Computed Tomography Slices Research Articles

Computed Tomography Scan Findings in Various Modes of Head Injury, Using GE Optima 128 Slice CT Scanner`

Background: Head injury is a global health problem that can cause disability and may result in death. CT scan detects and precisely localizes the skull fractures, epidural/subdural/subarachnoid hemorrhages, brain contusions and cerebral edema etc. CT has proven to be a valuable tool in the early diagnosis and prompt management of head trauma patients and has resulted in significant improvement in morbidity and mortality. Methods: A descriptive cross-sectional study, including 380 patients, presented to the radiology department of Hayatabad medical complex witha history of head trauma for computed tomography examination, from October 2019 to October 2020. The nature of the brain and skull lesions was analyzed in our study and the frequency of various findings was recorded. Results: Among 380 patients, the majority were males (248) making the male to female ratio to be around 2:1. The most prevalent finding was skull fractures (23.4%) followed by cerebral contusions (17.1%). Among extra-axial brain hemorrhages, extradural hematoma (15.2%) was observed more than subdural hematoma (6.8%) while only 3.4% presented with subarachnoid hemorrhages which also included intraventricular hemorrhages. Practical Implication: As road traffic accidents are the most common cause of head injuries so road traffic safety measures ought to be strictly enforced. Most of the CT scan done during head injuries were normal so CT guidelines for ordering should be implemented to scale back extra patient irradiation, unnecessary waste of resources and a further burden on the radiology department. Keywords: Head Injury, Computed Tomography (CT), Road Traffic Accidents (RTA), Skull Fractures, Epidural Hematoma.

StrokeViT with AutoML for brain stroke classification

Stroke, categorized under cardiovascular and circulatory diseases, is considered the second foremost cause of death worldwide, causing approximately 11% of deaths annually. Stroke diagnosis using a Computed Tomography (CT) scan is considered ideal for identifying whether the stroke is hemorrhagic or ischemic. However, most methods for stroke classification are based on a single slice-level prediction mechanism, meaning that the most imperative CT slice has to be manually selected by the radiologist from the original CT volume. This paper proposes an integration of Convolutional Neural Network (CNN), Vision Transformers (ViT), and AutoML to obtain slice-level predictions as well as patient-wise prediction results. While the CNN with inductive bias captures local features, the transformer captures long-range dependencies between sequences. This collaborative local-global feature extractor improves upon the slice-wise predictions of the CT volume. We propose stroke-specific feature extraction from each slice-wise prediction to obtain the patient-wise prediction using AutoML. While the slice-wise predictions helps the radiologist to verify close and corner cases, the patient-wise predictions makes the outcome clinically relevant and closer to real-world scenario. The proposed architecture has achieved an accuracy of 87% for single slice-level prediction and an accuracy of 92% for patient-wise prediction. For comparative analysis of slice-level predictions, standalone architectures of VGG-16, VGG-19, ResNet50, and ViT were considered. The proposed architecture has outperformed the standalone architectures by 9% in terms of accuracy. For patient-wise predictions, AutoML considers 13 different ML algorithms, of which 3 achieve an accuracy of more than 90%. The proposed architecture helps in reducing the manual effort by the radiologist to manually select the most imperative CT from the original CT volume and shows improvement over other standalone architectures for classification tasks. The proposed architecture can be generalized for volumetric scans aiding in the patient diagnosis of head and neck, lungs, diseases of hepatobiliary tract, genitourinary diseases, women’s imaging including breast cancer and various musculoskeletal diseases. Code for proposed stroke-specific feature extraction with the pre-trained weights of the trained model is available at: https://github.com/rishiraj-cs/StrokeViT_With_AutoML.

Improved Procedure for the 3D Reconstruction of Asphalt Concrete Mesostructures Considering the Similarity of Aggregate Phase Geometry between Adjacent CT Slices.

Existing image segmentation algorithms used for the computed tomography (CT) images of asphalt concrete mostly ignore the similarity of aggregate phase geometry between adjacent CT slices, thus increasing the variability in the aggregate phase pixel values between adjacent slices and leading to a large number of model defects, e.g., interconnected aggregates, flaky aggregates, and incomplete aggregates. The developed mesostructural models with these defects pose a challenge to following simulation operations. To address this issue, an improved procedure for the 3D reconstruction of asphalt concrete mesostructures considering the similarity of aggregate phase geometry between adjacent slices was developed, which includes two adjacent-slice pixel-value-correction algorithms, a multi-directional multiple-correction method, and an image pixel interpolation process. First, the bilinear interpolation algorithm was employed to improve the pixel density of 2D CT images and the average filtering algorithm was used to reduce the noise of the CT images. Subsequently, the OTSU method was employed to separate the asphalt mortar matrix phase from the aggregate phase, and the marker-based watershed segmentation method was used to separate the interconnected aggregates. Finally, the adjacent-slice pixel-value-correction algorithm was used to recover the similarity of aggregate phase geometry between adjacent CT slices, and the multi-directional multiple-correction method was used to further enhance the geometric similarity. The results show that the developed 3D reconstruction procedure removes most of the model defects in the 3D mesostructural model of asphalt concrete, thus realistically maintaining the 3D spatial distribution features and contour characteristics.

Quantification of Epicardial Adipose Tissue Volume and Attenuation for Cardiac CT Scans Using Deep Learning in a Single Multi-Task Framework.

Recent studies have shown that epicardial adipose tissue (EAT) is an independent atrial fibrillation (AF) prognostic marker and has influence on the myocardial function. In computed tomography (CT), EAT volume (EATv) and density (EATd) are parameters that are often used to quantify EAT. While increased EATv has been found to correlate with the prevalence and the recurrence of AF after ablation therapy, higher EATd correlates with inflammation due to arrest of lipid maturation and with high risk of plaque presence and plaque progression. Automation of the quantification task diminishes the variability in readings introduced by different observers in manual quantification and results in high reproducibility of studies and less time-consuming analysis. Our objective is to develop a fully automated quantification of EATv and EATd using a deep learning (DL) framework. We proposed a framework that consists of image classification and segmentation DL models and performs the task of selecting images with EAT from all the CT images acquired for a patient, and the task of segmenting the EAT from the output images of the preceding task. EATv and EATd are estimated using the segmentation masks to define the region of interest. For our experiments, a 300-patient dataset was divided into two subsets, each consisting of 150 patients: Dataset 1 (41,979 CT slices) for training the DL models, and Dataset 2 (36,428 CT slices) for evaluating the quantification of EATv and EATd. The classification model achieved accuracies of 98% for precision, recall and scores, and the segmentation model achieved accuracies in terms of mean ( std.) and median dice similarity coefficient scores of 0.844 ( 0.19) and 0.84, respectively. Using the evaluation set (Dataset 2), our approach resulted in a Pearson correlation coefficient of 0.971 ( = 0.943) between the label and predicted EATv, and the correlation coefficient of 0.972 ( = 0.945) between the label and predicted EATd. We proposed a framework that provides a fast and robust strategy for accurate EAT segmentation, and volume (EATv) and attenuation (EATd) quantification tasks. The framework will be useful to clinicians and other practitioners for carrying out reproducible EAT quantification at patient level or for large cohorts and high-throughput projects.

Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase.

Large slice thickness or slice increment causes information insufficiency of Computed Tomography (CT) data in the longitudinal direction, which degrades the quality of CT-based diagnosis. Traditional approaches such as high-resolution computed tomography (HRCT) and linear interpolation can solve this problem. However, HRCT suffers from dose increase, and linear interpolation causes artifacts. In this study, we propose a deep-learning-based approach to reconstruct densely sliced CT from sparsely sliced CT data without any dose increase. The proposed method reconstructs CT images from neighboring slices using a U-net architecture. To prevent multiple reconstructed slices from influencing one another, we propose a parallel architecture in which multiple U-net architectures work independently. Moreover, for a specific organ (i.e., the liver), we propose a range-clip technique to improve reconstruction quality, which enhances the learning of CT values within this organ by enlarging the range of the training data. CT data from 130 patients were collected, with 80% used for training and the remaining 20% used for testing. Experiments showed that our parallel U-net architecture reduced the mean absolute error of CT values in the reconstructed slices by 22.05%, and also reduced the incidence of artifacts around the boundaries of target organs, compared with linear interpolation. Further improvements of 15.12%, 11.04%, 10.94%, and 10.63% were achieved for the liver, left kidney, right kidney, and stomach, respectively, using the proposed range-clip algorithm. Also, we compared the proposed architecture with original U-net method, and the experimental results demonstrated the superiority of our approach.

Patellar Tendon–Trochlear Groove Angle Measured on a Single Computed Tomography Slice of the Distal Femoral Trochlear Groove Is a Reliable Measurement for the Evaluation of Patellar Instability

To verify the reliability of patellar tendon-trochlear groove angle (PTTG-A) measured by computed tomography (CT) and the clinical significance in evaluation of patellar instability. A retrospective study of hospitalized patients with knee pain or injury and had knee CT from January 2017 to June 2021 was performed. PTTG-A and tibial tuberosity-trochlear groove (TT-TG) distance were measured on CT. Spearman correlation analysis was analyzed between the 2 measurements. The intraclass correlation coefficient was determined for inter- and intraobserver reproducibility. The capacity of PTTG-A and TT-TG to predict patellar instability was evaluated by the receiver operating characteristic curve. Data from the control group were used to determine the pathologic thresholds and logistic regression analysis. Included were 113 patients. There were 60 patients with the history of at least 2 episodes of patellar dislocation (study group) and 53 patients without a history of patellar dislocation (control group). The respective PTTG-A and TT-TG distances in the study group (35.2 ± 8.4° and 19.6 ± 4.6 mm) were significantly greater than those of the controls (20.8 ± 5.8° and 13.3 ± 4.5 mm) (P < .001). The correlation between the 2 measurements was strong (r= 0.730, P < .001). The inter- and intraobserver reliability of the PTTG-A were better than TT-TG distance in both groups. The AUC of PTTG-A was greater than that of the TT-TG distance (0.895 vs 0.769, respectively). With the cutoff value of PTTG-A and TT-TG being 26.3° and 16.3 mm, the value of the pathologic threshold of PTTG-A was 30.0°, with a dominance ratio of 16.88 (95% confidence interval 2.88-98.89, P= .002). The PTTG-A measured on a single CT slice of the distal femoral trochlear groove is a more reliable measurement than TT-TG distance for the prediction of patellar instability. III; A retrospective cohort study.

A deep residual attention-based U-Net with a biplane joint method for liver segmentation from CT scans

Liver tumours are diseases with high morbidity and high deterioration probabilities, and accurate liver area segmentation from computed tomography (CT) scans is a prerequisite for quick tumour diagnosis. While 2D network segmentation methods can perform segmentation with lower device performance requirements, they often discard the rich 3D spatial information contained in CT scans, limiting their segmentation accuracy. Hence, a deep residual attention-based U-shaped network (DRAUNet) with a biplane joint method for liver segmentation is proposed in this paper, where the biplane joint method introduces coronal CT slices to assist the transverse slices with segmentation, incorporating more 3D spatial information into the segmentation results to improve the segmentation performance of the network. Additionally, a novel deep residual block (DR block) and dual-effect attention module (DAM) are introduced in DRAUNet, where the DR block has deeper layers and two shortcut paths. The DAM efficiently combines the correlations of feature channels and the spatial locations of feature maps. The DRAUNet with the biplane joint method is tested on three datasets, Liver Tumour Segmentation (LiTS), 3D Image Reconstruction for Comparison of Algorithms Database (3DIRCADb), and Segmentation of the Liver Competition 2007 (Sliver07), and it achieves 97.3%, 97.4%, and 96.9% Dice similarity coefficients (DSCs) for liver segmentation, respectively, outperforming most state-of-the-art networks; this strongly demonstrates the segmentation performance of DRAUNet and the ability of the biplane joint method to obtain 3D spatial information from 3D images.

Learning label diffusion maps for semi-automatic segmentation of lung CT images with COVID-19

Deep Learning (DL) has become one of the key approaches for dealing with many challenges in medical imaging, which includes lung segmentation in Computed Tomography (CT). The use of seeded segmentation methods is another effective approach to get accurate partitions from complex CT images, as they give users autonomy, flexibility and easy usability when selecting specific targets for measurement purposes or pharmaceutical interventions. In this paper, we combine the accuracy of deep contour leaning with the versatility of seeded segmentation to yield a semi-automatic framework for segmenting lung CT images from patients affected by COVID-19. More specifically, we design a DL-driven approach that learns label diffusion maps from a contour detection network integrated with a label propagation model, used to diffuse the seeds over the CT images. Moreover, the trained model induces the diffusion of the seeds by only taking as input a marked CT-scan, segmenting hundreds of CT slices in an unsupervised and recursive way. Another important trait of our framework is that it is capable of segmenting lung structures even in the lack of well-defined boundaries and regardless of the level of COVID-19 infection. The accuracy and effectiveness of our learned diffusion model are attested to by both qualitative as well as quantitative comparisons involving several user-steered segmentations methods and eight CT data sets containing different types of lesions caused by COVID-19.

Towards universal comparability of pericoronary adipose tissue attenuation: a coronary computed tomography angiography phantom study

ObjectivesDifferent computed tomography (CT) scanners, variations in acquisition protocols, and technical parameters employed for image reconstruction may introduce bias in the analysis of pericoronary adipose tissue (PCAT) attenuation derived from coronary computed tomography angiography (CCTA). Therefore, the aim of this study was to establish the effect of tube voltage, measured as kilovoltage peak (kVp), and iterative reconstruction on PCAT mean attenuation (PCATMA).MethodsTwelve healthy ex vivo porcine hearts were injected with iodine-enriched agar-agar to allow for ex vivo CCTA imaging on a 256-slice CT and a dual-source CT system. Images were acquired at tube voltages of 80, 100, 120, and 140 kVp and reconstructed by using both filtered back projection and iterative reconstruction algorithms. PCATMA was measured semi-automatically on CCTA images in the proximal segment of coronary arteries.ResultsThe tube voltage showed a significant effect on PCATMA measurements on both the 256-slice CT scanner (p < 0.001) and the dual-source CT system (p = 0.013), resulting in higher attenuation values with increasing tube voltage. Similarly, the use of iterative reconstructions was associated with a significant increase of PCATMA (256-slice CT: p < 0.001 and dual-source CT: p = 0.014). Averaged conversion factors to correct PCATMA measurements for tube voltage other than 120 kVp were 1.267, 1.080 and 0.947 for 80, 100, and 140 kVp, respectively.ConclusionPCATMA values are significantly affected by acquisition and reconstruction parameters. The same tube voltage and reconstruction type are recommended when PCAT attenuation is used in multicenter and longitudinal studies.Key Points• The tube voltage used for CCTA acquisition affects pericoronary adipose tissue attenuation, resulting in higher attenuation values of fat with increasing tube voltage.• Conversion factors for pericoronary adipose tissue attenuation values could be used to adjust for differences in attenuation between scans performed at different tube voltages.• In longitudinal CCTA studies employing pericoronary adipose tissue attenuation as imaging endpoint, it is recommended to maintain tube voltage and image reconstruction type constant across serial scans.

Association between surgical tracheostomy and chronic tracheal stenosis: A retrospective, single-center study.

Tracheal stenosis is a major complication of tracheostomy. Accordingly, anesthesiologists tend to select a smaller endotracheal tube (ETT) than usual for patients with a prior tracheostomy history, regardless of the presence or absence of respiratory symptoms. However, it likely comes from our trial and error, not scientific evidence. Therefore, in this study, we retrospectively examined the association between traditional surgical tracheostomy and tracheal stenosis as assessed by transverse computed tomography (CT). Patients who underwent surgery for head and neck cancer from January 2010 to December 2013, with a temporary tracheostomy closed within a couple of months, were included. Exclusion criteria were tracheostoma before surgery, permanent tracheostomy, or insufficient CT follow-up. Transverse CT slices were measured 2 cm above and below the tracheostomy site (0.5 cm/slice for a total of 9 slices). The minimum cross-sectional tracheal area and horizontal and vertical diameters in transverse CT slices were compared before (baseline: BL), 6 months (6M) and 12 months (12M) after tracheostomy. Tracheal stenosis was defined as a decrease in the minimum cross-sectional tracheal area compared to BL. Of 112 patients, 77 were included. The minimum tracheal area was significantly decreased at 6M and 12M compared to BL (BL: mean 285 [SD 68] mm2, 6M: 267 [70] mm2, P < 0.01 vs. BL, 12M: 269 [68] mm2, P < 0.01 vs. BL), and the localization was predominantly at or above the tracheostomy site at 6M and 12M. Tracheal stenosis was identified in 55 patients at 6M and in 49 patients at 12M without any respiratory symptoms. With regard to horizontal and vertical diameter, only horizontal diameter was significantly decreased at 6M and 12M compared to BL (BL: 16.8 [2.4] mm, 6M: 15.4 [2.7] mm, P < 0.01 vs. BL, 12M: 15.6 [2.8] mm, P < 0.01 vs. BL). Conventional surgical tracheostomy was associated with a decreased horizontal diameter of the trachea. It resulted in a decreased cross-sectional tracheal area in more than one-half of the patients; however, no patient complained of any respiratory symptoms. Therefore, even without respiratory symptoms, prior tracheostomy causes an increased risk of tracheal stenosis, and using a smaller ETT than usual could be reasonable.

U-NetCTS: U-Net deep neural network for fully automatic segmentation of 3D CT DICOM volume

The accurate segmentation of computed tomography (CT) scan volume is an essential step in radiomic analysis as well as in developing advanced surgical planning techniques with numerous medical applications. When this process is performed manually by a clinician, it is laborious, time consuming, prone to error, and its success depends to a large extent on the level of experience. In this work, we propose an automated deep learning (DL) segmentation framework for CT images called U-Net CT Segmentation (U-NetCTS) to combine the DL U-Net and CT images in the domain of automatic segmentation. Experimental results show that U-NetCTS framework can segment different CT DICOM image regions of interest in a range of random CT volumes. A statistical and qualitative comparison of the CT slices automatically segmented by U-NetCTS framework and ground-truth images indicates that U-NetCTS framework achieves a high level of accuracy, where the Tanimoto coefficient, dice similarity coefficient, and peak signal-to-noise ratio values are 99.06%, 99.52%, and 53.29 dB, respectively. The DC value is also higher than that of state-of-the-art DL techniques for automatic segmentation of CT images of various human organs. Furthermore, a total amount of 3595 CT slices is employed in this study with various CT region of interest to validate the results.

Interischial Spine Distance Is a Simple Index of the Narrow Pelvis That Can Predict Difficulty During Laparoscopic Low Anterior Resection.

A narrow pelvis makes laparoscopic rectal resection difficult. This study aimed to evaluate whether a simple measurement on computed tomography can predict procedural difficulty. A total of 62 patients with low rectal cancer underwent conventional laparoscopic low anterior resection. The interischial spine (IS) distance (ie, the distance between the ischial spines) was measured on an axial computed tomography slice. The operative time, blood loss, and time from the insertion of linear staplers to completion of clamping on the distal end of the rectum (clamp time) were compared between patients with narrow or wide pelvises. Overall, 42 men and 20 women with low rectal cancer were assessed. The mean tumor size was 34.5mm. Total or tumor-specific mesorectal excisions were performed in all cases; high ligation and resection of the inferior mesenteric arteries were carried out in 92% of patients. The mean operative time and blood loss were 206 minutes and 15mL, respectively. Four patients (6.5%) experienced postoperative complications, including 2 anastomotic leaks (3.2%). The mean IS distance was 93.3mm. In simple linear regression analysis, a shorter IS distance correlated with a longer operative time ( R2 =0.08, P =0.030) and the clamp time ( R2 =0.07, P =0.046). Using a receiver operating characteristic curve, a narrow pelvis was defined as an IS distance <94.7mm. Multivariate regression analysis revealed that an IS distance <94.7mm (odds ratio: 3.51; P =0.04) was independently associated with a longer clamp time. The IS distance is a simple and useful measurement for predicting the difficulty of laparoscopic low anterior resection.

Classification prediction of pancreatic cystic neoplasms based on radiomics deep learning models

BackgroundPreoperative prediction of pancreatic cystic neoplasm (PCN) differentiation has significant value for the implementation of personalized diagnosis and treatment plans. This study aimed to build radiomics deep learning (DL) models using computed tomography (CT) data for the preoperative differential diagnosis of common cystic tumors of the pancreas.MethodsClinical and CT data of 193 patients with PCN were collected for this study. Among these patients, 99 were pathologically diagnosed with pancreatic serous cystadenoma (SCA), 55 were diagnosed with mucinous cystadenoma (MCA) and 39 were diagnosed with intraductal papillary mucinous neoplasm (IPMN). The regions of interest (ROIs) were obtained based on manual image segmentation of CT slices. The radiomics and radiomics-DL models were constructed using support vector machines (SVMs). Moreover, based on the fusion of clinical and radiological features, the best combined feature set was obtained according to the Akaike information criterion (AIC) analysis. Then the fused model was constructed using logistic regression.ResultsFor the SCA differential diagnosis, the fused model performed the best and obtained an average area under the curve (AUC) of 0.916. It had a best feature set including position, polycystic features (≥6), cystic wall calcification, pancreatic duct dilatation and radiomics-DL score. For the MCA and IPMN differential diagnosis, the fused model with AUC of 0.973 had a best feature set including age, communication with the pancreatic duct and radiomics score.ConclusionsThe radiomics, radiomics-DL and fused models based on CT images have a favorable differential diagnostic performance for SCA, MCA and IPMN. These findings may be beneficial for the exploration of individualized management strategies.

Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods.

Medical image super-resolution (SR) has mainly been developed for a single image in the literature. However, there is a growing demand for high-resolution, thin-slice medical images. We hypothesized that fusing the two planes of a computed tomography (CT) study and applying the SR model to the third plane could yield high-quality thin-slice SR images. From the same CT study, we collected axial planes of 1 mm and 5 mm in thickness and coronal planes of 5 mm in thickness. Four SR algorithms were then used for SR reconstruction. Quantitative measurements were performed for image quality testing. We also tested the effects of different regions of interest (ROIs). Based on quantitative comparisons, the image quality obtained when the SR models were applied to the sagittal plane was better than that when applying the models to the other planes. The results were statistically significant according to the Wilcoxon signed-rank test. The overall effect of the enhanced deep residual network (EDSR) model was superior to those of the other three resolution-enhancement methods. A maximal ROI containing minimal blank areas was the most appropriate for quantitative measurements. Fusing two series of thick-slice CT images and applying SR models to the third plane can yield high-resolution thin-slice CT images. EDSR provides superior SR performance across all ROI conditions.

PAM-DenseNet: A Deep Convolutional Neural Network for Computer-Aided COVID-19 Diagnosis.

Currently, several convolutional neural network (CNN)-based methods have been proposed for computer-aided COVID-19 diagnosis based on lung computed tomography (CT) scans. However, the lesions of pneumonia in CT scans have wide variations in appearances, sizes, and locations in the lung regions, and the manifestations of COVID-19 in CT scans are also similar to other types of viral pneumonia, which hinders the further improvement of CNN-based methods. Delineating infection regions manually is a solution to this issue, while excessive workload of physicians during the epidemic makes it difficult for manual delineation. In this article, we propose a CNN called dense connectivity network with parallel attention module (PAM-DenseNet), which can perform well on coarse labels without manually delineated infection regions. The parallel attention module automatically learns to strengthen informative features from both channelwise and spatialwise simultaneously, which can make the network pay more attention to the infection regions without any manual delineation. The dense connectivity structure performs feature maps reuse by introducing direct connections from previous layers to all subsequent layers, which can extract representative features from fewer CT slices. The proposed network is first trained on 3530 lung CT slices selected from 382 COVID-19 lung CT scans, 372 lung CT scans infected by other pneumonia, and 200 normal lung CT scans to obtain a pretrained model for slicewise prediction. We then apply this pretrained model to a CT scans dataset containing 94 COVID-19 CT scans, 93 other pneumonia CT scans, and 93 normal lung scans, and achieve patientwise prediction through a voting mechanism. The experimental results show that the proposed network achieves promising results with an accuracy of 94.29%, a precision of 93.75%, a sensitivity of 95.74%, and a specificity of 96.77%, which is comparable to the methods that are based on manually delineated infection regions.

Deep learning-based defect detection in industrial CT volumes of castings

Industrial X-ray computed tomography (CT) has proven to be one of the most powerful non-destructive testing (NDT) methods for the inspection of light metal castings. The generated CT volume allows for the internal and external geometry of the specimen to be measured, casting defects to be localised and their statistical properties to be investigated. On the other hand, CT volumes are very prone to artefacts that can be mistaken for defects by conventional segmentation algorithms. These artefacts require trained operators to distinguish them from real defects, which makes CT inspection very time consuming if it is to be implemented on the production line. Foundries using this inspection method are constantly looking for a module that can perform this interpretation automatically. Based on CT data of aluminium alloy automotive and aerospace specimens provided by industrial partners, an automated approach for the analysis of discontinuities inside CT volumes is developed in this paper based on a two-stage pipeline: 2D segmentation of CT slices with automatic deep segmentation using U-Net to detect suspicious greyscale discontinuities; and classification of these discontinuities into true alarms (defects) or false alarms (artefacts and noise) using a new convolutional neural network classifier called CT-Casting-Net. The choice of each model and the training results are presented and discussed, as well as the efficiency of the approach as an automatic defect detection algorithm for industrial CT volumes using metrics relevant to the field of non-destructive testing. The approach is tested on six new CT volumes with 301 defects and achieves an object-level recall of 99%, a precision of 87% and a voxel-level intersection-over-union (IoU) of 62%.

Absolute iodine concentration for dynamic perfusion imaging of the myocardium: improved detection of poststenotic ischaemic in a 3D-printed dynamic heart phantom

BackgroundTo investigate the detection capabilities of myocardial perfusion defects of dual-energy computed tomography (CT) technology using time-resolved iodine-based maps for functional assessment of coronary stenosis in a dynamic heart phantom.MethodsAn anatomical heart model was designed using a three-dimensional (3D) printing technique. The lumen of the right coronary artery was reduced to 25% of the original areal cross-section. Scans were acquired with a 64-slice dual-layer CT equipment using a perfusion protocol with 36 time points. For distinguishing haemodynamically affected from unaffected myocardial regions, conventional and spectral mean transit time (MTT) parameter maps were compared. A dose reduction technique was simulated by using a subset of time points of the time attenuation curves (TACs).ResultsThe tracer kinetic modeling showed decreased errors on fit parameters from conventional to spectral TACs (42% reduction for A and 40% for λ). Three characteristic regions (highly, moderately, and not affected by the simulated stenosis) can be distinguished in all spectral perfusion maps. The best distinction was observed on MTT maps. An area under the curve (AUC) value of 1.00 for the voxel-wise differentiation of haemodynamically affected tissue was achieved versus a 0.89 AUC for conventional MTT maps. By temporal under-sampling, a dose reduction of approximately 78% from 19 to 4.3 mSv was achieved with a 0.96 AUC.ConclusionDual-energy CT can provide time-resolved iodine density data, which enables the calculation of absolute quantitative perfusion maps with decreased fitting errors, improving the accuracy for poststenotic myocardial ischaemic detection in a 3D-printed heart phantom.

Comparison of orbital volume measured using computed tomography and fluid displacement: A comparative study using dry skull

Objectives: The purpose of the study was as follows: (1) To compare orbital volume calculated using computed tomography (CT) scans with real-time measurements. (2) To evaluate if the orbital volume of the adjacent orbit can be taken as a tool of comparison for orbital volume correction in orbital fractures. Materials and Methods: A prospective study was conducted on 30 orbital cavities with intact orbital walls. The foramina and fissures were sealed using molding wax. Alginate impressions of the orbital cavity were taken to determine the orbital volume using the Archimedes principle. GE light speed 64 slices CT scanner was used to scan the orbits with 0.8 mm sections. Orbital volume was calculated using the CT software GE ADW 4.5 workstation. Results: The comparison of CT measurement and Archimedes principle measurement shows a mean and standard error of 0.2333 mm and 0.09794, respectively, on the right orbits and a mean and standard error of 0.10011 mm and 0.0981, respectively, on the left orbits. The comparison of the right and left orbits shows a mean and standard error of 0.4067 mm and 0.2771 mm, respectively, using the Archimedes principle and a mean and standard error of 0.3300 mm and 0.2775, respectively, using CT scans. Conclusion: It was found that the difference in orbital volume between CT and real-time measurement is very negligible. The study shows that CT is a reliable tool for the orbital volume measurement and the adjacent orbit can be taken as a comparative tool for the orbital volume corrections.

Computed Tomography Scan Findings in Various Modes of Head Injury, using Ge Optima 128 Slice CT Scanner

Background: Head injury is a global health problem that can cause disability and may result in death. CT scan detects and precisely localizes the skull fractures, epidural/subdural/subarachnoid hemorrhages, brain contusions and cerebral edema etc. CT has proven to be a valuable tool in the early diagnosis and prompt management of head trauma patients. Methods: A descriptive cross-sectional study, including 380 patients, presented to the radiology department of Hayatabad medical complex witha history of head trauma for computed tomography examination, from October 2019 to October 2020. The nature of the brain and skull lesions was analyzed in our study and the frequency of various findings was recorded. Results: Among 380 patients, the majority were males (248) making the male to female ratio to be around 2:1. The most prevalent finding was skull fractures (23.4%) followed by cerebral contusions (17.1%). Among extra-axial brain hemorrhages, extradural hematoma (15.2%) was observed more than subdural hematoma (6.8%) while only 3.4% presented with subarachnoid hemorrhages which also included intraventricular hemorrhages. Practical Implication: As road traffic accidents are the most common cause of head injuries so road traffic safety measures ought to be strictly enforced. Most of the CT scan done during head injuries were normal so CT guidelines for ordering should be implemented to scale back extra patient irradiation, unnecessary waste of resources Conclusion: Our study concluded that younger populations and males are more prone to head injury and road traffic accident is the most common mode of head trauma. So, ensuring proper traffic rules along with educating the more prone population will significantly reduce the incidence of serious head injuries. Keywords: Head Injury, Computed Tomography (CT), Road Traffic Accidents (RTA), Skull Fractures, Epidural Hematoma.

Gross anatomy, computed tomography, magnetic resonance imaging and bone mineral densitometry of the ovine metacarpo/metatarsophalangeal joint.

This study was aimed to provide anatomical atlas of the ovine metacarpo/metatarsophalangeal joints using computed tomography (CT) scan and magnetic resonance imaging (MRI), as well as to investigate bone mineral density (BMD) and morphometric features of this joint. The limbs of twenty adult Sanjabi sheep were examined. Imaging was performed using a 16-slice multi-detector CT scanner and a 1.5 Tesla MRI scanner. The obtained images were correlated with corresponding anatomical sections. BMD was measured by Dual Energy X-ray Absorptiometry (DEXA) method. Also morphometric features included distance between metacarpal and metatarsal heads, width of metacarpal and metatarsal head, length, width and the height of the proximal sesamoid bones were measured. In MRI images, compact bones, ligaments and tendons showed less signal intensity (hypointense). The fatty tissue and bone marrow had more signal intensity (hyperintense), but articular cartilage and synovial fluid showed moderate signal intensity. BMD in the left hind limb was significantly higher than other three limbs (p ≤0.05). The length of proximal sesamoid bones in left forelimb was higher than right forelimb (p ≤ 0.05). The thickness of proximal sesamoid bones in left limbs was higher than those in their counterparts (p ≤ 0.05). The width of the medial head in the forelimbs was significantly greater than the hind limbs (p ≤ 0.05). The present results might be useful in managing the clinical techniques on this joint. Larger volume of the proximal sesamoid bones and wider medial head in the forelimbs compared to the hindlimbs impel this speculation that the centre of gravity is closer to the forelimbs.