Non-contrast CT Images Research Articles

Correlation Between Intranodular Vessels and Tumor Invasiveness of Lung Adenocarcinoma Presenting as Ground-glass Nodules: A Deep Learning 3-Dimensional Reconstruction Algorithm-based Quantitative Analysis on Noncontrast Computed Tomography Images.

To evaluate the role of quantitative features of intranodular vessels based on deep learning in distinguishing pulmonary adenocarcinoma invasiveness. This retrospective study included 512 confirmed ground-glass nodules from 474 patients with 241 precursor glandular lesions (PGL), 126 minimally invasive adenocarcinomas (MIA), and 145 invasive adenocarcinomas (IAC). The pulmonary blood vessels were reconstructed on noncontrast computed tomography images using deep learning-based region-segmentation and region-growing techniques. The presence of intranodular vessels was evaluated based on the automatic calculation of vessel prevalence, vascular categories, and vessel volume percentage. Further comparisons were made between different invasive groups by the Mantel-Haenszel χ 2 test, χ 2 test, and analysis of variance. The detection rate of intranodular vessels in PGL (33.2%) was significantly lower than that of MIA (46.8%, P = 0.011) and IAC (55.2%, P < 0.001), while the vascular categories were similar (all P > 0.05). Vascular changes were more common in IAC and MIA than in PGL, mainly in increased vessel volume percentage (12.4 ± 19.0% vs. 6.3 ± 13.1% vs. 3.9 ± 9.4%, P < 0.001). The average intranodular artery and vein volume percentage of IAC (7.5 ± 14.0% and 5.0 ± 10.1%) was higher than that of PGL (2.1 ± 6.9% and 1.7 ± 5.8%) and MIA (3.2 ± 9.1% and 3.1 ± 8.7%), with statistical significance (all P < 0.05). The quantitative analysis of intranodular vessels on noncontrast computed tomography images demonstrated that the ground-glass nodules with increased internal vessel prevalence and volume percentages had higher possibility of tumor invasiveness.

Impact of a novel whole-heart motion-correction algorithm on non-contrast cardiac CT images and coronary artery calcium scores

Impact of a novel whole-heart motion-correction algorithm on non-contrast cardiac CT images and coronary artery calcium scores

Practices and utility of imaging among urological communities for urolithiasis, observations, and inferences from a targeted survey.

To evaluate the general practice among urologists about the use of various radiological imaging and measurement tools, and to compare the different preferences in radiological evaluations between Turkish and European urologists. Our study was designed as a survey study. The survey comprised 22 questions which evaluated the epidemiological information, caseload of participants, general preferences of participants on CT image slice thickness, basic radiologic workup routines prior to surgery, use of special tools and measurements on CT. Data collection was conducted with both an online poll and printed copies. A total of 222 urologists from 23 different countries responded to the survey. The most performed endourologic surgery was semi-rigid URS which was performed more than 25 times/year by 90.1% (n = 200) of the participants. Although PCNL was performed more commonly by Turkish urologists (39.7%) compared to their European (17.3%) colleagues (p < 0.001), it was still the least often performed endourological surgery among all participants (31.5%). The stone size evaluation was the most performed measurement performed by the participants. Although the group of surgeons used size measurement tools, there were differences between the two groups. Turkish urologists used size measurement before PCNL (85.7%) as opposed to European urologists who used it mostly before URS (91.4%). Non-contrast CT images for urolithiasis are mainly evaluated by urologists themselves and a considerable number of urologists do not use additional measurement tools in evaluating CT images. Although there are similarities in the knowledge of various radiological tools, there are distinct regional differences.

Spatial Attention-Guided Generative Adversarial Network for Synthesizing Contrast-enhanced Computed Tomography Images.

Compared to non-contrast computed tomography (NC-CT) scans, contrast-enhanced (CE) CT scans provide more abundant information about focal liver lesions (FLLs), which play a crucial role in the FLLs diagnosis. However, CE-CT scans require patient to inject contrast agent into the body, which increase the physical and economic burden of the patient. In this paper, we propose a spatial attention-guided generative adversarial network (SAG-GAN), which can directly obtain corresponding CE-CT images from the patient's NC-CT images. In the SAG-GAN, we devise a spatial attention-guided generator, which utilize a lightweight spatial attention module to highlight synthesis task-related areas in NC-CT image and neglect unrelated areas. To assess the performance of our approach, we test it on two tasks: synthesizing CE-CT images in arterial phase and portal venous phase. Both qualitative and quantitative results demonstrate that SAG-GAN is superior to existing GANs-based image synthesis methods.

Combining convolutional attention mechanism and residual deformable Transformer for infarct segmentation from CT scans of acute ischemic stroke patients.

Segmentation and evaluation of infarcts on medical images are essential for diagnosis and prognosis of acute ischemic stroke (AIS). Computed tomography (CT) is the first-choice examination for patients with AIS. To accurately segment infarcts from the CT images of patients with AIS, we proposed an automated segmentation method combining the convolutional attention mechanism and residual Deformable Transformer in this article. The method used the encoder-decoder structure, where the encoders were employed for downsampling to obtain the feature of the images and the decoder was used for upsampling and segmentation. In addition, we further applied the convolutional attention mechanism and residual network structure to improve the effectiveness of feature extraction. Our code is available at: https://github.com/XZhiXiang/AIS-segmentation/tree/master. The proposed method was assessed on a public dataset containing 397 non-contrast CT (NCCT) images of AIS patients (AISD dataset). The symptom onset to CT time was less than 24 h. The experimental results illustrate that this work had a Dice coefficient (DC) of 58.66% for AIS infarct segmentation, which outperforms several existing methods. Furthermore, volumetric analysis of infarcts indicated a strong correlation (Pearson correlation coefficient = 0.948) between the AIS infarct volume obtained by the proposed method and manual segmentation. The strong correlation between the infarct segmentation obtained via our method and the ground truth allows us to conclude that our method could accurately segment infarcts from NCCT images.

Epicardial adipose tissue volume, plaque vulnerability and myocardial ischemia in non-obstructive coronary artery disease

BackgroundEpicardial adipose tissue (EAT) accumulation has been associated with inflammation, atherosclerosis and microvascular dysfunction. Whether increased EAT volume is associated with coronary plaque vulnerability and demand myocardial ischemia in patients with non-obstructive coronary artery disease (CAD) is less explored. MethodsIn 125 patients (median age 63[58, 69] years and 58% women) with chest pain and non-obstructive CAD, EAT volume was quantified on non-contrast cardiac CT images. EAT volume in the highest tertile (>125 ml) was defined as high EAT volume. Total coronary plaque volume and plaque vulnerability were quantified by coronary CT angiography (CCTA). Demand myocardial ischemia was detected by contrast dobutamine stress echocardiography. ResultsHigh EAT volume was more common in men and associated with higher BMI, hypertension, increased left ventricular mass index (LVMi), C-reactive protein (CRP) and positive remodelling (all p < 0.05). There was no difference in age, coronary calcium score, total and non-calcified plaque volume or presence of demand myocardial ischemia between groups (all p ≥ 0.34). In a multivariable model, obesity (p = 0.006), hypertension (p = 0.007) and LVMi (p = 0.016) were independently associated with high EAT volume. Including plaque vulnerability in an alternative model, positive remodelling (p = 0.038) was independently associated with high EAT volume. ConclusionIn non-obstructive CAD, high EAT volume was associated with cardiometabolic risk factors, inflammation and plaque vulnerability, while there was no association with demand myocardial ischemia or coronary plaque volume. Following our results, the role of EAT volume as a biomarker in non-obstructive CAD remains unclear.

Greater Severity of Steatosis Is Associated with a Higher Risk of Incident Diabetes: A Retrospective Longitudinal Study.

Fatty liver is associated with increased risk of developing type 2 diabetes. We aimed to evaluate whether the severity of hepatic steatosis is associated with incident diabetes. We conducted a longitudinal analysis using data from 1,798 participants who underwent a comprehensive health checkup and abdominal computed tomography (CT). We assessed the association between baseline liver attenuation value on non-contrast CT images and risk of incident diabetes. All the participants were categorized into three groups based on the baseline liver attenuation value on non-contrast CT images: without hepatic steatosis (>57 Hounsfield unit [HU]), mild hepatic steatosis (41-57 HU), and moderate to severe hepatic steatosis (≤40 HU). During a median follow-up period of 5 years, 6.0% of the study participants progressed to diabetes. The incidence of diabetes was 17.3% in the moderate to severe hepatic steatosis group, 9.0% in the mild steatosis group, and 2.9% in those without hepatic steatosis. In a multivariate adjustment model, as compared with participants without hepatic steatosis, those with moderate to severe steatosis had a hazard ratio (HR) of 3.24 (95% confidence interval [CI], 1.64 to 4.2) for the development of diabetes, and those in the mild steatosis group had a HR of 2.33 (95% CI, 1.42 to 3.80). One standard deviation decrease in mean CT attenuation values of the liver was associated with a 40% increase in the development of diabetes (multivariate adjusted HR, 1.40; 95% CI, 1.2 to 1.63). We found a positive association between severity of hepatic steatosis and risk of incident diabetes. Greater severity of steatosis was associated with a higher risk of incident diabetes.

Non-contrast CT radiomics and machine learning for outcomes prediction of patients with acute ischemic stroke receiving conventional treatment

PurposeAccurate prediction of outcomes for patients with acute ischemic stroke (AIS) is crucial for clinical decision-making. In this study, we developed prediction models based on non-contrast computed tomography (NCCT) radiomics and clinical features to predict the modified Rankin Scale (mRS) six months after hospital discharge. MethodA two-center retrospective cohort of 240 AIS patients receiving conventional treatment was included. Radiomics features of the infarct area were extracted from baseline NCCT scans. We applied Kruskal-Wallis (KW) test and recursive feature elimination (RFE) to select features for developing clinical, radiomics, and fusion models (with clinical data and radiomics features), using support vector machine (SVM) algorithm. The prediction performance of the models was assessed by accuracy, sensitivity, specificity, F1 score, and receiver operating characteristic (ROC) curve. Shapley Additive exPlanations (SHAP) was applied to analyze the interpretability and predictor importance of the model. ResultsA total of 1454 texture features were extracted from the NCCT images. In the test cohort, the ROC analysis showed that the radiomics model and the fusion model showed AUCs of 0.705 and 0.857, which outperformed the clinical model (0.643), with the fusion model exhibiting the best performance. Additionally, the accuracy and sensitivity of the fusion model were also the best among the models (84.8% and 93.8%, respectively). ConclusionsThe model based on NCCT radiomics and machine learning has high predictive efficiency for the prognosis of AIS patients receiving conventional treatment, which can be used to assist early personalized clinical therapy.

Pure uric acid stone prediction model using the variant coefficient of stone density measured by thresholding 3D segmentation-based methods: A multicenter study

Urinary stones are common urological diseases with increasing prevalence and incidence worldwide. Among the various types of stones, uric acid stones can be dissolved by oral chemolysis without any surgical procedure. Therefore, our study demonstrates that variant coefficient of stone density measured by thresholding a three-dimensional segmentation-based method from noncontrast computed tomography images can be used to identify pure uric acid stones from non-pure uric acid stones. This study provides a preoperative pure uric acid stone prediction model that could reduce invasive procedural treatments. The pure uric acid stone prediction model may offer optimized clinical decision-making for patients with urinary stones. Background and objectivesWhile most urinary stones are managed with interventional therapy, uric acid (UA) stones can be dissolved by oral chemolysis without invasive procedures. This study aimed to develop and validate a pure UA (pUA) stone prediction model using a variant coefficient of stone density (VCSD) measured by thresholding a three-dimensional (3D) segmentation-based method. MethodsPatients with urolithiasis treated at Keimyung University Dongsan Hospital between January 2017 and December 2020 were divided into training and internal validation sets, and patients from Kyungpook National University Hospital between January 2017 and December 2018 were used as an external validation set. Each stone was segmented by a thresholding 3D segmentation-based method using an attenuation threshold of 130 Hounsfield units. VCSD was calculated as the stone heterogeneity index divided by the mean stone density. ResultsA total of 1175 urinary stone cases in 1023 patients were enrolled in this study. Of these, 224 (19.1%) were pUA stone cases. Among the potential predictors, thresholding 3D segmentation-based VCSD, age, sex, radio-opacity, hypertension, diabetes, and urine pH were identified as independent pUA stone predictors, and VCSD was the most powerful indicator. The pUA stone prediction model showed good discrimination, yielding area under the receiver operating characteristic curve of 0.960 (95% confidence interval (CI): 0.940–0.979, P < 0.001), 0.931 (95% CI: 0.875–0.987, P < 0.001), and 0.938 (95% CI: 0.912–0.965, P < 0.001) in the training, internal validation, and external validation sets, respectively. ConclusionsVCSD measured using 3D segmentation was a decisive independent predictive factor for pUA stones. Furthermore, the established prediction model with VCSD can serve as a noninvasive preoperative tool to identify pUA stones.

Preoperative CT Radiomics Nomogram for Predicting Microvascular Invasion in Stage I Non-Small Cell Lung Cancer

This retrospective study analyzed 188 cases of stage I NSCLC (63 MVI positives and 125 negatives), which were randomly assigned to training (n=133) and validation cohorts (n=55) at a ratio of 7:3. Preoperative non-contrast and contrast-enhanced CT (CECT) images were used to analyze computed tomography (CT) features and extract radiomics features. The student's t-test, the Mann-Whitney-U test, the Pearson correlation, the least absolute shrinkage and selection operator, and multivariable logistic analysis were used to select the significant CT and radiomics features. Multivariable logistic regression analysis was performed to build the clinical-CT, radiomics, and integrated models. The predictive performances were evaluated through the receiver operating characteristic curve and compared with the DeLong test. The integrated nomogram was analyzed regarding discrimination, calibration, and clinical significance. The rad-score was developed with one shape and four textural features. The integrated nomogram incorporating radiomics score, spiculation, and the number of tumor-related vessels (TVN) demonstrated better predictive efficacy than the radiomics and clinical-CT models in the training cohort (area under the curve [AUC], 0.893 vs 0.853 and 0.828, andp=0.043 and 0.027, respectively) and validation cohort (AUC, 0.887 vs 0.878 and 0.786, andp=0.761 and 0.043, respectively). The nomogram also demonstrated good calibration and clinical usefulness. The radiomics nomogram integrating the radiomics with clinical-CT features demonstrated good performance in predicting MVI status in stage I NSCLC. The nomogram may be a useful tool for physicians in improving personalized management of stage I NSCLC.

#5276 DEVELOPMENT OF A MULTIMODAL “KIDNEY AGE” PREDICTION BASED ON AUTOMATIC SEGMENTATION CT IMAGE IN PATIENTS WITH NORMAL RENAL FUNCTION

Abstract Background and Aims Renal function, for decades, has been of interest to clinicians and researchers to describe. For example, serum creatinine (Scr) and estimated glomerulus filtration rate (eGFR) is familiar but also limited in many circumstances. Meanwhile, the physiological volumes of the kidney cortex and medulla are presumed to change with age and have been proven to change with decreasing kidney function. Method We recruited 182 patients with normal Scr levels and contrasted CT images between Oct. 2021 and Feb 2022 in Peking Union Medical College Hospital (PUMCH) with their demographic and clinical data. The automatic segmentation method was modified from U-NET and used for both cortex and medullary separation and their volume calculation, respectively. We combined the kidney volume and clinical data as multimodal features of the machine learning model. All the data were separated into a training dataset (PUMCH training set, 80%) and a test dataset (PUMCH test set, 20%). Besides, we included patients with the same inclusion criteria but with diabetes (PUMCH-DM test set) and diabetic nephropathy (PUMCH-DN test set) for internal comparison to verify the possible clinical value of “KIDNEY AGE” (K-AGE). Data from DongZhiMen Hospital (DZMH test set) was used as separate external validation sets to evaluate model generalizability. Results The PUMCH training set included 146 participants with a mean age of 47.5±7.4 years. 58.9% were female, and the mean Scr is 63.5±12.3 μmol/L. The PUMCH test set included 36 participants with a mean age of 47.1±7.9 years, 52.7% were female, and the mean Scr was 66.9±13.0 μmol/L. For segmented kidneys, volume differences between non-contrast-enhanced CT and non-contrast-enhanced CT in the left and right kidneys were not evident. The multimodal neural network predicted: K-AGE approximately close to the patient's actual physiological age, with 92% prediction within the 95% confidential interval (Figure 1). We also compared the K-AGE prediction in PUMCH, PUMCH-DM, and PUMCH-DN test sets by applying U-NET-nonCon segmentation algorithm in non-contrast CT images. The mean absolute error increases along with the disease process (control group 5.00, diabetes group 6.99, diabetic nephropathy group 9.32) (Figure 2). Conclusion We established a machine learning model for predicting the K-AGE of normal Scr patients.

Predicting DWI-FLAIR mismatch on NCCT: the role of artificial intelligence in hyperacute decision making.

The presence of diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) mismatch was used to determine eligibility for intravenous thrombolysis in clinical trials. However, due to the restricted availability of MRI and the ambiguity of image assessment, it is not widely implemented in clinical practice. A total of 222 acute ischemic stroke patients underwent non-contrast computed tomography (NCCT), DWI, and FLAIR within 1 h of one another. Human experts manually segmented ischemic lesions on DWI and FLAIR images and independently graded the presence of DWI-FLAIR mismatch. Deep learning (DL) models based on the nnU-net architecture were developed to predict ischemic lesions visible on DWI and FLAIR images using NCCT images. Inexperienced neurologists evaluated the DWI-FLAIR mismatch on NCCT images without and with the model's results. The mean age of included subjects was 71.8 ± 12.8 years, 123 (55%) were male, and the baseline NIHSS score was a median of 11 [IQR, 6-18]. All images were taken in the following order: NCCT - DWI - FLAIR, starting after a median of 139 [81-326] min after the time of the last known well. Intravenous thrombolysis was administered in 120 patients (54%) after NCCT. The DL model's prediction on NCCT images revealed a Dice coefficient and volume correlation of 39.1% and 0.76 for DWI lesions and 18.9% and 0.61 for FLAIR lesions. In the subgroup with 15 mL or greater lesion volume, the evaluation of DWI-FLAIR mismatch from NCCT by inexperienced neurologists improved in accuracy (from 0.537 to 0.610) and AUC-ROC (from 0.493 to 0.613). The DWI-FLAIR mismatch may be reckoned using NCCT images through advanced artificial intelligence techniques.

Performance of an automated deep learning algorithm to identify hepatic steatosis within noncontrast computed tomography scans among people with and without HIV.

Hepatic steatosis (fatty liver disease) affects 25% of the world's population, particularly people with HIV (PWH). Pharmacoepidemiologic studies to identify medications associated with steatosis have not been conducted because methods to evaluate liver fat within digitized images have not been developed. We determined the accuracy of a deep learning algorithm (automatic liver attenuation region-of-interest-based measurement [ALARM]) to identify steatosis within clinically obtained noncontrast abdominal CT images compared to manual radiologist review and evaluated its performance by HIV status. We performed a cross-sectional study to evaluate the performance of ALARM within noncontrast abdominal CT images from a sample of patients with and without HIV in the US Veterans Health Administration. We evaluated the ability of ALARM to identify moderate-to-severe hepatic steatosis, defined by mean absolute liver attenuation <40 Hounsfield units (HU), compared to manual radiologist assessment. Among 120 patients (51 PWH) who underwent noncontrast abdominal CT, moderate-to-severe hepatic steatosis was identified in 15 (12.5%) persons via ALARM and 12 (10%) by radiologist assessment. Percent agreement between ALARM and radiologist assessment of absolute liver attenuation <40 HU was 95.8%. Sensitivity, specificity, positive predictive value, and negative predictive value of ALARM were 91.7% (95%CI, 51.5%-99.8%), 96.3% (95%CI, 90.8%-99.0%), 73.3% (95%CI, 44.9%-92.2%), and 99.0% (95%CI, 94.8%-100%), respectively. No differences in performance were observed by HIV status. ALARM demonstrated excellent accuracy for moderate-to-severe hepatic steatosis regardless of HIV status. Application of ALARM to radiographic repositories could facilitate real-world studies to evaluate medications associated with steatosis and assess differences by HIV status.

Validation of a deep learning model for traumatic brain injury detection and NIRIS grading on non-contrast CT: a multi-reader study with promising results and opportunities for improvement.

This study aimed to assess and externally validate the performance of a deep learning (DL) model for the interpretation of non-contrast computed tomography (NCCT) scans of patients with suspicion of traumatic brain injury (TBI). This retrospective and multi-reader study included patients with TBI suspicion who were transported to the emergency department and underwent NCCT scans. Eight reviewers, with varying levels of training and experience (two neuroradiology attendings, two neuroradiology fellows, two neuroradiology residents, one neurosurgery attending, and one neurosurgery resident), independently evaluated NCCT head scans. The same scans were evaluated using the version 5.0 of the DL model icobrain tbi. The establishment of the ground truth involved a thorough assessment of all accessible clinical and laboratory data, as well as follow-up imaging studies, including NCCT and magnetic resonance imaging, as a consensus amongst the study reviewers. The outcomes of interest included neuroimaging radiological interpretation system (NIRIS) scores, the presence of midline shift, mass effect, hemorrhagic lesions, hydrocephalus, and severe hydrocephalus, as well as measurements of midline shift and volumes of hemorrhagic lesions. Comparisons using weighted Cohen's kappa coefficient were made. The McNemar test was used to compare the diagnostic performance. Bland-Altman plots were used to compare measurements. One hundred patients were included, with the DL model successfully categorizing 77 scans. The median age for the total group was 48, with the omitted group having a median age of 44.5 and the included group having a median age of 48. The DL model demonstrated moderate agreement with the ground truth, trainees, and attendings. With the DL model's assistance, trainees' agreement with the ground truth improved. The DL model showed high specificity (0.88) and positive predictive value (0.96) in classifying NIRIS scores as 0-2 or 3-4. Trainees and attendings had the highest accuracy (0.95). The DL model's performance in classifying various TBI CT imaging common data elements was comparable to that of trainees and attendings. The average difference for the DL model in quantifying the volume of hemorrhagic lesions was 6.0mL with a wide 95% confidence interval (CI) of - 68.32 to 80.22, and for midline shift, the average difference was 1.4mm with a 95% CI of - 3.4 to 6.2. While the DL model outperformed trainees in some aspects, attendings' assessments remained superior in most instances. Using the DL model as an assistive tool benefited trainees, improving their NIRIS score agreement with the ground truth. Although the DL model showed high potential in classifying some TBI CT imaging common data elements, further refinement and optimization are necessary to enhance its clinical utility.

Exploring Texture Analysis to Optimize Bladder Preservation in Muscle Invasive Bladder Cancer.

To explore if texture analysis of Muscle Invasive Bladder Cancer (MIBC) can aid in better patient selection for bladder preservation. Pretreatment noncontrast CT images of 41 patients of MIBC treated with bladder preservation were included. The visible tumor was contoured on all slices by a single observer. The primary endpoint was to identify texture parameters associated with disease recurrence posttreatment. The secondary endpoints included intra and interobserver variability, single and multislice analysis, and differentiating the texture features of normal bladder and tumor. For interobserver variability of bladder tumor texture features, 3 observers contoured the visible tumor on all slices independently. Observer 1 contoured again at an interval of 1 month for intraobserver variability. The median follow-up was 30 months with 12 patients having a recurrence. In the primary endpoint analysis, the mean of the pixels at Spatial Scaling Filter (SSF) 2 for the no recurrence group and recurrence group was 6.44 v 13.73 respectively (P=.031) and the same at SSF-3 was 11.95 and 22.32 respectively (P=.034). The texture features that could significantly differentiate tumor and normal bladder were mean, standard deviation and kurtosis of the pixels at SSF-2 and entropy and kurtosis of the pixels at SSF-3. Overall, there was an excellent intra and interobserver concordance in texture features. Only multislice analysis and not single-slice could differentiate recurrence and no recurrence posttreatment. Texture analysis can be explored as a modality for patient selection for bladder preservation along with the established clinical parameters to improve outcomes.

Review of Diagnostic Modalities for Adrenal Incidentaloma.

Adrenal incidentalomas are common findings in clinical practice, with a prevalence of up to 4.2% in radiological studies. Due to the large number of focal lesions in the adrenal glands, it can be challenging to make a definitive diagnosis and determine the appropriate management. The purpose of this review is to present current diagnostic modalities used to preoperatively distinguish between adrenocortical adenoma (ACA) and adrenocortical cancer (ACC). Proper management and diagnosis are crucial in avoiding unnecessary adrenalectomies, which occur in over 40% of cases. A literature analysis was conducted to compare ACA and ACC using imaging studies, hormonal evaluation, pathological workup, and liquid biopsy. Before deciding on surgical treatment, the nature of the tumor can be accurately determined using noncontrast CT imaging combined with tumor size and metabolomics. This approach helps to narrow down the group of patients with adrenal tumors who require surgical treatment due to the suspected malignant nature of the lesion.

Advanced Faster RCNN: a non-contrast CT-based algorithm for detecting pancreatic lesions in multiple disease stages

To propose a non-contrast CT-based algorithm for automated and accurate detection of pancreatic lesions at a low cost. With Faster RCNN as the benchmark model, an advanced Faster RCNN (aFaster RCNN) model for pancreatic lesions detection based on plain CT was constructed. The model uses the residual connection network Resnet50 as the feature extraction module to extract the deep image features of pancreatic lesions. According to the morphology of pancreatic lesions, 9 anchor frame sizes were redesigned to construct the RPN module. A new Bounding Box regression loss function was proposed to constrain the training process of RPN module regression subnetwork by comprehensively considering the constraints of the lesion shape and anatomical structure. Finally, a detection frame was generated using the detector in the second stage. The data from a total of 728 cases of pancreatic diseases from 4 clinical centers in China were used for training (518 cases, 71.15%) and testing (210 cases, 28.85%) of the model. The performance of aFaster RCNN was verified through ablation experiments and comparison experiments with 3 classical target detection models SSD, YOLO and CenterNet. The aFaster RCNN model for pancreatic lesion detection achieved recall rates of 73.64% at the image level and 92.38% at the patient level, with an average precision of 45.29% and 53.80% at the image and patient levels, respectively, which were higher than those of the 3 models for comparison. The proposed method can effectively extract the imaging features of pancreatic lesions from non-contrast CT images to detect the pancreatic lesions.

Type A Aortic Dissection and Non-Contrast Computed Tomography.

Non-contrast enhanced chest computed tomography (CT) carries a low sensitivity for acute aortic dissection; CT Angiography remains the gold standard. We highlight the potential utility of non-contrast CT for detection of aortic dissection in a case of a young, immunocompromised man presenting with acute abdominal pain and renal injury. Given elevated creatinine, an initial non-contrast chest CT demonstrated subtle findings suggestive of aortic dissection (aneurysmal dilation of the proximal ascending aorta as well as displaced calcified intimal flap/intraluminal high linear density in the thoracic descending and distal abdominal aorta). Subsequent CT angiography confirmed the presence of an extensive type A aortic dissection. He underwent emergent exploratory laparotomy and hemiarch repair. Displaced calcified intimal flaps, intraluminal high-densities, intramural hematoma, and aneurysmal aortic dilation are common non-contrast computed tomography imaging findings that suggest aortic dissection.

IS-Net: Automatic Ischemic Stroke Lesion Segmentation on CT Images

Ischemic stroke is an acute cerebral vascular disease and makes up about 80% of all stroke cases. Non-contrast computed tomography (NCCT) is a widely applied imaging technique for ischemic stroke assessment. However, it is challenging to identify ischemic lesion on NCCT images due to its high variability in location, contrast, and geometry. In this work, we propose IS-Net, an encoder-decoder convolutional neural network for automatic ischemic stroke lesion segmentation on NCCT images. The proposed IS-Net takes hierarchical network as backbone while pyramid feature aggregation (PFA) module is designed to aggregate features from multi stages of backbone, and reasonable feature fusion strategy is considered in PFA to enhance multi-level propagation. To fully mine the boundary cues, edge constraint scheme is introduced by deep supervision which broadcasts low-level features to different modules. In addition, to overcome the limitation of fixed geometric structure of convolution for multi-range dependency exploitation, non-local parallel decoder is introduced with deformable convolution and self-attention. The proposed IS-Net is evaluated on manually labeled follow-up NCCT dataset composed of 1,004 cases (totally 9,020 images). The proposed IS-Net is compared with the state-of-the-art segmentation models and illustrates the highest score on segmentation criteria and sensitivity.

Clinical evaluation of a deep-learning model for automatic scoring of the Alberta stroke program early CT score on non-contrast CT

BackgroundAutomated measurement of the Alberta Stroke Program Early Computed Tomography Score (ASPECTS) can support clinical decision making. Based on a deep learning algorithm, we developed an automated ASPECTS scoring system...