Imaging Score Research Articles

Blind Quality Assessment of Images Containing Objects of Interest.

To monitor objects of interest, such as wildlife and people, image-capturing devices are used to collect a large number of images with and without objects of interest. As we are recording valuable information about the behavior and activity of objects, the quality of images containing objects of interest should be better than that of images without objects of interest, even if the former exhibits more severe distortion than the latter. However, according to current methods, quality assessments produce the opposite results. In this study, we propose an end-to-end model, named DETR-IQA (detection transformer image quality assessment), which extends the capability to perform object detection and blind image quality assessment (IQA) simultaneously by adding IQA heads comprising simple multi-layer perceptrons at the top of the DETRs (detection transformers) decoder. Using IQA heads, DETR-IQA carried out blind IQAs based on the weighted fusion of the distortion degree of the region of objects of interest and the other regions of the image; the predicted quality score of images containing objects of interest was generally greater than that of images without objects of interest. Currently, the subjective quality score of all public datasets is in accordance with the distortion of images and does not consider objects of interest. We manually extracted the images in which the five predefined classes of objects were the main contents of the largest authentic distortion dataset, KonIQ-10k, which was used as the experimental dataset. The experimental results show that with slight degradation in object detection performance and simple IQA heads, the values of PLCC and SRCC were 0.785 and 0.727, respectively, and exceeded those of some deep learning-based IQA models that are specially designed for only performing IQA. With the negligible increase in the computation and complexity of object detection and without a decrease in inference speeds, DETR-IQA can perform object detection and IQA via multi-tasking and substantially reduce the workload.

Mode of Imaging Study and Endovascular Therapy for a Large Ischemic Core: Insights From the RESCUE-Japan LIMIT.

Differences in measurement of the extent of acute ischemic stroke using the Alberta Stroke Program Early Computed Tomographic Score (ASPECTS) by non-contrast computed tomography (CT-ASPECTS stratum) and diffusion-weighted imaging (DWI-ASPECTS stratum) may impact the efficacy of endovascular therapy (EVT) in patients with a large ischemic core. The RESCUE-Japan LIMIT (Recovery by Endovascular Salvage for Cerebral Ultra-acute Embolism Japan-Large IscheMIc core Trial) was a multicenter, open-label, randomized clinical trial that evaluated the efficacy and safety of EVT in patients with ASPECTS of 3-5. CT-ASPECTS was prioritized when both CT-ASPECTS and DWI-ASPECTS were measured. The effects of EVT on the modified Rankin Scale (mRS) score at 90 days were assessed separately for each stratum. Among 183 patients, 112 (EVT group, 53; No-EVT group, 59) were in the CT-ASPECTS stratum and 71 (EVT group, 40; No-EVT group, 31) in the DWI-ASPECTS stratum. The common odds ratio (OR) (95% confidence interval) of the EVT group for one scale shift of the mRS score toward 0 was 1.29 (0.65-2.54) compared to the No-EVT group in CT-ASPECTS stratum, and 6.15 (2.46-16.3) in DWI-ASPECTS stratum with significant interaction between treatment assignment and mode of imaging study (P=0.002). There were significant interactions in the improvement of the National Institutes of Health Stroke Scale score at 48 hours (CT-ASPECTS stratum: OR, 1.95; DWIASPECTS stratum: OR, 14.5; interaction P=0.035) and mortality at 90 days (CT-ASPECTS stratum: OR, 2.07; DWI-ASPECTS stratum: OR, 0.23; interaction P=0.008). Patients with ASPECTS of 3-5 on MRI benefitted more from EVT than those with ASPECTS of 3-5 on CT.

The impact of deep learning reconstruction in low dose computed tomography on the evaluation of interstitial lung disease.

To evaluate the effect of the deep learning model reconstruction (DLM) method in terms of image quality and diagnostic agreement in low-dose computed tomography (LDCT) for interstitial lung disease (ILD), 193 patients who underwent LDCT for suspected ILD were retrospectively reviewed. Datasets were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction Veo (ASiR-V), and DLM. For image quality analysis, the signal, noise, signal-to-noise ratio (SNR), blind/referenceless image spatial quality evaluator (BRISQUE), and visual scoring were evaluated. Also, CT patterns of usual interstitial pneumonia (UIP) were classified according to the 2022 idiopathic pulmonary fibrosis (IPF) diagnostic criteria. The differences between CT images subjected to FBP, ASiR-V 30%, and DLM were evaluated. The image noise and BRISQUE scores of DLM images was lower and SNR was higher than that of the ASiR-V and FBP images (ASiR-V vs. DLM, p < 0.001 and FBP vs. DLR-M, p < 0.001, respectively). The agreement of the diagnostic categorization of IPF between the three reconstruction methods was almost perfect (κ = 0.992, CI 0.990-0.994). Image quality was improved with DLM compared to ASiR-V and FBP.

Retrospective study on the modified Uhl technique of closed reduction and percutaneous pin in the treatment of Colles' fracture

To retrospectively assess the advantages of the modified Uhl technique in the treatment of Colles' fracture guided by the principles of Chinese osteosynthesis (CO) concept. A retrospective study was conducted on 358 patients with Colles' fracture treated with the modified Uhl technique of closed reduction and percutaneous pin between January 2016 and June 2021. Out of these, 120 eligible cases were selected and categorized into two groups according to different surgical methods:the closed reduction and percutaneous pin group, and the open reduction group. Sixty-eight patients in the closed reduction and percutaneous pin group were treated with the modified Uhl technique, while fifty-two patients in the open reduction group were treated with open reduction and internal fixation using plates. The modified Sarmiento imaging score, Gartland-Werley wrist score, operation time, hospital stay, and treatment costs between the two groups were compared at a 6-month postoperative follow-up. There were no significant differences in terms of gender, age, affected side, injure factors, time of injury to surgery, Sarmiento imaging score, and Gartland-Werley wrist joint score (P>0.05). The closed reduction and percutaneous pin group exhibited an operation time of (35.88±14.11) minutes, hospitalization stay of (9.78±2.48) days, and treatment costs of (16 074.91±1 964.48) yuan, while the open reduction group demonstrated comparatively longer operation time of (65.48±14.26) minutes, hospitalization stay of (15.88±2.00) days, and treatment costs of (20 451.27±1 760.22) yuan (P<0.01). The modified Uhl technique presents notable advantages in the management of Colles' fracture, including reliable fixation, less trauma, shorter operation time, less pain, shorter hospital stay, and cost-effectiveness. This technique exhibits promising potential for broader clinical application. However, it is important to note that the pin could potentially damage tendons, and in cases of Colles' fractures with osteoporosis and comminuted fragments, additional techniques may be required for reliable fixation.

Invention of automated numerical algorithm adopting binarization for the evaluation of scalp hair coverage: An image analysis providing a substitute for phototrichogram and global photography assessment for hair diseases

BackgroundThe efficacy of therapeutic modalities for hair disease can be evaluated globally by photo assessment and more precisely by phototrichogram (PTG). However, the latter procedure is laborious, time consuming, subject to inter-observer variation, and requires hair clipping. ObjectiveTo establish an automated and patient/investigator friendly methodology enabling quantitative hair amount evaluation for daily clinical practice. MethodsA novel automated numerical algorithm (aNA) adopting digital image binarization (i.e., black and white color conversion) was invented to evaluate hair coverage and measure PTG parameters in scalp images. Step-by-step improvement of aNA was attempted through comparative analyses of the data obtained respectively by the novel approach and conventional PTG/global photography assessment (GPA). ResultsFor measuring scalp hair coverage, the initial version of aNA generally agreed with the cumulative hair diameter as assessed using PTG, showing a coefficient of 0.60. However, these outcomes were influenced by the angle of hair near the parting line. By integrating an angle compensation formula, the standard deviation of aNA data decreased from 5.7% to 1.2%. Consequently, the coefficient of determination for hair coverage calculated using the modified aNA and cumulative hair diameter assessed by PTG increased to 0.90. Furthermore, the change in hair coverage as determined by the modified aNA protocol correlated well with changes in the GPA score of images obtained using clinical trials. ConclusionThe novel aNA method provides a valuable tool for enabling simple and accurate evaluation of hair growth and volume for clinical trials and for treatment of hair disease.

Magnetic resonance imaging analysis of the distribution of cartilage damage in scaphoid nonunion.

This study aimed to evaluate the distribution and severity of cartilage damage using magnetic resonance imaging in patients with scaphoid nonunion without advanced wrist arthritis. We retrospectively analysed MRI of patients who underwent osteosynthesis for scaphoid nonunion. Cartilage damage was assessed in eight wrist regions using a modified Whole-Organ Magnetic Resonance Imaging Score. The frequencies of regions affected by any cartilage damage (Score ≥2.5) depicted on MRI were analysed. The study included 32 patients (31 men and one woman), with a mean age of 32 years (SD 11). The distal radioscaphoid (29/32), scaphotrapeziotrapezoid (STT) (22/32), proximal radioscaphoid (14/32) and scaphocapitate (11/32) joints were most commonly affected by degenerative cartilage damage. The STT and proximal radioscaphoid joint were especially likely to be involved in early-stage scaphoid nonunion advanced collapse. We recommend that surgeons should investigate the cartilage status of these joints during decision-making for scaphoid nonunion surgery.Level of evidence: III.

Bone marrow fibrosis is associated with non-response to CD19 CAR T-cell therapy in B-acute lymphoblastic leukemia.

CD19 directed CAR T-cell therapy is used to treat relapsed/refractory B-cell acute lymphoblastic leukemia. The role of the pre-CAR bone marrow (BM) stromal microenvironment in determining response to CAR T-cell therapy has been understudied. We performed whole transcriptome analysis, reticulin fibrosis assessment and CD3 T-cell infiltration on BM core biopsies from pre- and post-CAR timepoints for 61 patients, as well as on a cohort of 54 primary B-ALL samples. Pathways of fibrosis, extracellular matrix development, and associated transcription factors AP1 and TGF-β3, were enriched and upregulated in nonresponders (NR) even prior to CAR T cell therapy. NR showed significantly higher levels of BM fibrosis compared to complete responders by both clinical reticulin assessment and AI-assisted digital image scoring. CD3+ T cells showed a trend toward lower infiltration in NR. NR had significantly higher levels of pre-CAR fibrosis compared to primary B-ALL. High levels of fibrosis were associated with lower overall survival after CAR T-cell therapy. In conclusion, BM fibrosis is a novel mechanism mediating nonresponse to CD19-directed CAR T-cell therapy in B-ALL. A widely used clinically assay for quantitating myelofibrosis can be repurposed to determine patients at high risk of non-response. Genes and pathways associated with BM fibrosis are a potential target to improve response.

Primary Endovascular Thrombectomy in Acute Ischemic Stroke in Patients Ineligible for Intravenous Thrombolysis

Endovascular treatment (EVT) of acute ischemic stroke (AIS) is the main treatment of large vessel occlusion (LVO). Nonetheless, access to EVT is limited specially in developing countries. It is not uncommon in these regions to miss the time window for intravenous thrombolysis (IVT) or to arrive within the IVT window but with a contraindication for it. Hence, a lot of patients with LVO face a situation where either they receive EVT only or conservative management according to available logistics.&#x0D; Aim: To study the outcome of EVT vs best medical treatment (BMT) in two Egyptian stroke centres (Tanta and Alexandria) in AIS patients ineligible for IVT.&#x0D; Results: 390 patients with AIS and LVO were included in the study. 74 underwent EVT while 316 underwent BMT. There were no statistical differences in age, sex, time of onset, initial severity, or imaging scores in both groups. The EVT group had more diabetes mellitus (DM) patients, more smokers and more systolic and diastolic blood pressure (BP) while the BMT had more anticoagulated patients. The EVT group had better functional outcome but more symptomatic intracerebral haemorrhage with no difference in mortality.&#x0D; Conclusion: Endovascular treatment doubles the good functional outcome of AIS in LVO patients but ICH is more with no effect on mortality.

Is a Novel Fluoroscopic Intraoperative Reference System Superior to Conventional Management for Distal Radius Fracture Reduction? A Propensity-matched Comparative Study.

Is a Novel Fluoroscopic Intraoperative Reference System Superior to Conventional Management for Distal Radius Fracture Reduction? A Propensity-matched Comparative Study.

Deep Transfer Learning-Based Approach for Glucose Transporter-1 (GLUT1) Expression Assessment

Glucose transporter-1 (GLUT-1) expression level is a biomarker of tumour hypoxia condition in immunohistochemistry (IHC)-stained images. Thus, the GLUT-1 scoring is a routine procedure currently employed for predicting tumour hypoxia markers in clinical practice. However, visual assessment of GLUT-1 scores is subjective and consequently prone to inter-pathologist variability. Therefore, this study proposes an automated method for assessing GLUT-1 scores in IHC colorectal carcinoma images. For this purpose, we leverage deep transfer learning methodologies for evaluating the performance of six different pre-trained convolutional neural network (CNN) architectures: AlexNet, VGG16, GoogleNet, ResNet50, DenseNet-201 and ShuffleNet. The target CNNs are fine-tuned as classifiers or adapted as feature extractors with support vector machine (SVM) to classify GLUT-1 scores in IHC images. Our experimental results show that the winning model is the trained SVM classifier on the extracted deep features fusion Feat-Concat from DenseNet201, ResNet50 and GoogLeNet extractors. It yields the highest prediction accuracy of 98.86%, thus outperforming the other classifiers on our dataset. We also conclude, from comparing the methodologies, that the off-the-shelf feature extraction is better than the fine-tuning model in terms of time and resources required for training.

Dynamic cardiac MRI with high spatiotemporal resolution using accelerated spiral-out and spiral-in/out bSSFP pulse sequences at 1.5 T

ObjectiveTo develop two spiral-based bSSFP pulse sequences combined with L + S reconstruction for accelerated ungated, free-breathing dynamic cardiac imaging at 1.5 T.Materials and methodsTiny golden angle rotated spiral-out and spiral-in/out bSSFP sequences combined with view-sharing (VS), compressed sensing (CS), and low-rank plus sparse (L + S) reconstruction were evaluated and compared via simulation and in vivo dynamic cardiac imaging studies. The proposed methods were then validated against the standard cine, in terms of quantitative image assessment and qualitative quality rating.ResultsThe L + S method yielded the least residual artifacts and the best image sharpness among the three methods. Both spiral cine techniques showed clinically diagnostic images (score > 3). Compared to standard cine, there were significant differences in global image quality and edge sharpness for spiral cine techniques, while there was significant difference in image contrast for the spiral-out cine but no significant difference for the spiral-in/out cine. There was good agreement in left ventricular ejection fraction for both the spiral-out cine (− 1.6 pm 3.1%) and spiral-in/out cine (− 1.5 pm 2.8%) against standard cine.DiscussionCompared to the time-consuming standard cine (~ 5 min) which requires ECG-gating and breath-holds, the proposed spiral bSSFP sequences achieved ungated, free-breathing cardiac movies at a similar spatial (1.5 × 1.5 × 8 mm3) and temporal resolution (36 ms) per slice for whole heart coverage (10–15 slices) within 45 s, suggesting the clinical potential for improved patient comfort or for imaging patients with arrhythmias or who cannot hold their breath.

Hybridizing machine learning in survival analysis of cardiac PET/CT imaging

BackgroundMachine Learning (ML) allows integration of the numerous variables delivered by cardiac PET/CT, while traditional survival analysis can provide explainable prognostic estimates from a restricted number of input variables. We implemented a hybrid ML-and-survival analysis of multimodal PET/CT data to identify patients who developed myocardial infarction (MI) or death in long-term follow up.MethodsData from 739 intermediate risk patients who underwent coronary CT and selectively stress 15O-water-PET perfusion were analyzed for the occurrence of MI and all-cause mortality. Images were evaluated segmentally for atherosclerosis and absolute myocardial perfusion through 75 variables that were integrated through ML into an ML-CCTA and an ML-PET score. These scores were then modeled along with clinical variables through Cox regression. This hybridized model was compared against an expert interpretation-based and a calcium score-based model.ResultsCompared with expert- and calcium score-based models, the hybridized ML-survival model showed the highest performance (CI .81 vs .71 and .64). The strongest predictor for outcomes was the ML-CCTA score.ConclusionPrognostic modeling of PET/CT data for the long-term occurrence of adverse events may be improved through ML imaging score integration and subsequent traditional survival analysis with clinical variables. This hybridization of methods offers an alternative to traditional survival modeling of conventional expert image scoring and interpretation.

Correlating Quantitative MRI-based Apparent Diffusion Coefficient Metrics with 24-month Neurodevelopmental Outcomes in Neonates from the HEAL Trial.

Background Multiple qualitative scoring systems have been created to capture the imaging severity of hypoxic ischemic brain injury. Purpose To evaluate quantitative volumes of acute brain injury at MRI in neonates with hypoxic ischemic brain injury and correlate these findings with 24-month neurodevelopmental outcomes and qualitative brain injury scoring by radiologists. Materials and Methods In this secondary analysis, brain diffusion-weighted MRI data from neonates in the High-dose Erythropoietin for Asphyxia and Encephalopathy trial, which recruited participants between January 2017 and October 2019, were analyzed. Volume of acute brain injury, defined as brain with apparent diffusion coefficient (ADC) less than 800 × 10-6 mm2/sec, was automatically computed across the whole brain and within the thalami and white matter. Outcomes of death and neurodevelopmental impairment (NDI) were recorded at 24-month follow-up. Associations between the presence and volume (in milliliters) of acute brain injury with 24-month outcomes were evaluated using multiple logistic regression. The correlation between quantitative acute brain injury volume and qualitative MRI scores was assessed using the Kendall tau-b test. Results A total of 416 neonates had available MRI data (mean gestational age, 39.1 weeks ± 1.4 [SD]; 235 male) and 113 (27%) showed evidence of acute brain injury at MRI. Of the 387 participants with 24-month follow-up data, 185 (48%) died or had any NDI. Volume of acute injury greater than 1 mL (odds ratio [OR], 13.9 [95% CI: 5.93, 32.45]; P < .001) and presence of any acute injury in the brain (OR, 4.5 [95% CI: 2.6, 7.8]; P < .001) were associated with increased odds of death or any NDI. Quantitative whole-brain acute injury volume was strongly associated with radiologists' qualitative scoring of diffusion-weighted images (Kendall tau-b = 0.56; P < .001). Conclusion Automated quantitative volume of brain injury is associated with death, moderate to severe NDI, and cerebral palsy in neonates with hypoxic ischemic encephalopathy and correlated well with qualitative MRI scoring of acute brain injury. Clinical trial registration no. NCT02811263 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Huisman in this issue.

Phenylketonuria: A Scoring System for Brain Magnetic Resonance Imaging.

The purpose of our study was to devise a new brain Magnetic Resonance Imaging (MRI) scoring system based on the Loes and modified Loes scores in phenylketonuria (PKU) patients. The brain MRI scans of patients with late diagnosed PKU were evalu- ated retrospectively. Patients' age at diagnosis, age at which diet started, age at MRI, and, blood phenylalanine (Phe) levels at the time point closest to the MRI were recorded. Eleven patients aged from 3 to 28 years were included in the study. The median MRI involvement score was 17 (interquartile range = 3). The most involved white matter areas were the parietooccipital areas. There was a significant (P = .046) correlation between the blood Phe level at the timepoint closest to the imaging and the MRI involvement score. Our study provides insights into the MRI findings and scoring system in PKU patients. We have developed a scoring system based on the widely used Loes and modified Loes scoring systems that can be implemented in clinical practice. Also, our study contributes to the long-forgotten and largely abandoned area-imaging findings in late diagnosed and untreated PKU patients and set the stage for the future research in this field.

The CADA-MRIT: An MRI Inventory Tool for Evaluating Cerebral Lesions in CADASIL Across Cohorts.

Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) is the most frequent genetic cerebrovascular disease. The clinical aspects of the disease in relation to the various types of lesions on MRI vary widely not only within families but also between different cohorts reported worldwide. Many limitations prevent comparison of imaging data obtained with different scanners and sequences in different patient cohorts. We aimed to develop and validate a simple tool to inventory quickly the key MRI features in CADASIL to compare imaging data across different populations. The Inventory Tool (CADA-MRIT) was designed by consensus after repeated expert meetings. It consists of 11 imaging items to assess periventricular, deep, and superficial white matter hyperintensity (WMH), lacunes, cerebral microbleeds (CMB), centrum semiovale and basal ganglia dilated perivascular spaces (dPVS), superficial and deep atrophy, large infarcts, and macrobleeds. The reliability, clinical relevance, and time-effectiveness of CADA-MRIT were assessed using data from 3 independent patient cohorts. Imaging data from 671 patients with CADASIL (440 from France, 119 from Germany, and 112 from Taiwan) were analyzed. Their mean age was 53.4 ± 12.2 years, 54.5% were women, 56.2% had stroke, and 31.1% had migraine with aura. Any lacune was present in at least 70% of individuals, whereas CMB occurred in 83% of patients from the Asian cohort and in only 35% of European patients. CADA-MRIT scores obtained for WMH, CMB, and dPVS were comparable regardless of the scanner or sequence used (weighted κ > 0.60). Intrarater and interrater agreements were from good to very good (weighted κ > 0.60). Global WMH and atrophy scores correlated strongly with accurate volumetric quantification of WMH or brain parenchymal fraction (Pearson r > 0.60). Different imaging scores were significantly associated with the main clinical manifestations of the disease. The time for evaluating 1 patient was approximately 2-3 minutes. The CADA-MRIT is an easy-to-use tool for analyzing and comparing the most frequent MRI lesions of CADASIL across different populations. This instrument is reliable. It can be used with different imaging sequences or scanners. It also provides clinically relevant scores in a very short time for completion.

Impact of steroid and lidocaine injection in the sacroiliac joint in axial spondyloarthritis patients: a randomized controlled trial

Background: The value of steroid and lidocaine injection of the sacroiliac joint in axial spondyloarthritis patients on magnetic resonance imaging scores and clinical disease outcome measures is not yet well assessed.&#x0D; Patient and methods: Participants were randomly assigned into two groups; Group I received unilateral ultrasound-guided sacroiliac joint injection with .5% lidocaine hydrochloride mixed with triamcinolone. At the same time, group II received subcutaneous saline injection. All participants fulfilled the ASAS criteria for axial SpA and all had bone marrow edema of at least one sacroiliac joint at baseline. Outcomes measures were: Visual Analogue Scale (VAS), Ankylosing Spondylitis Disease Activity Score (ASDAS), Bath Ankylosing Spondylitis Functional Index (BASFI), and Spondyloarthritis Research Consortium of Canada (SPARCC) scores. Participants were assessed at baseline (before and after sacroiliac joint injection) and after three months. This clinical trial was registered on clinicaltrials.gov under the number NCT04895228.&#x0D; Results: In this study, a total of 61 participants were registered. There was a significant difference between both groups regarding pain, spine mobility, SPARCC, and ASDAS scores in favor of group I. Spine mobility showed the earliest improvement, followed by pain whilst SPARCC, and ASDAS scores showed improvement after three months. Higher disease activity, younger age, and shorter disease duration were all associated with better outcomes. Bilateral hip involvement was a predictor of poor response.&#x0D; Conclusion: Sacroiliac joint injection of lidocaine and triamcinolone in axial SpA patients is a cost-effective and practical technique for controlling pain, improving function, disease activity scores, and bone marrow edema with acceptable complications and relatively sustained effect.&#x0D;

Deep learning model with collage images for the segmentation of dedicated breast positron emission tomography images.

Dedicated breast positron emission tomography (dbPET) has high contrast and resolution optimized for detecting small breast cancers, leading to its noisy characteristics. This study evaluated the application of deep learning to the automatic segmentation of abnormal uptakes on dbPET to facilitate the assessment of lesions. To address data scarcity in model training, we used collage images composed of cropped abnormal uptakes and normal breasts for data augmentation. This retrospective study included 1598 examinations between April 2015 and August 2020. A U-Net-based model with an uptake shape classification head was trained using either the original or augmented dataset comprising collage images. The Dice score, which measures the pixel-wise agreement between a prediction and its ground truth, of the models was compared using the Wilcoxon signed-rank test. Moreover, the classification accuracies were evaluated. After applying the exclusion criteria, 662 breasts were included; among these, 217 breasts had abnormal uptakes (mean age: 58 ± 14years). Abnormal uptakes on the cranio-caudal and mediolateral maximum intensity projection images of 217 breasts were annotated and labeled as focus, mass, or non-mass. The inclusion of collage images into the original dataset yielded a Dice score of 0.884 and classification accuracy of 91.5%. Improvement in the Dice score was observed across all subgroups, and the score of images without breast cancer improved significantly from 0.750 to 0.834 (effect size: 0.76, P = 0.02). Deep learning can be applied for the automatic segmentation of dbPET, and collage images can improve model performance.

A text image generation model based on deep learning

The traditional text-image confrontation model utilizes a convolutional network in the discriminator to extract image features, yet this fails to involve the spatial relationship between underlying objects, resulting in a poor-quality generated image. To remedy this, a capsule network is proposed to improve the model. The convolutional network in the discriminator is replaced with a capsule network, thereby improving the robustness of the images. Through experiments on the Oxford-102 and CUB datasets, it has been found that the new model can effectively improve the quality of generated text-image. The FID value of the generated flower image decreased by 14.49%, and the FID value of the generated bird image decreased by 9.64%. Additionally, the Inception Score of images generated on the Oxford-102 and CUB datasets increased by 22.60% and 26.28%, respectively, indicating that the improved model generated richer and more meaningful image features.

Evaluation of Radiation Exposure and Image Quality in Congenital Catheterization Laboratory; A Single Centre Comparative Study Using Different Acquisition Modes

Abstract Background The exposure to ionizing radiation delivered during the catheterization procedures has various negative biological effects to the patient, so concern has risen sharply about radiation hazards over the past decade.While angiography imaging system vendors have all made great strides with new technologies that reduce the amount of x-rays needed while maintaining excellent image quality, the procedures have become more complex, lasting longer and require more imaging than standard procedures. Aim of the Work To study the effect of lowering radiation dose by using a fluoro angiography on image quality in pediatric cardiac catheterization. Patients and Methods We studied 90 patients who underwent cardiac cath. for CHD at Ain Shams University hospital. Patients were randomized into three groups according to mode of acquisition used in procedure (fluro angiography only–cine angiography only–mixed). Radiation indices were measured, also image quality questionnaire was filled by operators after each procedure. Results statistically significant difference between three modalities of acquisition as regard the radiation indices (DAP, total air kemra, fluoroscopy time) with p value &amp;lt;0.005. While operators satisfaction with image was nearly the same in the three groups with median score 68.5 (p value 0.681). Conclusion Based on the results of the current study it can be concluded that: Mixed imaging acquisition had highest radiation exposure indices in comparison with other two acquisition modalities (fluro angiography only – cine angiography only), with statistically significant difference with fluro only mode (p value &amp;lt;0.005), and no statistically significant deference with cine only mode. Complexity of the procedures &amp; increased the cath. lab machine imaging protocol to 30 fps and repeat the same injection in the cine mode after fluro mode were the most important factors that made mixed acquisition had the highest radiation indices and exposure. Image quality and operators satisfaction were nearly the same in three acquisition modes (fluro-cine-mixed) with median image score 68.5 (p value 0.681), in expense of more radiation exposure in mixed mode. Increase operators awareness to radiation and continuous monitoring of radiation exposure with application of ALARA principles is important to reduce radiation exposure.

Quantification of Synovial Fluid Using Magnetic Resonance Fingerprinting Multicomponent Imaging in the Articular Cartilage of the Knee

The purpose of this study was to verify the feasibility of magnetic resonance fingerprinting (MRF)-derived synovial fluid fraction (SFF) mapping for quantifying subvoxel-sized cartilage defects. MRF was performed on a 3-Tesla scanner and used to derive T2 and SFF maps. An ex vivo experiment was performed using bovine bone; different numbers of holes (4, 6, 8, 10, and 12) were drilled separately on the articular surface, and SFF values were compared among the drilled areas. In a clinical study, 16 osteoarthritis patients underwent sagittal 3D fast spinecho (FSE) and MRF scanning, and knee cartilage segmentation was performed on each image. For morphologic analysis, fluid-excluded images of the SFF (FEISFF) and T2 maps (FEIT2) were generated using the cartilage segmentations, and the whole-organ magnetic resonance imaging score (WORMS) of each FEI and 3D FSE image were compared using the kappa coefficient. For quantitative analysis, intact cartilage volumes in the SFF (VSFF) and T2 maps (VT2) were calculated, and their correlations with reference to the actual cartilage volume on 3D FSE images (V3D) were evaluated. In the ex vivo experiment, the SFF value increased as the number of holes increased. The kappa coefficients of the WORMS were 0.80 and 0.64 in the SFF and T2 maps, respectively, and substantial to almost perfect agreement was observed in the medial tibiofemoral joint. The V3D-VSFF and V3D-VT2 correlation coefficients differed by 0.03 or more in the medial tibiofemoral joint. The MRF-derived SFF map can feasibly evaluate small, invisible cartilage defects and quantify cartilage volumes.