Non-contrast CT Images Research Articles

Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection

Objectives: Subarachnoid Hemorrhage (SAH) is a serious neurological emergency case with a higher mortality rate. An automatic SAH detection is needed to expedite and improve identification, aiding timely and efficient treatment pathways. The existence of noisy and dissimilar anatomical structures in NCCT images, limited availability of labeled SAH data, and ineffective training causes the issues of irrelevant features, overfitting, and vanishing gradient issues that make SAH detection a challenging task. Methods: In this work, the water waves dynamic factor and wandering strategy-based Sand Cat Swarm Optimization, namely DWSCSO, are proposed to ensure optimum feature selection while a Parametric Rectified Linear Unit with a Stacked Convolutional Neural Network, referred to as PRSCNN, is developed for classifying grades of SAH. The DWSCSO and PRSCNN surpass current practices in SAH detection by improving feature selection and classification accuracy. DWSCSO is proposed to ensure optimum feature selection, avoiding local optima issues with higher exploration capacity and avoiding the issue of overfitting in classification. Firstly, in this work, a modified region-growing method was employed on the patient Non-Contrast Computed Tomography (NCCT) images to segment the regions affected by SAH. From the segmented regions, the wide range of patterns and irregularities, fine-grained textures and details, and complex and abstract features were extracted from pre-trained models like GoogleNet, Visual Geometry Group (VGG)-16, and ResNet50. Next, the PRSCNN was developed for classifying grades of SAH which helped to avoid the vanishing gradient issue. Results: The DWSCSO-PRSCNN obtained a maximum accuracy of 99.48%, which is significant compared with other models. The DWSCSO-PRSCNN provides an improved accuracy of 99.62% in CT dataset compared with the DL-ICH and GoogLeNet + (GLCM and LBP), ResNet-50 + (GLCM and LBP), and AlexNet + (GLCM and LBP), which confirms that DWSCSO-PRSCNN effectively reduces false positives and false negatives. Conclusions: the complexity of DWSCSO-PRSCNN was acceptable in this research, for while simpler approaches appeared preferable, they failed to address problems like overfitting and vanishing gradients. Accordingly, the DWSCSO for optimized feature selection and PRSCNN for robust classification were essential for handling these challenges and enhancing the detection in different clinical settings.

Age-specific ASPECTS atlas of Chinese subjects across different age groups for assessing acute ischemic stroke

The Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a valuable and easy-to-use method for assessing acute ischemic stroke. It aids in identifying suitable candidates for thrombolytic therapies and evaluating treatment effectiveness. However, ASPECTS evaluation primarily relies on visual observation in current clinical practice, lacking a common standardized space. Additionally, different doctors may have varying clinical experiences, leading to a poor inter-reader agreement and potential errors in the final ASPECTS scoring. To address these issues and fill in the absence of a publicly available ASPECTS atlas, this work constructs age-specific Chinese ASPECTS atlases based on non-contrast computed tomography images of 281 healthy subjects across different age groups. Images of different age groups are warped into respective common averaged spaces, where the average intensity atlases are computed. More importantly, 10 ASPECTS regions can be obtained during this process. We develop an automated ASPECTS region mapping pipeline and collect an independent dataset to validate our atlas. The results prove that the age-specific ASPECTS atlas is of great promise in clinical availability.

Segmentation-based quantitative measurements in renal CT imaging using deep learning

BackgroundRenal quantitative measurements are important descriptors for assessing kidney function. We developed a deep learning-based method for automated kidney measurements from computed tomography (CT) images.MethodsThe study datasets comprised potential kidney donors (n = 88), both contrast-enhanced (Dataset 1 CE) and noncontrast (Dataset 1 NC) CT scans, and test sets of contrast-enhanced cases (Test set 2, n = 18), cases from a photon-counting (PC)CT scanner reconstructed at 60 and 190 keV (Test set 3 PCCT, n = 15), and low-dose cases (Test set 4, n = 8), which were retrospectively analyzed to train, validate, and test two networks for kidney segmentation and subsequent measurements. Segmentation performance was evaluated using the Dice similarity coefficient (DSC). The quantitative measurements’ effectiveness was compared to manual annotations using the intraclass correlation coefficient (ICC).ResultsThe contrast-enhanced and noncontrast models demonstrated excellent reliability in renal segmentation with DSC of 0.95 (Test set 1 CE), 0.94 (Test set 2), 0.92 (Test set 3 PCCT) and 0.94 (Test set 1 NC), 0.92 (Test set 3 PCCT), and 0.93 (Test set 4). Volume estimation was accurate with mean volume errors of 4%, 3%, 6% mL (contrast test sets) and 4%, 5%, 7% mL (noncontrast test sets). Renal axes measurements (length, width, and thickness) had ICC values greater than 0.90 (p < 0.001) for all test sets, supported by narrow 95% confidence intervals.ConclusionTwo deep learning networks were shown to derive quantitative measurements from contrast-enhanced and noncontrast renal CT imaging at the human performance level.Relevance statementDeep learning-based networks can automatically obtain renal clinical descriptors from both noncontrast and contrast-enhanced CT images. When healthy subjects comprise the training cohort, careful consideration is required during model adaptation, especially in scenarios involving unhealthy kidneys. This creates an opportunity for improved clinical decision-making without labor-intensive manual effort.Key PointsTrained 3D UNet models quantify renal measurements from contrast and noncontrast CT.The models performed interchangeably to the manual annotator and to each other.The models can provide expert-level, quantitative, accurate, and rapid renal measurements.Graphical

8234 Composite Pheochromocytoma-Ganglioneuroma: Two Clinical Cases Presenting To St. Elizabeth’s Medical Center

Abstract Disclosure: M. El Najjar: None. E. Naous: None. C. Blake: None. A.T. Sweeney: None. Introduction: Pheochromocytomas (PCCS) are rare catecholamine producing tumors that originate from the chromaffin cells of the adrenal medulla. In 3-9% of cases, they may be accompanied by other tumors. Ganglioneuromas are the most encountered tumor type that occur with PCC and are termed composite PCC-GN. The entity is very rare with &amp;lt; 35 cases reported. Herein, we present 2 cases of composite PCC-GN. Case Presentation: Patient 1 (Pt1) &amp; Patient 2 (Pt2): were 35- &amp; 54-year-old obese females. Pt1 had controlled hypertension and symptoms of anxiety along with palpitations, diaphoresis and flushing. Pt2 had type 2 diabetes and complained of abdominal pain. Metabolic studies showed elevated total plasma fractionated metanephrines(MNs). MNs in Pt1 and Pt2 were: 76 and 61pg/ml respectively (normal &amp;lt;57 pg/ml) and normetaneprines levels were 161 and 116pg/ml respectively (normal &amp;lt;148 pg/ml). Abdominal computed tomography (CT) scans demonstrated right adrenal masses in both cases with Pt1 having a 2.3 x 2.3 x 2.6 cm mass (Figure1) with smooth margins measuring 36 Hounsfield units (HU) on non-contrast(NC) CT imaging with 0% washout on delayed imaging after IV contrast. Pt2 on NCCT had a 4.5 x 3.5 cm right adrenal mass measuring 73 HU and a subsequent abdominal MRI(Figure2) demonstrated the mass to have heterogenous signal intensity. Both patients were prepared with pre-operative a and b blockade and underwent laparoscopic robotic adrenalectomies without complications. Pathological analyses in both cases revealed composite PCC-GN. Pt2 underwent genetic testing which did not reveal any known mutations. Surveillance in both patients demonstrated no recurrence. Clinical lesson: The clinical presentation of PCC-GNs is indistinguishable from isolated PCCs. The definitive diagnosis is through histopathological analysis. Histologically the composite tumor is composed of two distinct patterns with PCC showing angular cells with granular, basophilic cytoplasm, arranged in nests, while GNs show ganglion cells in fibrous stroma. Immunohistochemistry show the PCCs staining for chromogranin A and synaptophysin while GNs stain for S-100 protein and neurofilament antibody. Most cases occur in patients between 40 - 60 years old. Most PCC-GNs are functional, with increased MNs. PCC-GN composite tumors may occur sporadically but have also been described as part of syndromes such as MEN2A and NF1. The definitive treatment for PCC-GN is complete surgical excision which is associated with an excellent prognosis. The probability of recurrence is low though distant metastases have rarely been reported. Therefore, lifetime surveillance is critical. Presentation: 6/3/2024

CT-based Intra-thrombus and Peri-thrombus Radiomics for Prediction of Prognosis After Endovascular Thrombectomy: A Retrospective Study Across Two Centers.

Complications from endovascular thrombectomy (EVT) can negatively affect clinical outcomes, making the development of a more precise and objective prediction model essential. This research aimed to assess the effectiveness of radiomic features derived from pre-surgical CT scans in predicting the prognosis post- EVT in acute ischemic stroke patients. This investigation included 336 acute ischemic stroke patients from two medical centers, spanning from March 2018 to March 2024. The participants were split into a training cohort of 161 patients and a validation cohort of 175 patients. Patient outcomes were rated with the mRS: 0-2 for good, 3-6 for poor. A total of 428 radiomic features were derived from intra-thrombus and peri-thrombus regions in non-contrast CT and CT angiography images. Feature selection was conducted using a least absolute shrinkage and selection operator regression model. The efficacy of eight different supervised learning models was assessed using the area under the curve (AUC) of the receiver operating characteristic curve. Among all models tested in the validation cohort, the logistic regression algorithm for combined model achieved the highest AUC (0.87, with a 95% confidence interval of 0.81 to 0.92), outperforming other algorithms. The combined use of radiomic features from both the intra-thrombus and peri-thrombus regions significantly enhanced diagnostic accuracy over models using features from a single region (0.81 vs 0.70, 0.77), highlighting the benefit of integrating data from both regions for improved prediction. The findings suggest that a combined radiomics model based on CT imaging serves as a potent approach to assessing the prognosis following EVT. The logistic regression model, in particular, proved to be both effective and stable, offering critical insights for the management of stroke. AUC=area under the curve; EVT=endovascular thrombectomy; KNN=k-nearest neighbors; LASSO=least absolute shrinkage and selection operator; LightGBM=Light Gradient Boosting Machine; LR=logistic regression; MLP=multi-layer perceptron; RF=random forest; SVM=support vector machine; XGBoost=extreme gradient boosting.

Enhancing Diagnostic Accuracy in Body Packing Cases: The Impact of Preliminary Diagnosis Awareness on Computed Tomography Evaluation

Objective: Body packing refers to the concealment of illegal substances within the body. This study aims to evaluate the computed tomography (CT) findings of body packing cases, and to assess whether considering the possibility of body packing in preliminary diagnosis will affect the accuracy of specialists evaluating in the emergency and intensive care departments. Materials and Methods: 20 body packing cases were retrospectively examined for the presence of foreign bodies. A control group was created from 20 non-contrast abdominal CT images. Re-evaluation involved four radiologists. Before evaluating, two radiologists were advised they could be body packers. Results: In 18 (90%) of 20 body packers, foreign bodies were visible in the intestinal lumen, mostly 14 (70%) in the colon. Radiologists who were given preliminary diagnosis, correctly identified all 18 (100%) intestinal foreign body cases and did not make any false positives. Two other radiologists correctly identified 16 (88.9%) cases and missed 2 (11.1%) cases and there was significantly difference (p

Constructing machine learning models based on non-contrast CT radiomics to predict hemorrhagic transformation after stoke: a two-center study.

Machine learning (ML) models were constructed according to non-contrast computed tomography (NCCT) images as well as clinical and laboratory information to assess risk stratification for the occurrence of hemorrhagic transformation (HT) in acute ischemic stroke (AIS) patients. A retrospective cohort was constructed with 180 AIS patients who were diagnosed at two centers between January 2019 and October 2023 and were followed for HT outcomes. Patients were analyzed for clinical risk factors for developing HT, infarct texture features were extracted from NCCT images, and the radiomics score (Rad-score) was calculated. Then, five ML models were established and evaluated, and the optimal ML algorithm was used to construct the clinical, radiomics, and clinical-radiomics models. Receiver operating characteristic (ROC) curves were used to compare the performance of the three models in predicting HT. Based on the outcomes of the AIS patients, 104 developed HT, and the remaining 76 had no HT. The HT group consisted of 27 hemorrhagic infarction (HI) and 77 parenchymal-hemorrhage (PH). Patients with HT had a greater neutrophil-to-lymphocyte ratio (NLR), baseline National Institutes of Health Stroke Scale (NIHSS) score, infarct volume, and Rad-score and lower Alberta stroke program early CT score (ASPECTS) (all p < 0.01) than patients without HT. The best ML algorithm for building the model was logistic regression. In the training and validation cohorts, the AUC values for the clinical, radiomics, and clinical-radiomics models for predicting HT were 0.829 and 0.876, 0.813 and 0.898, and 0.876 and 0.957, respectively. In subgroup analyses with different treatment modalities, different infarct sizes, and different stroke time windows, the assessment accuracy of the clinical-radiomics model was not statistically meaningful (all p > 0.05), with an overall accuracy of 79.5%. Moreover, this model performed reliably in predicting the PH and HI subcategories, with accuracies of 82.9 and 92.9%, respectively. ML models based on clinical and NCCT radiomics characteristics can be used for early risk evaluation of HT development in AIS patients and show great potential for clinical precision in treatment and prognostic assessment.

Ensemble machine learning to predict futile recanalization after mechanical thrombectomy based on non-contrast CT imaging

ObjectivesDespite successful recanalization after Mechanical Thrombectomy (MT), approximately 25 % of patients with Acute Ischemic Stroke (AIS) due to Large Vessel Occlusion (LVO) show unfavorable clinical outcomes, namely Futile Recanalization (FR). We aimed to use a Machine Learning (ML) Non-Contrast brain CT (NCCT) imaging predictive model to identify FR in patients undergoing MT. Materials & methodsBetween July 2022 and December 2022, 70 consecutive patients with LVO undergoing a complete recanalization (eTICI 3) with MT within 8 h from onset at our Centre were analyzed. Two NCCT images per patient of middle cerebral artery vascular territory and patients' clinical characteristics were classified by the presence of ischemic features on 24 h NCCT after MT. Each slice was segmented with “Mazda” software ver.4.6 by placing a Region Of Interest (ROI) on the whole brain by two radiologists in consensus. A total of 381 features were extracted for each slice. The dataset was split into train and test set with a 70:30 ratio. ResultsEleven classification models were trained. An Ensemble Machine Learning (EML) model was obtained by averaging the predictions of models with accuracy on a test set >70 %, with and without patients' clinical characteristics.The EML model combined with clinical data showed an accuracy of 0.76, a sensitivity of 0.88, a specificity of 0.69 with a NPV of 0.90, a PPV of 0.64, with AUC of 0.84. ConclusionNCCT and ML analysis shows promise in predicting FR after complete recanalization following MT in AIS patients. Larger studies are required to confirm these preliminary results.

A Fully Automated Pipeline Using Swin Transformers for Deep Learning-Based Blood Segmentation on Head Computed Tomography Scans After Aneurysmal Subarachnoid Hemorrhage

Accurate volumetric assessment of spontaneous aneurysmal subarachnoid hemorrhage (aSAH) is a labor-intensive task performed with current manual and semiautomatic methods that might be relevant for its clinical and prognostic implications. In the present research, we sought to develop and validate an artificial intelligence-driven, fully automated blood segmentation tool for subarachnoid hemorrhage (SAH) patients via noncontrast computed tomography (NCCT) scans employing a transformer-based Swin-UNETR architecture. We retrospectively analyzed NCCT scans from patients with confirmed aSAH utilizing the Swin-UNETR for segmentation. The performance of the proposed method was evaluated against manually segmented ground truth data using metrics such as Dice score, intersection over union, volumetric similarity index , symmetric average surface distance , sensitivity, and specificity. A validation cohort from an external institution was included to test the generalizability of the model. The model demonstrated high accuracy with robust performance metrics across the internal and external validation cohorts. Notably, it achieved high Dice coefficient (0.873±0.097), intersection over union (0.810±0.092), volumetric similarity index (0.840±0.131), sensitivity (0.821±0.217), and specificity (0.996±0.004) values and a low symmetric average surface distance (1.866±2.910), suggesting proficiency in segmenting blood in SAH patients. The model's efficiency was reflected in its processing speed, indicating potential for real-time applications. Our Swin UNETR-based model offers significant advances in the automated segmentation of blood in SAH patients on NCCT images. Despite the computational demands, the model operates effectively on standard hardware with a user-friendly interface, facilitating broader clinical adoption. Further validation across diverse datasets is warranted to confirm its clinical reliability.

CT-based deep learning radiomics biomarker for programmed cell death ligand 1 expression in non-small cell lung cancer

BackgroundProgrammed cell death ligand 1 (PD-L1), as a reliable predictive biomarker, plays an important role in guiding immunotherapy of lung cancer. To investigate the value of CT-based deep learning radiomics signature to predict PD-L1 expression in non-small cell lung cancers(NSCLCs).Methods259 consecutive patients with pathological confirmed NSCLCs were retrospectively collected and divided into the training cohort and validation cohort according to the chronological order. The univariate and multivariate analyses were used to build the clinical model. Radiomics and deep learning features were extracted from preoperative non-contrast CT images. After feature selection, Radiomics score (Rad-score) and deep learning radiomics score (DLR-score) were calculated through a linear combination of the selected features and their coefficients. Predictive performance for PD-L1 expression was evaluated via the area under the curve (AUC) of receiver operating characteristic, the calibration curves, and the decision curve analysis.ResultsThe clinical model based on Cytokeratin 19 fragment and lobulated shape obtained an AUC of 0.767(95% CI: 0.673–0.860) in the training cohort and 0.604 (95% CI:0.477–0.731) in the validation cohort. 11 radiomics features and 15 deep learning features were selected by LASSO regression. AUCs of the Rad-score were 0.849 (95%CI: 0.783–0.914) and 0.717 (95%CI: 0.607–0.826) in the training cohort and validation cohort, respectively. AUCs of DLR-score were 0.938 (95%CI: 0.899–0.977) and 0.818(95%CI:0.727–0.910) in the training cohort and validation cohort, respectively. AUCs of the DLR-score were significantly higher than those of the Rad-score and the clinical model.ConclusionThe CT-based deep learning radiomics signature could achieve clinically acceptable predictive performance for PD-L1 expression, which showed potential to be a surrogate imaging biomarker or a complement of immunohistochemistry assessment.

Artificial Intelligence-based automated CT brain interpretation to accelerate treatment for acute stroke in rural India: An interrupted time series study.

In resource-limited settings, timely treatment of acute stroke is dependent upon accurate diagnosis that draws on non-contrast computed tomography (NCCT) scans of the head. Artificial Intelligence (AI) based devices may be able to assist non-specialist physicians in NCCT interpretation, thereby enabling faster interventions for acute stroke patients in these settings. We evaluated the impact of an AI device by comparing the time to intervention (TTI) from NCCT imaging to significant intervention before (baseline) and after the deployment of AI, in patients diagnosed with stroke (ischemic or hemorrhagic) through a retrospective interrupted time series analysis at a rural hospital managed by non-specialists in India. Significant intervention was defined as thrombolysis or antiplatelet therapy in ischemic strokes, and mannitol for hemorrhagic strokes or mass effect. We also evaluated the diagnostic accuracy of the software using the teleradiologists' reports as ground truth. Impact analysis in a total of 174 stroke patients (72 in baseline and 102 after deployment) demonstrated a significant reduction of median TTI from 80 minutes (IQR: 56·8-139·5) during baseline to 58·50 (IQR: 30·3-118.2) minutes after AI deployment (Wilcoxon rank sum test-location shift: -21·0, 95% CI: -38·0, -7·0). Diagnostic accuracy evaluation in a total of 864 NCCT scans demonstrated the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) in detecting intracranial hemorrhage to be 0·89 (95% CI: 0·83-0·93), 0·99 (0·98-1·00), 0·96 (0·91-0·98) and 0·97 (0·96-0·98) respectively, and for infarct these were 0·84 (0·79-0·89), 0·81 (0·77-0·84), 0·58 (0·52-0·63), and 0·94 (0·92-0·96), respectively. AI-based NCCT interpretation supported faster abnormality detection with high accuracy, resulting in persons with acute stroke receiving significantly earlier treatment. Our results suggest that AI-based NCCT interpretation can potentially improve uptake of lifesaving interventions for acute stroke in resource-limited settings.

Risk Factors of Asymptomatic Kidney Stone Passage in Adults with Recurrent Kidney Stones.

Kidney stones are a common health problem and are characterized by a high risk of recurrence. A certain number of kidney stones passed asymptomatically. Data regarding the frequency of asymptomatic spontaneous stone passages are limited. To assess the frequency of asymptomatic spontaneous stone passage and its covariates, we conducted a post-hoc analysis of the prospective randomized NOSTONE trial. All asymptomatic spontaneous stone passages were identified by comparing the total number of kidney stones on low-dose non-contrast CT imaging at the beginning and end of the study, considering symptomatic stone passages and surgical stone removal. The statistical analysis focused on the association of independent variables and the number of asymptomatic spontaneous stone passages using linear regression analyses. Of the 416 randomized patients, 383 with both baseline and end-of-study CT were included in this analysis. The median follow-up period was 35 months, the median patient age was 49 years (IQR:40 - 55), and 20% of the patients were female. A total of 442 stone events occurred in 209 out of 383 (55%) patients: 217 out of 442 (49%) were symptomatic spontaneous stone passages, 67 out of 442 (15%) were surgically removed stones, and 158 out of 442 (36%) were asymptomatic spontaneous stone passages. The median size of asymptomatic stones (2.4 mm; IQR:1.95-3.4) and the size of symptomatic stones (2.15 mm; IQR:1.68-2.79) that passed spontaneously were not significantly different (p=0.37). The number of asymptomatic spontaneous stone passages was significantly associated with a higher number of stones on CT at randomization (P=0.001). Limitations include the lack of data on stone size at the time of passage and overrepresentation of White men. Asymptomatic stone passage was common in patients with recurrent calcium-containing kidney stones. The higher the number of stones at presentation, the more likely it was that a kidney stone would spontaneously pass over time without causing any symptoms.

Synthetic hematocrit from virtual non-contrast images for myocardial extracellular volume evaluation with photon-counting detector CT.

To assess the accuracy of a synthetic hematocrit derived from virtual non-contrast (VNC) and virtual non-iodine images (VNI) for myocardial extracellular volume (ECV) computation with photon-counting detector computed tomography (PCD-CT). Consecutive patients undergoing PCD-CT including a coronary CT angiography (CCTA) and a late enhancement (LE) scan and having a blood hematocrit were retrospectively included. In the first 75 patients (derivation cohort), CCTA and LE scans were reconstructed as VNI at 60, 70, and 80 keV and as VNC with quantum iterative reconstruction (QIR) strengths 2, 3, and 4. Blood pool attenuation (BPmean) was correlated to blood hematocrit. In the next 50 patients (validation cohort), synthetic hematocrit was calculated using BPmean. Myocardial ECV was computed using the synthetic hematocrit and compared with the ECV using the blood hematocrit as a reference. In the derivation cohort (49 men, mean age 79 ± 8 years), a correlation between BPmean and blood hematocrit ranged from poor for VNI of CCTA at 80 keV, QIR2 (R2 = 0.12) to moderate for VNI of LE at 60 keV, QIR4; 70 keV, QIR3 and 4; and VNC of LE, QIR3 and 4 (all, R2 = 0.58). In the validation cohort (29 men, age 75 ± 14 years), synthetic hematocrit was calculated from VNC of the LE scan, QIR3. Median ECV was 26.9% (interquartile range (IQR), 25.5%, 28.8%) using the blood hematocrit and 26.8% (IQR, 25.4%, 29.7%) using synthetic hematocrit (VNC, QIR3; mean difference, -0.2%; limits of agreement, -2.4%, 2.0%; p = 0.33). Synthetic hematocrit calculated from VNC images enables an accurate computation of myocardial ECV with PCD-CT. Virtual non-contrast images from cardiac late enhancement scans with photon-counting detector CT allow the calculation of a synthetic hematocrit, which enables accurate computation of myocardial extracellular volume. Blood hematocrit is mandatory for conventional myocardial extracellular volume computation. Synthetic hematocrit can be calculated from virtual non-iodine and non-contrast photon-counting detector CT images. Synthetic hematocrit from virtual non-contrast images enables computation of the myocardial extracellular volume.

Epicardial fat modifies the relationship between coronary calcium score and all-cause mortality: The St. Francis Heart Study

ObjectiveEpicardial fat is associated with cardiovascular risk factors and adverse outcomes. However, it is not clear if epicardial fat remains to be a mortality risk when coronary calcium score (CAC) is taken into account. MethodsWe studied the 1005 participants from the St. Francis Heart Study who were apparently healthy with CAC scores at 80th percentile or higher for age and gender, randomly assigned to placebo or statin therapy. At baseline, lipid profiles and non-contrast CT images were obtained where the epicardial fat volume was analyzed. Likelihood ratio testing was used to assess the additional prognostic value of epicardial fat to CAC for the risk of all-cause mortality. ResultsIncreased epicardial fat volume was associated with higher CAC. For each unit increase in lnCAC, the average epicardial fat volume increased by 3.34 mL/m2. After a mean follow-up period of 17 years, 179 (18%) participants died. Increased epicardial fat volume was associated with an adjusted hazard ratio of 1.11 (95% CI: 1.02 to 1.20) predicting all-cause mortality. In the stratified analysis testing strata of epicardial fat and CAC, those with increased epicardial fat and increased CAC had the highest risk of death. Compared with a model containing lnCAC and traditional risk factors, a model additionally containing epicardial fat volume yielded a better model fit (likelihood ratio test p < 0.001). ConclusionIncreased epicardial fat volume is associated with increased all-cause mortality risk. In addition, it portends incremental prognostic value to CAC score in mortality prediction.

Diagnostic yield of computed tomography angiography in patients presenting with spontaneous intracerebral hemorrhage.

Hypertension and cerebral amyloid angiopathy are the most common causes of spontaneous intracerebral hemorrhage (ICH); however, these conditions do not imply macrovascular pathology. Still, computed tomography (CT) angiography (CTA) is often performed in the acute phase in patients with ICH. To assess the diagnostic yield of CTA in the detection of secondary etiology in consecutive patients with spontaneous ICH. We performed a retrospective analysis of data from a prospective single-center cohort study of 203 patients presenting with spontaneous ICH admitted to a comprehensive stroke center over a two-year period (15 October 2016 to 15 October 2018). The underlying vascular pathology was assessed using CTA. CTA was performed in addition to non-contrast CT and/or magnetic resonance imaging (MRI). Vascular pathology was found in 11 of 203 (5.4%) patients and included arteriovenous malformations (n=4), aneurysms (n=4), vasospasms (n=1), cerebral venous thrombosis (n=1), and other vascular malformations (n=1). In eight cases, the finding was deemed symptomatic. Patients with vascular pathology on CTA more often had lobar located hemorrhages (63.6% vs. 36.4%, P = 0.049). Numerically, patients with vascular pathology were younger, had smaller hematoma volumes, and lower mortality. Underlying macrovascular pathology was detected on CTA in only approximately 1 of 20 consecutive patients with ICH. The patients with vascular pathology more often had a hemorrhage with a lobar location and young age and the present study is supportive of a risk-based stratification approach in performing CTA.

Time conditioning for arbitrary contrast phase generation in interventional computed tomography

Minimally invasive ablation techniques for renal cancer are becoming more popular due to their low complication rate and rapid recovery period. Despite excellent visualisation, one drawback of the use of computed tomography (CT) in these procedures is the requirement for iodine-based contrast agents, which are associated with adverse reactions and require a higher x-ray dose. The purpose of this work is to examine the use of time information to generate synthetic contrast enhanced images at arbitrary points after contrast agent injection from non-contrast CT images acquired during renal cryoablation cases. To achieve this, we propose a new method of conditioning generative adversarial networks with normalised time stamps and demonstrate that the use of a HyperNetwork is feasible for this task, generating images of competitive quality compared to standard generative modelling techniques. We also show that reducing the receptive field can help tackle challenges in interventional CT data, offering significantly better image quality as well as better performance when generating images for a downstream segmentation task. Lastly, we show that all proposed models are robust enough to perform inference on unseen intra-procedural data, while also improving needle artefacts and generalising contrast enhancement to other clinically relevant regions and features.

Swirl sign score system: a novel and practical tool for predicting hematoma expansion risk after spontaneous intracerebral haemorrhage.

To methodically analyse the swirl sign and construct a scoring system to predict the risk of hematoma expansion (HE) after spontaneous intracerebral haemorrhage (sICH). We analysed 231 of 683 sICH patients with swirl signs on baseline noncontrast CT (NCCT) images. The characteristics of the swirl sign were analysed, including the number, maximum diameter, shape, boundary, minimum CT value of the swirl sign, and the minimum distance from the swirl sign to the edge of the hematoma. In the development cohort, univariate and multivariate analyses were used to identify independent predictors of HE, and logistic regression analysis was used to construct the swirl sign score system. The swirl sign score system was verified in the validation cohort. The number and the minimum CT value of the swirl sign were independent predictors of HE. The swirl sign score system was constructed (2 points for the number of swirl signs >1 and 1 point for the minimum CT value ≤41 Hounsfield units). The area under the curve of the swirl sign score system in predicting HE was 0.773 and 0.770 in the development and validation groups, respectively. The swirl sign score system is an easy-to-use radiological grading scale that requires only baseline NCCT images to effectively identify subjects at high risk of HE. Our newly developed semiquantitative swirl sign score system greatly improves the ability of swirl sign to predict HE.

Multiscale and multiperception feature learning for pancreatic lesion detection based on noncontrast CT

Background. Pancreatic cancer is one of the most malignant tumours, demonstrating a poor prognosis and nearly identically high mortality and morbidity, mainly because of the difficulty of early diagnosis and timely treatment for localized stages. Objective. To develop a noncontrast CT (NCCT)-based pancreatic lesion detection model that could serve as an intelligent tool for diagnosing pancreatic cancer early, overcoming the challenges associated with low contrast intensities and complex anatomical structures present in NCCT images. Approach. We design a multiscale and multiperception (MSMP) feature learning network with ResNet50 coupled with a feature pyramid network as the backbone for strengthening feature expressions. We added multiscale atrous convolutions to expand different receptive fields, contextual attention to perceive contextual information, and channel and spatial attention to focus on important channels and spatial regions, respectively. The MSMP network then acts as a feature extractor for proposing an NCCT-based pancreatic lesion detection model with image patches covering the pancreas as its input; Faster R-CNN is employed as the detection method for accurately detecting pancreatic lesions. Main results. By using the new MSMP network as a feature extractor, our model outperforms the conventional object detection algorithms in terms of the recall (75.40% and 90.95%), precision (40.84% and 68.21%), F1 score (52.98% and 77.96%), F2 score (64.48% and 85.26%) and Ap50 metrics (53.53% and 70.14%) at the image and patient levels, respectively. Significance.The good performance of our new model implies that MSMP can mine NCCT imaging features for detecting pancreatic lesions from complex backgrounds well. The proposed detection model is expected to be further developed as an intelligent method for the early detection of pancreatic cancer.

Cerebrospinal fluid volume as an early radiological factor for clinical course prediction after aneurysmal subarachnoid hemorrhage. A pilot study

BackgroundThe pathological mechanisms following aneurysmal subarachnoid hemorrhage (SAH) are poorly understood. Limited clinical evidence exists on the association between cerebrospinal fluid (CSF) volume and the risk of delayed cerebral ischemia (DCI) or cerebral vasospasm (CV). In this study, we raised the hypothesis that the amount of CSF or its ratio to hemorrhage blood volume, as determined from non-contrast Computed Tomography (NCCT) images taken on admission, could be a significant predictor for CV and DCI. MethodsThe pilot study included a retrospective analysis of NCCT scans of 49 SAH patients taken shortly after an aneurysm rupture (33 males, 16 females, mean age 56.4 ± 15 years). The SynthStrip and Slicer3D software tools were used to extract radiological factors – CSF, brain, and hemorrhage volumes from the NCCT images. The “pure” CSF volume (VCSF) was estimated in the range of [−15, 15] Hounsfield units (HU). ResultsVCSF was negatively associated with the risk of CV occurrence (p = 0.0049) and DCI (p = 0.0069), but was not associated with patients’ outcomes. The hemorrhage volume (VSAH) was positively associated with an unfavorable outcome (p = 0.0032) but was not associated with CV/DCI. The ratio VSAH/VCSF was positively associated with, both, DCI (p = 0.031) and unfavorable outcome (p = 0.002). The CSF volume normalized by the brain volume showed the highest characteristics for DCI prediction (AUC = 0.791, sensitivity = 0.80, specificity = 0.812) and CV prediction (AUC = 0.769, sensitivity = 0.812, specificity = 0.70). ConclusionIt was demonstrated that “pure” CSF volume retrieved from the initial NCCT images of SAH patients (including CV, Non-CV, DCI, Non-DCI groups) is a more significant predictor of DCI and CV compared to other routinely used radiological biomarkers. VCSF could be used to predict clinical course as well as to personalize the management of SAH patients. Larger multicenter clinical trials should be performed to test the added value of the proposed methodology.

Predicting postoperative rehemorrhage in hypertensive intracerebral hemorrhage using noncontrast CT radiomics and clinical data with an interpretable machine learning approach

In hypertensive intracerebral hemorrhage (HICH) patients, while emergency surgeries effectively reduce intracranial pressure and hematoma volume, their significant risk of causing postoperative rehemorrhage necessitates early detection and management to improve patient prognosis. This study sought to develop and validate machine learning (ML) models leveraging clinical data and noncontrast CT radiomics to pinpoint patients at risk of postoperative rehemorrhage, equipping clinicians with an early detection tool for prompt intervention. The study conducted a retrospective analysis on 609 HICH patients, dividing them into training and external verification cohorts. These patients were categorized into groups with and without postoperative rehemorrhage. Radiomics features from noncontrast CT images were extracted, standardized, and employed to create several ML models. These models underwent internal validation using both radiomics and clinical data, with the best model’s feature significance assessed via the Shapley additive explanations (SHAP) method, then externally validated. In the study of 609 patients, postoperative rehemorrhage rates were similar in the training (18.8%, 80/426) and external verification (17.5%, 32/183) cohorts. Six significant noncontrast CT radiomics features were identified, with the support vector machine (SVM) model outperforming others in both internal and external validations. SHAP analysis highlighted five critical predictors of postoperative rehemorrhage risk, encompassing three radiomics features from noncontrast CT and two clinical data indicators. This study highlights the effectiveness of an SVM model combining radiomics features from noncontrast CT and clinical parameters in predicting postoperative rehemorrhage among HICH patients. This approach enables timely and effective interventions, thereby improving patient outcomes.