Search

Background: Computed tomography (CT) and magnetic resonance imaging (MRI) are indicated for use in preoperative planning and may complicate diagnosis and place a burden on patients with lumbar disc herniation. Purpose: To investigate the diagnostic potential of MRI-based synthetic CT with conventional CT in the diagnosis of lumbar disc herniation. Material and Methods: After obtaining prior institutional review board approval, 19 patients who underwent conventional and synthetic CT imaging were enrolled in this prospective study. Synthetic CT images were generated from the MRI data using U-net. The two sets of images were compared and analyzed qualitatively by two musculoskeletal radiologists. The images were rated on a 4-point scale to determine their subjective quality. The agreement between the conventional and synthetic images for a diagnosis of lumbar disc herniation was determined independently using the kappa statistic. The diagnostic performances of conventional and synthetic CT images were evaluated for sensitivity, specificity, and accuracy, and the consensual results based on T2-weighted imaging were employed as the reference standard. Results: The inter-reader and intra-reader agreement were almost moderate for all evaluated modalities (κ = 0.57−0.79 and 0.47−0.75, respectively). The sensitivity, specificity, and accuracy for detecting lumbar disc herniation were similar for synthetic and conventional CT images (synthetic vs. conventional, reader 1: sensitivity = 91% vs. 81%, specificity = 83% vs. 100%, accuracy = 87% vs. 91%; P < 0.001; reader 2: sensitivity = 84% vs. 81%, specificity = 85% vs. 98%, accuracy = 84% vs. 90%; P < 0.001). Conclusion: Synthetic CT images can be used in the diagnostics of lumbar disc herniation. [ABSTRACT FROM AUTHOR]

Linear-array-based photoacoustic computed tomography (PACT) has been widely used in vascular imaging due to its low cost and high compatibility with current ultrasound systems. However, linear-array transducers have inherent limitations for three-dimensional imaging due to the poor elevation resolution. In this study, we introduced a deep learning-assisted data process algorithm to enhance the image quality in linear-array-based PACT. Compared to our earlier study where training was performed on 2D reconstructed data, here, we utilized 2D and 3D reconstructed data to train the two networks separately. We then fused the image data from both 2D and 3D training to get features from both algorithms. The numerical and in vivo validations indicate that our approach can improve elevation resolution, recover the true size of the object, and enhance deep vessels. Our deep learning-assisted approach can be applied to translational imaging applications that require detailed visualization of vascular features. [ABSTRACT FROM AUTHOR]

With an ever-growing aging population, the prevalence of normal pressure hydrocephalus (NPH) is increasing. Clinical symptoms of NPH include cognitive impairment, gait disturbance, and urinary incontinence. Surgery can improve symptoms, which leads to the disease's alternative name: treatable dementia. The Evans index (EI), defined as the ratio of the maximal width of the frontal horns to the maximum inner skull diameter, is the most commonly used index to indirectly assess the condition of the ventricles in NPH patients. EI measurement is simple, fast, and does not require any special software; in clinical practice, an EI >0.3 is the criterion for ventricular enlargement. However, EI's measurement methods, threshold setting, correlation with ventricle volume, and even its clinical value has been questioned. Based on the EI, the z-EI and anteroposterior diameter of the lateral ventricle index were derived and are discussed in this review. [ABSTRACT FROM AUTHOR]

Cross-modality medical image synthesis between magnetic resonance (MR) images and computed tomography (CT) images has attracted increasing attention in many medical imaging area. Many deep learning methods have been used to generate pseudo-MR/CT images from counterpart modality images. In this study, we used U-Net and Cycle-Consistent Adversarial Networks (CycleGAN), which were typical networks of supervised and unsupervised deep learning methods, respectively, to transform MR/CT images to their counterpart modality. Experimental results show that synthetic images predicted by the proposed U-Net method got lower mean absolute error (MAE), higher structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) in both directions of CT/MR synthesis, especially in synthetic CT image generation. Though synthetic images by the U-Net method has less contrast information than those by the CycleGAN method, the pixel value profile tendency of the synthetic images by the U-Net method is closer to the ground truth images. This work demonstrated that supervised deep learning method outperforms unsupervised deep learning method in accuracy for medical tasks of MR/CT synthesis. [ABSTRACT FROM AUTHOR]

To align multimodal images is important for information fusion, clinical diagnosis, treatment planning, and delivery, while few methods have been dedicated to matching computerized tomography (CT) and magnetic resonance (MR) images of lumbar spine. This study proposes a coarse-to-fine registration framework to address this issue. Firstly, a pair of CT-MR images are rigidly aligned for global positioning. Then, a bending energy term is penalized into the normalized mutual information for the local deformation of soft tissues. In the end, the framework is validated on 40 pairs of CT-MR images from our in-house collection and 15 image pairs from the SpineWeb database. Experimental results show high overlapping ratio (in-house collection, vertebrae 0.97 ± 0.02 , blood vessel 0.88 ± 0.07 ; SpineWeb, vertebrae 0.95 ± 0.03 , blood vessel 0.93 ± 0.10) and low target registration error (in-house collection, ≤ 2.00 ± 0.62 mm ; SpineWeb, ≤ 2.37 ± 0.76 mm) are achieved. The proposed framework concerns both the incompressibility of bone structures and the nonrigid deformation of soft tissues. It enables accurate CT-MR registration of lumbar spine images and facilitates image fusion, spine disease diagnosis, and interventional treatment delivery. [ABSTRACT FROM AUTHOR]

Purpose: To recommend a new simple and explicit index termed the anteroposterior diameter of the lateral ventricle index (ALVI) for assessing brain ventricular size in neuroimaging and to compare Evans index (EI) between idiopathic normal pressure hydrocephalus (iNPH) patients and age-matched healthy elderly subjects. Methods: Retrospective measurements of ventricular volume (VV), relative VV (RVV), the EI, and the ALVI were taken from thin-section CT scans for 23 pre-shunt-insertion iNPH patients and 62 age-matched healthy elderly volunteers. The area under the receiver operating characteristic (ROC) curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were calculated to assess the effectiveness of ALVI scores for predicting VV. Results: The correlations between VV or RVV and ALVI scores (VV, r = 0.957; RVV, r = 0.983) were significantly stronger than the corresponding correlations with EI scores (VV, r = 0.843; RVV, r = 0.840). The AUC for ALVI scores was significantly greater than the AUC for EI scores. Furthermore, with the inclusion of the ALVI, the NRI value was 0.14 and the IDI value was 0.14; these improvements were also statistically significant. Conclusion: The ALVI is a more accurate and more explicitly defined marker of VV than the EI and assesses ventricular enlargement effectively. We suggest that ventricular enlargement of the healthy elderly be defined by ALVI > 0.50. [ABSTRACT FROM AUTHOR]

Background: Compared to adults, there are relatively few studies on COVID-19 infection in children, and even less focusing on the unique features of COVID-19 in children in terms of laboratory findings, locations of computerized tomography (CT) lesions, and the role of CT in evaluating clinical recovery. The objective of this study is to report the results from patients at Wuhan Children's Hospital, located within the initial center of the outbreak.Methods: Clinical, imaging, and laboratory data of 76 children were collected retrospectively and analyzed with the Fisher exact test and Cox regression statistical methods.Results: Among 50 children with a positive COVID-19 real-time reverse-transcriptase polymerase chain reaction (PCR), five had negative PCR results initially but showed positive results in subsequent tests. Eight (16%) patients had lymphopenia, seven (14%) with thrombocytopenia, four (8%) with lymphocytosis, two (4%) with thrombocytosis, ten (20%) with elevated C-reactive protein, four (8%) with hemoglobin above, and six (12%) with below standard reference values. Seven (14%) of the 50 had no radiologic evidence of disease on chest CT. For the 43 patients who had abnormal CT findings, in addition to previously reported patterns of ground-glass opacity (67%), local patchy shadowing (37%), local bilateral patchy shadowing (21%), and lesion location of lower lobes (65%), other CT features include that an overwhelming number of pediatric patients had lesions in the subpleural area (95%) and 22 of the 28 lower lobe lesions were in the posterior segment (78%). Lesions in most of the 15 patients (67%) who received chest CT at discharge were not completely absorbed, and 26% of these pediatric patients had CT lesions that were either unchanged or worse.Conclusions: There were a few differences between COVID-19 children and COVID-19 adults in terms of laboratory findings and CT characteristics. CT is a powerful tool to detect and characterize COVID-19 pneumonia but has little utility in evaluating clinical recovery for children. These results oppose current COVID-19 hospital discharge criteria in China, as one requirement is that pulmonary imaging must show significant lesion absorption prior to discharge. These differences between pediatric and adult cases of COVID-19 may necessitate pediatric-specific discharge criteria. [ABSTRACT FROM AUTHOR]

Objectives: To evaluate the performance of a novel three-dimensional (3D) joint convolutional and recurrent neural network (CNN-RNN) for the detection of intracranial hemorrhage (ICH) and its five subtypes (cerebral parenchymal, intraventricular, subdural, epidural, and subarachnoid) in non-contrast head CT.Methods: A total of 2836 subjects (ICH/normal, 1836/1000) from three institutions were included in this ethically approved retrospective study, with a total of 76,621 slices from non-contrast head CT scans. ICH and its five subtypes were annotated by three independent experienced radiologists, with majority voting as reference standard for both the subject level and the slice level. Ninety percent of data was used for training and validation, and the rest 10% for final evaluation. A joint CNN-RNN classification framework was proposed, with the flexibility to train when subject-level or slice-level labels are available. The predictions were compared with the interpretations from three junior radiology trainees and an additional senior radiologist.Results: It took our algorithm less than 30 s on average to process a 3D CT scan. For the two-type classification task (predicting bleeding or not), our algorithm achieved excellent values (≥ 0.98) across all reporting metrics on the subject level. For the five-type classification task (predicting five subtypes), our algorithm achieved > 0.8 AUC across all subtypes. The performance of our algorithm was generally superior to the average performance of the junior radiology trainees for both two-type and five-type classification tasks.Conclusions: The proposed method was able to accurately detect ICH and its subtypes with fast speed, suggesting its potential for assisting radiologists and physicians in their clinical diagnosis workflow.Key Points: • A 3D joint CNN-RNN deep learning framework was developed for ICH detection and subtype classification, which has the flexibility to train with either subject-level labels or slice-level labels. • This deep learning framework is fast and accurate at detecting ICH and its subtypes. • The performance of the automated algorithm was superior to the average performance of three junior radiology trainees in this work, suggesting its potential to reduce initial misinterpretations. [ABSTRACT FROM AUTHOR]

Electrode position after deep brain stimulation (DBS) for Parkinson's disease (PD) needs to be confirmed, but there are concerns about the risk of postoperative magnetic resonance imaging (MRI) after DBS. These issues could be avoided by fusion images obtained from preoperative MRI and postoperative computed tomography (CT). This study aimed to investigate image fusion technology for displaying the position of the electrodes compared with postoperative MRI. This was a retrospective study of 32 patients with PD treated with bilateral subthalamic nucleus (STN) DBS between April 2015 and March 2016. The postoperative (same day) CT and preoperative MRI were fused using the Elekta Leksell 10.1 planning workstation (Elekta Instruments, Stockholm, Sweden). The position of the electrodes was compared between the fusion images and postoperative 1–2-week MRI. The position of the electrodes was highly correlated between the fusion and postoperative MRI (all r between 0.865 and 0.996; all P < 0.001). The differences of the left electrode position in the lateral and vertical planes was significantly different between the two methods (0.30 and 0.24 mm, respectively, both P < 0.05), but there were no significant differences for the other electrode and planes (all P > 0.05). The position of the electrodes was highly correlated between the fusion and postoperative MRI. The CT-MRI fusion images could be used to avoid the potential risks of MRI after DBS in patients with PD. [ABSTRACT FROM AUTHOR]

Background: Apart from transepicondylar axis, the native femoral sulcus was also reported to be used as a guide for the femoral component position in total knee arthroplasty (TKA). However, it was not shown in patients with severe knee osteoarthritis. This study was conducted to compare the position of trochlear groove in patients with and without osteoarthritis, and to assess whether trochlear groove could be used as a guide for position of femoral component in TKA for severe knee osteoarthritis. Methods: Total 50 severe knee osteoarthritis patients (Kellgren Lawrence grade 3 or 4) who underwent TKA were included. Meanwhile, 50 patients who underwent arthroscopic surgery without osteoarthritis were included as control. The distance from trochlear groove to the midpoint of a virtual anterior condyle osteotomy line (parallel to the posterior condyle line) (a-b) was recorded by radiological and surgical measurements. Midpoint of transepicondylar axis and trochlear groove were used as guide for placing prosthesis model in TKA, respectively. No-thumb test was performed to assess the patellar tracking. The position of femoral component was finally performed using trochlear groove as guide in TKA. Results: Value of "a-b" was significantly different between osteoarthritic and control knees (P = 0.008). During the placement of prosthesis model, similar patellar tracking was detected between using midpoint of transepicondylar axis and trochlear groove as guide (P > 0.05). After placing femoral component using trochlear groove as guide, most patients obtained good patellofemoral congruence with pneumatic tourniquet inflated (n = 43) or deflated (n = 5), and good patellofemoral congruence was also obtained by lateral patellar retinaculum release in two patients. Conclusion: Despite the shifting of trochlear groove caused by severe knee osteoarthritis, trochlear groove can be used as a guide for position of femoral component, with equivalent patellar tracking compared with transepicondylar axis. [ABSTRACT FROM AUTHOR]

With the wide use of small animals for biomedical studies, in vivo small-animal whole-body imaging plays an increasingly important role. Photoacoustic tomography (PAT) is an emerging whole-body imaging modality that shows great potential for preclinical research. As a hybrid technique, PAT is based on the acoustic detection of optical absorption from either endogenous tissue chromophores, such as oxyhemoglobin and deoxyhemoglobin, or exogenous contrast agents. Because ultrasound scatters much less than light in tissue, PAT generates high-resolution images in both the optical ballistic and diffusive regimes. Using near-infrared light, which has relatively low blood absorption, PAT can image through the whole body of small animals with acoustically defined spatial resolution. Anatomical and vascular structures are imaged with endogenous hemoglobin contrast, while functional and molecular images are enabled by the wide choice of exogenous optical contrasts. This paper reviews the rapidly growing field of small-animal whole-body PAT and highlights studies done in the past decade. [ABSTRACT FROM PUBLISHER]

The world is currently experiencing an ongoing pandemic of an infectious disease named coronavirus disease 2019 (i.e., COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Computed Tomography (CT) plays an important role in assessing the severity of the infection and can also be used to identify those symptomatic and asymptomatic COVID-19 carriers. With a surge of the cumulative number of COVID-19 patients, radiologists are increasingly stressed to examine the CT scans manually. Therefore, an automated 3D CT scan recognition tool is highly in demand since the manual analysis is time-consuming for radiologists and their fatigue can cause possible misjudgment. However, due to various technical specifications of CT scanners located in different hospitals, the appearance of CT images can be significantly different leading to the failure of many automated image recognition approaches. The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis. In this paper, we proposed a COVID-19 CT scan recognition model namely coronavirus information fusion and diagnosis network (CIFD-Net) that can efficiently handle the multi-domain shift problem via a new robust weakly supervised learning paradigm. Our model can resolve the problem of different appearance in CT scan images reliably and efficiently while attaining higher accuracy compared to other state-of-the-art methods. • We proposed a weakly supervised learning framework for automated COVID-19 diagnosis. • We propose a novel noisy label correction that propagates patient-level predictions. • We develop a slice aggregation module to alleviate the data distribution shift. [ABSTRACT FROM AUTHOR]

Significance: Coherence, a fundamental property of waves and fields, plays a key role in photoacoustic image reconstruction. Previously, techniques such as short-lag spatial coherence (SLSC) and filtered delay, multiply, and sum (FDMAS) have utilized spatial coherence to improve the reconstructed resolution and contrast with respect to delay-and-sum (DAS). While SLSC uses spatial coherence directly as the imaging contrast, FDMAS employs spatial coherence implicitly. Despite being more robust against noise, both techniques have their own drawbacks: SLSC does not preserve a relative signal magnitude, and FDMAS shows a reduced contrast-to-noise ratio. Aim: To overcome these limitations, our aim is to develop a beamforming algorithm—generalized spatial coherence (GSC)—that unifies SLSC and FDMAS into a single equation and outperforms both beamformers. Approach: We demonstrated the application of GSC in photoacoustic computed tomography (PACT) through simulation and experiments and compared it to previous beamformers: DAS, FDMAS, and SLSC. Results: GSC outperforms the imaging metrics of previous state-of-the-art coherence-based beamformers in both simulation and experiments. Conclusions: GSC is an innovative reconstruction algorithm for PACT, which combines the strengths of FDMAS and SLSC expanding PACT's applications. [ABSTRACT FROM AUTHOR]

• Tibial plateau fractures(TPF) are a common type of fracture. • Accurate Schatzker classification is important in TPF patients. • CT imaging has higher accuracy than standard X-ray imaging. • It may be possible to apply deep learning to CT images of TPF. • Deep learning can assist junior doctors with Schatzker classification. This study aimed to automatically segment knee computed tomography (CT) images of tibial plateau fractures using a three-dimensional (3D) U-net-based method, accurately construct 3D maps of tibial plateau fractures, and examine their usefulness for Schatzker classification in clinical practice. We retrospectively enrolled 234 cases with tibial plateau fractures from our hospital in this study. The four constituent bones of the knee were manually annotated using ITK-SNAP software. Finally, image features were extracted using deep learning. The usefulness of the results for Schatzker classification was examined by an orthopaedic and a radiology resident. On average, our model required < 40 s to process a 3D CT scan of the knee. The average Dice coefficient for all four knee bones was higher than 0.950, and highly accurate 3D maps of the tibia were produced. With the aid of the results of our model, the accuracy, sensitivity, and specificity of the Schatzker classification of both residents improved. The proposed method can rapidly and accurately segment knee CT images of tibial plateau fractures and assist residents with Schatzker classification, which can help improve diagnostic efficiency and reduce the workload of junior doctors in clinical practice. [ABSTRACT FROM AUTHOR]

This study retrospectively included some patients with colorectal cancer diagnosed by histopathology, to explore the feasibility of CT medical image texture analysis in predicting KRAS gene mutations in patients with colorectal cancer. Before any surgical procedure, all patients received an enhanced CT scan of the abdomen and pelvis, as well as genetic testing. To define patient groups, divide all patients into test and validation sets based on the order of patient enrollment. A radiologist took a look at the plain axial CT image of the tumor, as well as the portal vein CT image, at the corresponding level. The physician points the computer's cursor to the relevant area in the image, and TexRAD software programs together texture parameters based on various spatial scale factors, also known as total mean, total variance, statistical entropy, overall total average, mean total, positive mean, skewness value, kurtosis value, and general skewness. Using the same method again two weeks later, the observer and another physician measured the image of each patient again to see if the method was consistent between observers. With regard to clinical information, the KRAS gene mutation group and the wild group of participants in the test set and validation set each had values for the texture parameter. In a study of patients with colorectal cancer, the results demonstrated that CT texture parameters were correlated with the presence of the KRAS gene mutation. The best CT prediction model includes the values of the medium texture image's slope and the other CT fine texture image's value of entropy, the medium texture image's slope and kurtosis, and the medium texture image's mean and the other CT fine texture image's value of entropy. Regardless of the training set or the validation set, patients with and without KRAS gene mutations did not differ significantly in clinical characteristics. This method can be used to identify mutations in the KRAS gene in patients with colorectal cancer, making it practical to implement CT medical image texture analysis technology for that purpose. [ABSTRACT FROM AUTHOR]

Photoacoustic computed tomography (PACT) is an emerging imaging modality. While many contrast agents have been developed for PACT, these typically cannot immediately be used in humans due to the lengthy regulatory process. We screened two hundred types of ingestible foodstuff samples for photoacoustic contrast with 1064 nm pulse laser excitation, and identified roasted barley as a promising candidate. Twenty brands of roasted barley were further screened to identify the one with the strongest contrast, presumably based on complex chemical modifications incurred during the roasting process. Individual roasted barley particles could be detected through 3.5 cm of chicken-breast tissue and through the whole hand of healthy human volunteers. With PACT, but not ultrasound imaging, a single grain of roasted barley was detected in a field of hundreds of non-roasted particles. Upon oral administration, roasted barley enabled imaging of the gut and peristalsis in mice. Prepared roasted barley tea could be detected through 2.5 cm chicken breast tissue. When barley tea was administered to humans, photoacoustic imaging visualized swallowing dynamics in healthy volunteers. Thus, roasted barley represents an edible foodstuff that should be considered for photoacoustic contrast imaging of swallowing and gut processes, with immediate potential for clinical translation. [ABSTRACT FROM AUTHOR]

• Tree-structured convolutional gated recurrent unit (ConvGRU) is proposed to explicitly model the topological structure of the coronary artery. • An end-to-end deep learning-based framework is presented to accurately segment coronary arteries from 3D CCTA data. • Four large-scale CCTA datasets are employed to extensively evaluate the performance of the proposed framework. Extensive research has been devoted to the segmentation of the coronary artery. However, owing to its complex anatomical structure, it is extremely challenging to automatically segment the coronary artery from 3D coronary computed tomography angiography (CCTA). Inspired by recent ideas to use tree-structured long short-term memory (LSTM) to model the underlying tree structures for NLP tasks, we propose a novel tree-structured convolutional gated recurrent unit (ConvGRU) model to learn the anatomical structure of the coronary artery. However, unlike tree-structured LSTM proposed for semantic relatedness as well as sentiment classification in natural language processing, our tree-structured ConvGRU model considers the local spatial correlations in the input data as the convolutions are used for input-to-state as well as state-to-state transitions, thus more suitable for image analysis. To conduct voxel-wise segmentation, a tree-structured segmentation framework is presented. It consists of a fully convolutional network (FCN) for multi-scale discriminative feature extraction and the final prediction, and a tree-structured ConvGRU layer for anatomical structure modeling. The proposed framework is extensively evaluated on four large-scale 3D CCTA dataset (the largest to the best of our knowledge), and experiments show that our method is more accurate as well as efficient, compared with other coronary artery segmentation approaches. [ABSTRACT FROM AUTHOR]