of View ◽  
Experimental Setup ◽  
Reconstruction Algorithms ◽  
X Ray ◽  
Synchrotron Tomography ◽  
Correlation Image ◽  
X Ray Computed ◽  
Single Dataset

A hybrid method of stitching X-ray computed tomography (CT) datasets is proposed and the feasibility to apply the scheme in a synchrotron tomography beamline with micrometre resolution is shown. The proposed method enables the field of view of the system to be extended while spatial resolution and experimental setup remain unchanged. The approach relies on taking full tomographic datasets at different positions in a mosaic array and registering the frames using Fourier phase correlation and a residue-based correlation. To ensure correlation correctness, the limits for the shifts are determined from the experimental motor position readouts. The masked correlation image is then minimized to obtain the correct shift. The partial datasets are blended in the sinogram space to be compatible with common CT reconstructors. The feasibility to use the algorithm to blend the partial datasets in projection space is also shown, creating a new single dataset, and standard reconstruction algorithms are used to restore high-resolution slices even with a small number of projections.

A Robust Deep Learning Segmentation Method for Hematoma Volumetric Detection in Intracerebral Hemorrhage

Stroke ◽  
2021 ◽  
Author(s):  
Nannan Yu ◽  
He Yu ◽  
Haonan Li ◽  
Nannan Ma ◽  
Chunai Hu ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Image Segmentation ◽  
Deep Learning ◽  
Intracerebral Hemorrhage ◽  
Epidural Hematoma ◽  
Contour Method ◽  
Data Sets ◽  
Segmentation Method ◽  
Data Set ◽  
Testing Data

Background and Purpose: Hematoma volume (HV) is a significant diagnosis for determining the clinical stage and therapeutic approach for intracerebral hemorrhage (ICH). The aim of this study is to develop a robust deep learning segmentation method for the fast and accurate HV analysis using computed tomography. Methods: A novel dimension reduction UNet (DR-UNet) model was developed for computed tomography image segmentation and HV measurement. Two data sets, 512 ICH patients with 12 568 computed tomography slices in the retrospective data set and 50 ICH patients with 1257 slices in the prospective data set, were used for network training, validation, and internal and external testing. Moreover, 13 irregular hematoma cases, 11 subdural and epidural hematoma cases, and 50 different HV cases into 3 groups (<30, 30–60, and >60 mL) were selected to further evaluate the robustness of DR-UNet. The image segmentation performance of DR-UNet was compared with those of UNet, the fuzzy clustering method, and the active contour method. The HV measurement performance was compared using DR-UNet, UNet, and the Coniglobus formula method. Results: Using DR-UNet, the segmentation model achieved a performance similar to that of expert clinicians in 2 independent test data sets containing internal testing data (Dice of 0.861±0.139) and external testing data (Dice of 0.874±0.130). The HV measurement derived from DR-UNet was strongly correlated with that from manual segmentation (R 2 =0.9979; P <0.0001). In the irregularly shaped hematoma group and the subdural and epidural hematoma group, DR-UNet was more robust than UNet in both hematoma segmentation and HV measurement. There is no statistical significance in segmentation accuracy among 3 different HV groups. Conclusions: DR-UNet can segment hematomas from the computed tomography scans of ICH patients and quantify the HV with better accuracy and greater efficiency than the main existing methods and with similar performance to expert clinicians. Due to robust performance and stable segmentation on different ICHs, DR-UNet could facilitate the development of deep learning systems for a variety of clinical applications.

scholarly journals Influence of Different Arm Positions in the Localizer Radiograph(s) on Patient Dose during Exposure-Controlled CT Examinations of the Neck to Pelvis

Tomography ◽  
2021 ◽  
Vol 7 (3) ◽  
pp. 313-322
Author(s):  
Tony M. Svahn ◽  
Lovre Peric ◽  
Jennifer C. Ast
Keyword(s):  
Computed Tomography ◽  
Monte Carlo ◽  
Effective Dose ◽  
Patient Dose ◽  
Whole Body ◽  
Ct Scanner ◽  
Effective Doses ◽  
The Impact ◽  
Total Effective Dose

Our aim was to examine the impact of different arm positions during imaging of the localizer radiograph(s) on effective dose for exposure-controlled computed tomography (CT) (Siemens/Canon) scans of the neck to pelvis. An anthropomorphic whole-body phantom was scanned from the neck to pelvis with the arms positioned in three different ways during the acquisition of the localizer radiograph: (i) above the head, (ii) alongside the trunk, and (iii) along the trunk with the hands placed on the abdomen. In accordance with clinical routines, the arms were not included in the subsequent helical scans. Effective doses were computed to a standard-sized patient (male/female) using a dedicated system-specific Monte Carlo-based software. Effective doses for the Canon CT scanner for the different alternatives (male/female) were (a) 5.3/6.62 mSv, (b) 5.62/7.15 mSv and (c) 5.92/7.44 mSv. For the Siemens CT scanner, effective doses were (a) 4.47/5.59 mSv, (b) 5.4/6.69 mSv and (c) 5.7/6.99 mSv. Arms placed above the head during localizer radiograph imaging in the current CT procedures substantially reduced the total effective dose to the patient.

scholarly journals Three-dimensional deep learning with spatial erasing for unsupervised anomaly segmentation in brain MRI

2021 ◽  
Author(s):  
Marcel Bengs ◽  
Finn Behrendt ◽  
Julia Krüger ◽  
Roland Opfer ◽  
Alexander Schlaefer
Keyword(s):  
Deep Learning ◽  
Brain Mri ◽  
Magnetic Resonance Images ◽  
Spatial Context ◽  
Data Sets ◽  
Learning Methods ◽  
Data Set ◽  
Performance Improvements ◽  
Wide Range ◽  
The Impact

Abstract Purpose Brain Magnetic Resonance Images (MRIs) are essential for the diagnosis of neurological diseases. Recently, deep learning methods for unsupervised anomaly detection (UAD) have been proposed for the analysis of brain MRI. These methods rely on healthy brain MRIs and eliminate the requirement of pixel-wise annotated data compared to supervised deep learning. While a wide range of methods for UAD have been proposed, these methods are mostly 2D and only learn from MRI slices, disregarding that brain lesions are inherently 3D and the spatial context of MRI volumes remains unexploited. Methods We investigate whether using increased spatial context by using MRI volumes combined with spatial erasing leads to improved unsupervised anomaly segmentation performance compared to learning from slices. We evaluate and compare 2D variational autoencoder (VAE) to their 3D counterpart, propose 3D input erasing, and systemically study the impact of the data set size on the performance. Results Using two publicly available segmentation data sets for evaluation, 3D VAEs outperform their 2D counterpart, highlighting the advantage of volumetric context. Also, our 3D erasing methods allow for further performance improvements. Our best performing 3D VAE with input erasing leads to an average DICE score of 31.40% compared to 25.76% for the 2D VAE. Conclusions We propose 3D deep learning methods for UAD in brain MRI combined with 3D erasing and demonstrate that 3D methods clearly outperform their 2D counterpart for anomaly segmentation. Also, our spatial erasing method allows for further performance improvements and reduces the requirement for large data sets.

Sign in / Sign up

Export Citation Format

Share Document