Non-contrast-enhanced Computed Tomography Research Articles

CT-based radiomics: A potential indicator of KRAS mutation in pulmonary adenocarcinoma.

This study aimed to validate a CT-based radiomics signature for predicting Kirsten rat sarcoma (KRAS) mutation status in lung adenocarcinoma (LADC). A total of 815 LADC patients were included. Radiomics features were extracted from non-contrast-enhanced CT (NECT) and contrast-enhanced CT (CECT) images using Pyradiomics. CT-based radiomics were combined with clinical features to distinguish KRAS mutation status. Four feature selection methods and four deep learning classifiers were employed. Data was split into 70% training and 30% test sets, with SMOTE addressing imbalance in the training set. Model performance was evaluated using AUC, accuracy, precision, F1 score, and recall. The analysis revealed that 10.4% of patients showed KRAS mutations. The study extracted 1061 radiomics features and combined them with 17 clinical features. After feature selection, two signatures were constructed using top 10, 20, and 50 features. The best performance was achieved using Multilayer Perceptron with 20 features. CECT, it showed 66% precision, 76% recall, 69% F1-score, 84% accuracy, and AUC of 93.3% and 87.4% for train and test sets, respectively. For NECT, accuracy was 85% and 82%, with AUC of 90.7% and 87.6% for train and test sets, respectively. CT-based radiomics signature is a noninvasive method that can predict KRAS mutation status of LADC when mutational profiling is unavailable.

Stone-event-free survival after retrograde intrarenal surgery: is the stone-free-status so relevant for the future outcomes?

The primary aim of stone treatment is to achieve stone-free status. Residual fragments can cause stone growth, recurrence, urinary tract infections, and ureteric obstruction. Our goal was to describe the natural history of stone burden after retrograde intrarenal surgery (RIRS) based on stone-free status (SFS), evaluating stone growth and stone-events. We retrospectively reviewed data from patients who underwent RIRS at a tertiary care center between October 2014 and September 2019. The stone burden was assessed by measuring the maximum diameter (mm) and volume (mm3). Patients were divided into four groups according to SFS-(A) absolute stone-free, no stones on non-contrast-enhanced computed tomography (NCCT); (B) relative stone-free with ≤ 2mm fragments, (C) relative stone-free with 2.1-4mm fragments, and (D) residual fragments > 4mm. Our main outcomes were stone growth over time (defined as an increase in diameter compared to first postoperative measurement) and incidence of stone-related events (pain or additional intervention to treat symptoms, obstruction, or removing fragments). A total of 98 patients were included in the study-42 were classified as absolute stone-free (Group A), 20 were categorized as relatively stone-free (Groups B and C), and 36 had a residual stone burden with fragments larger than 4mm (Group D) on postoperative NCCT. There was a significant difference in the number of stones among the groups (p < 0.001). The pre-operative stone volume differed significantly among the groups (p = 0.003). Group A had the lowest median total stone volume (551.3mm3). Twenty patients (20.4%) developed stone-events during a mean follow-up period of 62.3months (± 26.0). Stone-event-free survival differed significantly between the groups (p = 0.028), with Group D demonstrating a higher incidence of stone-related events post-RIRS compared to the other groups. Sixteen patients (16.3%) had renal colic requiring a hospital visit across all groups. Thirteen patients (13.3%) required re-intervention (3 patients belonged to Group A, 1 to Group B, 2 to Group C, and 7 to Group D). Group D shows a higher rate of stone-related events post-RIRS. Ensuring complete stone-free status after RIRS is crucial for treatment success. Other factors should be considered in the management, including ensuring compliance with general preventive measures and stone-specific pharmacological treatments to prevent recurrence.

Prediction of Ischemic Stroke Functional Outcomes from Acute-Phase Noncontrast CT and Clinical Information.

Background Clinical outcome prediction based on acute-phase ischemic stroke data is valuable for planning health care resources, designing clinical trials, and setting patient expectations. Existing methods require individualized features and often involve manually engineered, time-consuming postprocessing activities. Purpose To predict the 90-day modified Rankin Scale (mRS) score with a deep learning (DL) model fusing noncontrast-enhanced CT (NCCT) and clinical information from the acute phase of stroke. Materials and Methods This retrospective study included data from six patient datasets from four multicenter trials and two registries. The DL-based imaging and clinical model was trained by using NCCT data obtained 1-7 days after baseline imaging and clinical data (age; sex; baseline and 24-hour National Institutes of Health Stroke Scale scores; and history of hypertension, diabetes, and atrial fibrillation). This model was compared with models based on either NCCT or clinical information alone. Model-specific mRS score prediction accuracy, mRS score accuracy within 1 point of the actual mRS score, mean absolute error (MAE), and performance in identifying unfavorable outcomes (mRS score, >2) were evaluated. Results A total of 1335 patients (median age, 71 years; IQR, 60-80 years; 674 female patients) were included for model development and testing through sixfold cross validation, with distributions of 979, 133, and 223 patients across training, validation, and test sets in each of the six cross-validation folds, respectively. The fused model achieved an MAE of 0.94 (95% CI: 0.89, 0.98) for predicting the specific mRS score, outperforming the imaging-only (MAE, 1.10; 95% CI: 1.05, 1.16; P < .001) and the clinical information-only (MAE, 1.00; 95% CI: 0.94, 1.05; P = .04) models. The fused model achieved an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.92) for predicting unfavorable outcomes, outperforming the clinical information-only model (AUC, 0.88; 95% CI: 0.87, 0.90; P < .001) and the imaging-only model (AUC, 0.85; 95% CI: 0.84, 0.87; P < .001). Conclusion A fused DL-based NCCT and clinical model outperformed an imaging-only model and a clinical-information-only model in predicting 90-day mRS scores. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Lee in this issue.

A deep learning algorithm for the detection of aortic dissection on non-contrast-enhanced computed tomography via the identification and segmentation of the true and false lumens of the aorta.

Aortic dissection is a life-threatening clinical emergency, but it is often missed and misdiagnosed due to the limitations of diagnostic technology. In this study, we developed a deep learning-based algorithm for identifying the true and false lumens in the aorta on non-contrast-enhanced computed tomography (NCE-CT) scans and to ascertain the presence of aortic dissection. Additionally, we compared the diagnostic performance of this algorithm with that of radiologists in detecting aortic dissection. We included 320 patients with suspected acute aortic syndrome from three centers (Beijing Anzhen Hospital Affiliated to Capital Medical University, Fujian Provincial Hospital, and Xiangya Hospital of Central South University) between May 2020 and May 2022 in this retrospective study. All patients underwent simultaneous NCE-CT and contrast-enhanced CT (CE-CT). The cohort comprised 160 patients with aortic dissection and 160 without aortic dissection. A deep learning algorithm, three-dimensional (3D) full-resolution U-Net, was continuously trained and refined to segment the true and false lumens of the aorta to determine the presence of aortic dissection. The algorithm's efficacy in detecting dissections was evaluated using the receiver operating characteristic (ROC) curve, including the area under the curve (AUC), sensitivity, and specificity. Furthermore, a comparative analysis of the diagnostic capabilities between our algorithm and three radiologists was conducted. In diagnosing aortic dissection using NCE-CT images, the developed algorithm demonstrated an accuracy of 93.8% [95% confidence interval (CI): 89.8-98.3%], a sensitivity of 91.6% (95% CI: 86.7-95.8%), and a specificity of 95.6% (95% CI: 91.2-99.3%). In contrast, the radiologists achieved an accuracy of 88.8% (95% CI: 83.5-94.1%), a sensitivity of 90.6% (95% CI: 83.5-94.1%), and a specificity of 94.1% (95% CI: 72.9-97.6%). There was no significant difference between the algorithm's performance and radiologists' mean performance in accuracy, sensitivity, or specificity (P>0.05). The algorithm proficiently segments the true and false lumens in aortic NCE-CT images, exhibiting diagnostic capabilities comparable to those of radiologists in detecting aortic dissection. This suggests that the algorithm could reduce misdiagnoses in clinical practice, thereby enhancing patient care.

Prognostic value of CT scan-based radiomics in intracerebral hemorrhage patients: A systematic review and meta-analysis

ObjectivesWe conducted a systematic review and meta-analysis of current publications on the potential role of non-contrast-enhanced computed tomography (NCCT) radiomics as a prognostic indicator in patients with intracerebral hemorrhage (ICH). MethodsWe systematically searched PubMed, EMBASE, and the Web of Science from inception until January 8, 2024. Studies with NCCT-based radiomics features for predicting the prognostic outcomes of ICH patients were included. We calculated the pooled sensitivity, specificity, diagnostic odds ratio (DOR), and area under curve (AUC) values. The radiomics quality score (RQS), METhodological RadiomICs Score (METRICS), and the quality assessment of diagnostic accuracy studies (QUADAS-2) were used for quality assessment. ResultsTwenty-two studies were included. The pooled sensitivity, specificity, DOR, and AUC of radiomics models were 0.73, 0.78, 10.03, and 0.83, respectively, while on the combined radiomics models with other non-radiomics features were 0.80, 0.80, 16.28, and 0.86. Subgroup analysis showed that studies with the following covariates have a higher accuracy: single center, modified Rankin Scale (mRS) criteria for the ICH outcomes assessment, following patients for evaluation of ICH outcomes for more than a month, automatic segmentation, capturing the radiomics feature from the only intra-hematomal region, using PyRadiomic tool for features extraction, and using non-logistic regression for modeling. The quality of literature using QUADAS-2 and METRICS tools was good and was under-average using the RQS tool. No publication bias was detected. ConclusionsRadiomics features showed moderate to high accuracy for predicting ICH prognostic outcomes. Although the QUADAS-2 and METRICS assessments indicated good quality, the radiomics pipeline quality was under-average. Clinical RelevanceNCCT-based radiomics features can provide information about the prognostic outcomes of ICH patients after patient admission. This study exploits the value of current evidence on NCCT-based radiomics methodology in the prediction of ICH prognosis.

Exploring the potential of combined B-mode features and color Doppler ultrasound in the diagnosis of ureteric stone as an alternative to ionizing radiation exposure by computed tomography.

To assess the diagnostic efficacy of integrating B-mode and color Doppler capabilities of ultrasound (US) to establish a robust standalone diagnostic tool for the diagnosis of ureteric stones as an alternative to non-contrast-enhanced computed tomography (NCCT). A total of 140 consecutive patients diagnosed with ureteric stones using NCCT were enrolled. On the same day, US in both B-mode and Color Doppler was performed by an experienced radiologist who was blinded to the NCCT scan results. The diagnostic rate of US for stone detection was recorded. Additionally, baseline patient and stone characteristics were analyzed for their association with the accuracy of stone detection using US. US exhibited a high sensitivity of 91.43%, detecting 128 out of 140 stone foci. Notably, ureteric stones in the proximal and uretero-vesical junction (UVJ) segments were readily identifiable compared to those in the pelvic region (p = 0.0003). Additionally, hydronephrosis enhanced the US's ability to detect stones (p < 0.0001). Conversely, abdominal gases and obesity adversely affected US capabilities (p < 0.0001 and p = 0.009, respectively). Stone side, size, and density showed no statistically significant impact (p > 0.05). US with its color Doppler capabilities could serve as a reliable and safe alternative imaging modality in the diagnostic work up of patients with ureterolithiasis. Factors including stone location, Hydronephrosis, weight and abdominal gases significantly influenced its accuracy.

RFLSE: Joint radiomics feature‐enhanced level‐set segmentation for low‐contrast SPECT/CT tumour images

AbstractDoctors typically use non‐contrast‐enhanced computed tomography (NCECT) in the treatment of kidney cancer to map kidney and tumour structural information to functional imaging single‐photon emission computed tomography, which is then used to assess patient kidney function and predict postoperative recovery. However, the assessment of kidney function and formulation of surgical plans is constrained by the low contrast of tumours in NCECT, which hinders the acquisition of accurate tumour boundaries. Therefore, this study designed a radiomics feature‐enhanced level‐set evolution (RFLSE) to precisely segment small‐sample low‐contrast kidney tumours. Integration of high‐dimensional radiomics features into the level‐set energy function enhances the edge detection capability of low‐contrast kidney tumours. The use of sensitive radiomics features to control the regional term parameters achieves adaptive adjustment of the curve evolution amplitude, improving the level‐set segmentation process. The experimental data used low‐contrast, limited‐sample tumours provided by hospitals, as well as the public datasets BUSI18 and KiTS19. Comparative results with advanced energy functionals and deep learning models demonstrate the precision and robustness of RFLSE segmentation. Additionally, the application value of RFLSE in assisting doctors with accurately marking tumours and generating high‐quality pseudo‐labels for deep learning datasets is demonstrated.

The role of CT brain findings in the early diagnosis of infantile encephalitic beriberi.

Thiamine deficiency disease may occur in infants from thiamine-deficient mothers in developing countries, as well as in infants fed solely with soy-based formula. Thiamine deficiency in infants may present with acute neurological manifestations of infantile encephalitic beriberi. To review the role of noncontrast CT brain findings in infantile encephalitic beriberi in early diagnosis. A retrospective review of noncontrast CT scans of the brain in 21 infants with acute-onset infantile encephalitic beriberi was carried out. On noncontrast-enhanced CT brain, hypodense lesions were seen symmetrically in the putamen in all the babies; symmetric hypodensities were seen in the caudate nuclei in 14/21 (67%), in dorsomedial thalami/hypothalamic/subthalamic area in 4/21 (19%), and in the globi pallidi in 2/21 (9.5%) of the infants. Recognition of symmetrical hypodense lesions in the basal ganglia and medial thalami/hypothalamic/subthalamic area on noncontrast CT scan of the brain are important early features to recognize in encephalitic beriberi in at-risk infants. IEBB is a cause of hypodense bilateral basal ganglia and may be identified by this finding in the appropriate clinical settings.

The ratio of the maximum density values: a new method for predicting hemorrhagic transformation in acute ischemic stroke patients undergoing mechanical thrombectomy.

It is challenging yet critical to differentiate between hemorrhagic transformation (HT) and contrast extravasation on non-contrast-enhanced computed tomography (NCCT) scans following mechanical thrombectomy (MT) in patients with acute ischemic stroke. We propose a new method called the ratio of maximum density values (RMDV) to minimize the confusion of contrast extravasation and to evaluate the diagnostic significance of RMDV in predicting HT on immediate post-interventional NCCT scans. We conducted a retrospective analysis of the prospective patients' database who received MT for acute ischemic stroke caused by occlusion of the intracranial large artery and showed postinterventional cerebral hyperdensities (PCHDs) on NCCT scans immediately after MT. Based on the subsequent NCCT scans, we divided patients with PCHDs into the HT and the non-HT groups. The clinical characters and radiological details were collected and compared to the two groups. We assessed the ability of RMDV >1 to predict HT by analyzing the receiver operating characteristic curve. One hundred and three patients showed PCHDs; 58 (56.31%) were classified as HT, while 45 (43.69%) were classified as non-HT. The only notable distinction between the two groups was the proportion of RMDV >1 in the HT group. The correlation between HT and RMDV >1 with an area under the curve of 0.826 (95% confidence interval, 0.739 to 0.894). The sensitivity, specificity, positive, and negative predictive values of RMDV >1 on NCCT for predicting HT were 89.66, 75.56, 82.54, and 85.00%, respectively. The utilization of RMDV >1 on immediate NCCT scans after MT can predict early HT with good sensitivity and specificity.

A deep learning approach to remove contrast from contrast-enhanced CT for proton dose calculation.

Non-Contrast Enhanced CT (NCECT) is normally required for proton dose calculation while Contrast Enhanced CT (CECT) is often scanned for tumor and organ delineation. Possible tissue motion between these two CTs raises dosimetry uncertainties, especially for moving tumors in the thorax and abdomen. Here we report a deep-learning approach to generate NCECT directly from CECT. This method could be useful to avoid the NCECT scan, reduce CT simulation time and imaging dose, and decrease the uncertainties caused by tissue motion between otherwise two different CT scans. A deep network was developed to convert CECT to NCECT. The network receives a 3D image from CECT images as input and generates a corresponding contrast-removed NCECT image patch. Abdominal CECT and NCECT image pairs of 20 patients were deformably registered and 8000 image patch pairs extracted from the registered image pairs were utilized to train and test the model. CTs of clinical proton patients and their treatment plans were employed to evaluate the dosimetric impact of using the generated NCECT for proton dose calculation. Our approach achieved a Cosine Similarity score of 0.988 and an MSE value of 0.002. A quantitative comparison of clinical proton dose plans computed on the CECT and the generated NCECT for five proton patients revealed significant dose differences at the distal of beam paths. V100% of PTV and GTV changed by 3.5% and 5.5%, respectively. The mean HU difference for all five patients between the generated and the scanned NCECTs was ∼4.72, whereas the difference between CECT and the scanned NCECT was ∼64.52, indicating a ∼93% reduction in mean HU difference. A deep learning approach was developed to generate NCECTs from CECTs. This approach could be useful for the proton dose calculation to reduce uncertainties caused by tissue motion between CECT and NCECT.

Comparison of preoperative CT- and MRI-based multiparametric radiomics in the prediction of lymph node metastasis in rectal cancer

ObjectiveTo compare computed tomography (CT)- and magnetic resonance imaging (MRI)-based multiparametric radiomics models and validate a multi-modality, multiparametric clinical-radiomics nomogram for individual preoperative prediction of lymph node metastasis (LNM) in rectal cancer (RC) patients.Methods234 rectal adenocarcinoma patients from our retrospective study cohort were randomly selected as the training (n = 164) and testing (n = 70) cohorts. The radiomics features of the primary tumor were extracted from the non-contrast enhanced computed tomography (NCE-CT), the enhanced computed tomography (CE-CT), the T2-weighted imaging (T2WI) and the gadolinium contrast-enhanced T1-weighted imaging (CE-TIWI) of each patient. Three kinds of models were constructed based on training cohort, including the Clinical model (based on the clinical features), the radiomics models (based on NCE-CT, CE-CT, T2WI, CE-T1WI, CT, MRI, CT combing with MRI) and the clinical-radiomics models (based on CT or MRI radiomics model combing with clinical data) and Clinical-IMG model (based on CT and MRI radiomics model combing with clinical data). The performances of the 11 models were evaluated via the area under the receiver operator characteristic curve (AUC), accuracy, sensitivity, and specificity in the training and validation cohort. Differences in the AUCs among the 11 models were compared using DeLong’s test. Finally, the optimal model (Clinical-IMG model) was selected to create a radiomics nomogram. The performance of the nomogram to evaluate clinical efficacy was verified by ROC curves and decision curve analysis (DCA).ResultsThe MRI radiomics model in the validation cohort significantly outperformed than CT radiomics model (AUC, 0.785 vs. 0.721, p&amp;lt;0.05). The Clinical-IMG nomogram had the highest prediction efficiency than all other predictive models (p&amp;lt;0.05), of which the AUC was 0.947, the sensitivity was 0.870 and the specificity was 0.884.ConclusionMRI radiomics model performed better than both CT radiomics model and Clinical model in predicting LNM of RC. The clinical-radiomics nomogram that combines the radiomics features obtained from both CT and MRI along with preoperative clinical characteristics exhibits the best diagnostic performance.

Hematuria: Is it useful in predicting renal or ureteral stones in patient presenting to emergency department with flank pain?

The objective of the study was to evaluate hematuria as a diagnostic test for renal and ureteral stones compared with a noncontrast-enhanced computed tomography (CT) scan (gold standard test) in emergency room patients with acute flank pain. In total, 604 patients treated in our emergency department from 2006 to 2011, with a history of flank pain and suspected urolithiasis were included in a retrospective review. All patients were evaluated with a noncontrast-enhanced CT scan and urine analysis. Using the noncontrast CT scan as the gold standard for the evaluation of the presence, number, size, and site (renal or ureteral [upper, middle, and lower]) of the stones, we calculated the sensitivity, specificity, and positive and negative predictive values of hematuria for diagnosing both renal and ureteral stones. Urolithiasis was diagnosed in 388 patients (64%) and 216 patients (36%) had no stones on a noncontrast-enhanced CT scan. The sensitivity, specificity, positive predictive value, and negative predictive value for microhematuria were 77%, 33%, 67%, and 45%, respectively. Microhematuria was more common in patients with ureteral stones only (139 patients) and had a sensitivity of 85% compared to patients with renal stones only (32 patients), with a sensitivity of 55% (P < 0.001). There were no significant differences in the specificity or positive or negative predictive values. Although microhematuria is more sensitive to ureteral stones, the absence of microhematuria does not exclude the possibility of urolithiasis and a noncontrast-enhanced CT scan should be the gold standard diagnostic tool.

Clinical Reproducibility of the Stone Volume Measurement: A "Kidney Stone Calculator" Study.

An accurate estimation of the stone burden is the key factor for predicting retrograde intra-renal surgical outcomes. Volumetric calculations better stratify stone burden than linear measurements. We developed a free software to assess the stone volume and estimate the lithotrity duration according to 3D-segmented stone volumes, namely the Kidney Stone Calculator (KSC). The present study aimed to validate the KSC's reproducibility in clinical cases evaluating its inter-observer and intra-observer correlations. Fifty patients that harbored renal stones were retrospectively selected from a prospective cohort. For each patient, three urologists with different experience levels in stone management made five measurements of the stone volume on non-contrast-enhanced computed tomography (NCCT) images using the KSC. the overall inter-observer correlation (Kendall's concordance coefficient) was 0.99 (p < 0.0001). All three paired analyses of the inter-observer reproducibility were superior to 0.8. The intra-observer variation coefficients varied from 4% to 6%, and Kendall's intra-observer concordance coefficient was found to be superior to 0.98 (p < 0.0001) for each participant. Subgroup analyses showed that the segmentation of complex stones seems to be less reproductible. The Kidney Stone Calculator is a reliable tool for the stone burden estimation. Its extension for calculating the lithotrity duration is of major interest and could help the practitioner in surgical planning.

Aorta and main pulmonary artery segmentation using stacked U-Net and localization on non-contrast-enhanced computed tomography images.

The contact between the aorta, main pulmonary artery (MPA), main pulmonary vein, vena cava (VC), and esophagus affects segmentation of the aorta and MPA in non-contrast-enhanced computed tomography (NCE-CT) images. A two-stage stacked U-Net and localization of the aorta and MPA were developed for the segmentation of the aorta and MPA in NCE-CT images. Normal-dose NCE-CT images of 24 subjects with chronic thromboembolic pulmonary hypertension (CTEPH) and low-dose NCE-CT images of 100 subjects without CTEPH were used in this study. The aorta is in contact with the ascending aorta (AA) and MPA, the AA with the VC, the aortic arch (AR) with the VC and esophagus, and the descending aorta (DA) with the esophagus. These contact surfaces were manually annotated. The contact surfaces were quantified using the contact surface ratio (CSR). Segmentation of the aorta and MPA in NCE-CT images was performed by localization of the aorta and MPA and a two-stage stacked U-Net. Localization was performed by extracting and processing the trachea and main bronchus. The first stage of the stacked U-Net consisted of a 2D U-Net, 2D U-Net with a pre-trained VGG-16 encoder, and 2D attention U-Net. The second stage consisted of a 3D U-Net with four input channels: the CT volume and three segmentation results of the first stage. The model was trained and tested using 10-fold cross-validation. Segmentation of the entire volume was evaluated using the Dice similarity coefficient (DSC). Segmentation of the contact area was also assessed using the mean surface distance (MSD). The statistical analysis of the evaluation underwent a multi-comparison correction. CTEPH and non-CTEPH cases were classified based on the vessel diameters measured from the segmented MPA. For the noncontact surfaces of AA, the MSD of stacked U-Net was 0.31±0.10mm (p<0.05) and 0.32±0.13mm (p<0.05) for non-CTEPH and CTEPH cases, respectively. For contact surfaces with a CSR of 0.4 or greater in AA, the MSD was 0.52±0.23mm (p<0.05), and 0.68±0.29mm (p>0.05) for non-CTEPH and CTEPH cases, respectively. MSDs were lower than those of 2D and 3D U-Nets for contact and noncontact surfaces; moreover, MSDs increased slightly with larger CSRs. However, the stacked U-Net achieved MSDs of approximately 1pixel for a wide contact surface. The area under the receiver operating characteristic curve for CTEPH and non-CTEPH classification using the right main pulmonary artery (RMPA) diameter was 0.97 (95% confidence interval [CI]: 0.94-1.00). Segmentation of the aorta and MPA on NCE-CT images were affected by vascular and esophageal contact. The application of stacked U-Net and localization techniques for non-CTEPH and CTEPH cases mitigated the impact of contact, suggesting its potential for diagnosing CTEPH.

Prevalence of malignant or possibly malignant renal masses among homogeneous low-attenuation masses that are too small to characterize at computed tomography.

Homogeneous low-attenuation renal masses that are too small to characterize (tstc) are considered clinically insignificant; however, based primarily on expert opinion. To determine the prevalence of malignant or possibly malignant masses among homogeneous low-attenuation renal masses that are tstc. This retrospective cross-sectional study evaluated 75 patients with 104 tstc who underwent renal CT and MRI between Jan 2016 and Jul 2022. Low-attenuation renal masses measuring < 1cm in size were identified and, independently evaluated by two blinded radiologists measuring attenuation (Hounsfield Units, HU) at non-contrast enhanced CT (NECT) and nephrographic phase contrast-enhanced (CE)-CT when possible. Reference standard for benign cyst was MRI and for other renal masses was pathology or MRI showing enhancement. Average tstc size was 6 ± 2 (range 2-10) mm. Considering only incidental tstc (CT performed for another reason), 100% (98/98, 95%CI 96-100%) tstc were benign. Overall, considering both incidental and tstc referred for further characterization, there were 94% (98/104; 95% Confidence Intervals [CIs] 88-98%) benign cysts and 6% (6/104; 95%CI 2-12%) other masses (1 Bosniak 2F cystic mass, 2 probable renal cell carcinoma (RCC), three metastases). Pseudoenhancement, attenuation change > 10 HU or > 20 HU, was present in 29% (15/59) and 12% (7/59) benign cysts. All six other masses enhanced by > 20 HU. CECT threshold of ≤ 30 HU correctly classified 62% of benign cysts (61/98). All six other masses measured > 30 HU at CECT. The prevalence of malignant or possibly malignant renal masses among homogeneous low-attenuation too small to characterize masses among incidental tstc masses is near zero. Attenuation measurements misclassify a substantial proportion of these cysts, likely due to their small size.

Diagnostic Sensitivity of Unenhanced CT for Cerebral Venous Thrombosis: Can Clot Density Measurement Replace CT Venogram?

Objectives Cerebral venous sinus thrombosis is an important cause of stroke in young adults. Noncontrast-enhanced CT head (NECT) is almost always the first investigation. Our objectives were as follows: 1. How accurately does venous sinus density on NECT predict the presence of clot on CT venogram (CTV)? 2. Whether repeated measurements changed the confidence? 3. How many venous sinus thrombus would be missed if we do not do a CTV? 4. Can clot density measurement replace CTV? Methods Multicenter case-control study was designed with data from seven hospitals. Inclusion criteria: all CT and magnetic resonance imaging venograms with a prior NECT, performed between 1.1.2018 and 31.12.2018 (12 months), were included. Hounsfield unit (HU) values were calculated at the site of highest density on the NECT. Logistic regression analysis was performed using STATA. Result Two-hundred seventy-seven cases met the criteria with 33 positive cerebral venous thrombosis (density on NECT 60-92 HU) and 244 negative examinations (density on NECT 31-68 HU). Area under the curve for average clot density on NECT was 0.9984. Conclusion We found a strong relationship between sinus density on NECT and outcome of CTV. Repeating density measurements did not add any predictive value or changed outcome. Advances in Knowledge Density 70 HU or higher on NECT always resulted in a positive CTV but would miss a fifth of the positives. Cutoff at 60 HU would not miss any but result in significant false positives. An efficient option could be to limit CTV to sinus densities 60 to 70 HU only. However, a larger study would be required for such change in practice.

Abstract TP98: Deep Learning-based Automatic Ischemic Core Estimation Based On Non-contrastenhanced Computed Tomography

Background/Purpose: With the spread of thrombus retrieval procedures, the demand for immediate diagnosis and severity assessment of ischemic stroke is increasing, but current standard method using ASPECTS is semi-quantitative, and has low consistency among physicians. We develop and validate the fully automatic machine learning-based ischemic core segmentation model based only on non-contrast-enhanced computed tomography (NCCT). Materials and Methods: This multicenter retrospective study included patients with anterior circulation acute ischemic stroke who received both CT and MRI before thrombolysis or recanalization treatment between 2013 to 2019. The ischemic core on CT was manually delineated referencing the DWI and ADC map. A deep learning-based ischemic core segmentation model was developed using the derivation cohort data from 3 institutions (n=313), and the model performance was validated on the external validation cohort data from 3 institutions (n=106). Results: On the validation cohort, the median time between CT and MRI was 18 min. The ischemic core volume calculated by the DL model was significantly correlated with the reference standard (Pearson r=0.91, p&lt;.001). The correlation was significant both in early time window (&lt;4.5hr from onset; Pearson r=0.91, p&lt;.0.01) and the late time window (&gt;4.5hr from onset; Pearson r=0.93, p&lt;0.01). The median difference between model and reference standard was 4.7 mL (IQR, 0.8-12.4 mL). The DL model displayed high accuracy on discriminating large ischemic core (&gt;70mL) with a sensitivity of 84.2%, specificity of 97.7%, and AUC of 0.91. Conclusions: A segmentation model of cerebral ischemic core volume of the anterior circulation based on NCCT using deep learning showed good correlation with the correct labels generated with reference to MRI.

Cephalhaematoma Mimicking an Extradural Haematoma due to MirrorImage Artifact on Sonography in a Term Neonate: A Case Report

Cephalhaematomas and subgaleal haematomas are among the most common birth injuries and are associated with birth trauma, forceps, and vacuum-assisted deliveries. They present as scalp swelling and are usually identified shortly after birth. During sonographic examination, if an ultrasound beam scatters off a mirror-like interface, it creates mirror-image artifacts that can cause a diagnostic dilemma. In this case report, a six-day-old neonate presented with a right-side parietal cephalhaematoma that appeared to resemble an epidural haematoma on routine sonographic examination. Gray scale ultrasound revealed an anechoic structure resembling an epidural haematoma in the right parietal region. However, a non-contrast-enhanced computed tomography (NECT) scan of the brain showed a cephalhaematoma without an underlying epidural haematoma. Further evaluation using colour Doppler sonography revealed normal vascular findings within an anechoic space, and gray scale imaging in the sagittal plane showed normal cerebral parenchyma without midline shift. These findings helped identify the observed structure as a mirror-image artifact. It is important to note that these artifacts can lead to diagnostic errors, resulting in additional investigations and causing anxiety for parents. Understanding and being aware of these artifacts can help avoid unnecessary imaging and reduce radiation exposure.

Automated estimation of ischemic core volume on noncontrast-enhanced CT via machine learning.

Accurate estimation of ischemic core on baseline imaging has treatment implications in patients with acute ischemic stroke (AIS). Machine learning (ML) algorithms have shown promising results in estimating ischemic core using routine noncontrast computed tomography (NCCT). We used an ML-trained algorithm to quantify ischemic core volume on NCCT in a comparative analysis to pretreatment magnetic resonance imaging (MRI) diffusion-weighted imaging (DWI) in patients with AIS. Patients with AIS who had both pretreatment NCCT and MRI were enrolled. An automatic segmentation ML approach was applied using Brainomix software (Oxford, UK) to segment the ischemic voxels and calculate ischemic core volume on NCCT. Ischemic core volume was also calculated on baseline MRI DWI. Comparative analysis was performed using Bland-Altman plots and Pearson correlation. A total of 72 patients were included. The time-to-stroke onset time was 134.2/89.5 minutes (mean/median). The time difference between NCCT and MRI was 64.8/44.5 minutes (mean/median). In patients who presented within 1 hour from stroke onset, the ischemic core volumes were significantly (p = 0.005) underestimated by ML-NCCT. In patients presented beyond 1 hour, the ML-NCCT estimated ischemic core volumes approximated those obtained by MRI-DWI and with significant correlation (r = 0.56, p < 0.001). The ischemic core volumes calculated by the described ML approach on NCCT approximate those obtained by MRI in patients with AIS who present beyond 1 hour from stroke onset.

Artificial intelligence-driven ASPECTS for the detection of early stroke changes in non-contrast CT: a systematic review and meta-analysis

BackgroundRecent advances in machine learning have enabled development of the automated Alberta Stroke Program Early CT Score (ASPECTS) prediction algorithms using non-contrast enhanced computed tomography (NCCT) scans. The applicability of...