Photon-Counting CT in the Head and Neck: Current Applications and Future Prospects.

Photon-counting detectors (PCDs) represent a major milestone in the evolution of CT imaging. CT scanners using PCD systems have already been shown to generate images with substantially greater spatial resolution, superior iodine contrast-to-noise ratio, and reduced artifact compared with conventional energy-integrating detector-based systems. These benefits can be achieved with considerably decreased radiation dose. Recent studies have focused on the advantages of PCD-CT scanners in numerous anatomic regions, particularly the coronary and cerebral vasculature, pulmonary structures, and musculoskeletal imaging. However, PCD-CT imaging is also anticipated to be a major advantage for head and neck imaging. In this paper, we review current clinical applications of PCD-CT in head and neck imaging, with a focus on the temporal bone, facial bones, and paranasal sinuses; minor arterial vasculature; and the spectral capabilities of PCD systems.

Atherosclerotic carotid artery disease Radiomics: A systematic review with meta-analysis and radiomic quality score assessment.

BACKGROUND: Stroke, a leading global cause of mortality and neurological disability, is often associated with atherosclerotic carotid artery disease. Distinguishing between symptomatic and asymptomatic carotid artery disease is crucial for appropriate treatment decisions. Radiomics, a quantitative image analysis technique, and ML have emerged as promising tools in medical imaging, including neuroradiology. This systematic review and meta-analysis aimed to evaluate the methodological quality of studies employing radiomics for atherosclerotic carotid artery disease analysis and ML algorithms for culprit plaque identification using CT or MRI. MATERIALS AND METHODS: Pubmed, WoS and Scopus databases were searched for relevant studies published from January 2005 to May 2023. RQS assessed methodological quality of studies included in the review. QUADAS-2 assessed the risk of bias. A meta-analysis and three meta regressions were conducted on study performance based on model type, imaging modality and segmentation method. RESULTS: RQS assessed methodological quality, revealing an overall low score and consistent findings with other radiology domains. QUADAS-2 indicated an overall low risk, except for a single study with high bias. The meta-analysis demonstrated that radiomics-based ML models for predicting culprit plaques had a satisfactory performance, with an AUC of 0.85, surpassing clinical models. However, combining radiomics with clinical features yielded the highest AUC of 0.89. Meta-regression analyses confirmed these findings. MRI-based models slightly outperformed CT-based ones, but the difference was not significant. CONCLUSION: In conclusion, radiomics and ML hold promise for assessing carotid plaque vulnerability, aiding in early cerebrovascular event prediction. Combining radiomics with clinical data enhances predictive performance.

Deep Learning Based Reconstruction of 3D-T1-SPACE Vessel Wall Imaging Provides Improved Image Quality with Reduced Scan Times: A Preliminary Study.

BACKGROUND AND PURPOSE: Intra-cranial vessel wall imaging (IC-VWI) is technically challenging to implement, given the simultaneous requirements of high spatial resolution, excellent blood and CSF signal suppression and clinically acceptable gradient times. Herein, we present our preliminary findings on the evaluation of a deep learning optimized sequence using T1 weighted imaging. MATERIALS AND METHODS: Clinical and optimized Deep learning-based image reconstruction (DLBIR) T1 SPACE sequences were evaluated, comparing non-contrast sequences in ten healthy controls and post-contrast sequences in five consecutive patients. Images were reviewed on a Likert-like scale by four fellowship-trained neuroradiologists. Scores (range 1-4) were separately assigned for eleven vessel segments in terms of vessel wall and lumen delineation. Additionally, images were evaluated in terms of overall background noise, image sharpness and homogenous CSF signal. Segment-wise scores were compared using paired samples t-tests. RESULTS: The scan time for the clinical and DLBIR sequences were 7:26 minutes and 5:23 minutes respectively. DLBIR images showed consistently higher wall signal and lumen visualization scores, with the differences being statistically significant in the majority of vessel segments on both pre and post contrast images. DLBIR images had lower background noise, higher image sharpness and uniform CSF signal. Depiction of intracranial pathologies was better or similar on the DLBIR images. CONCLUSIONS: Our preliminary findings suggest that DLBIR optimized IC-VWI sequences may be helpful in achieving shorter gradient times with improved vessel wall visualization and overall image quality. These improvements may help with wider adoption of ICVWI in clinical practice and should be further validated on a larger cohort. ABBREVIATIONS: DL deep learning; VWI = vessel wall imaging.

Machine Learning Detects Symptomatic Plaques in Patients With Carotid Atherosclerosis on CT Angiography.

BACKGROUND: This study aimed to develop and validate a computed tomography angiography based machine learning model that uses plaque composition data and degree of carotid stenosis to detect symptomatic carotid plaques in patients with carotid atherosclerosis. METHODS: The machine learning based model was trained using degree of stenosis and the volumes of 13 computed tomography angiography derived intracarotid plaque subcomponents (eg, lipid, intraplaque hemorrhage, calcium) to identify plaques associated with cerebrovascular events. The model was internally validated through repeated 10-fold cross-validation and tested on a dedicated testing cohort according to discrimination and calibration. RESULTS: This retrospective, single-center study evaluated computed tomography angiography scans of 268 patients with both symptomatic and asymptomatic carotid atherosclerosis (163 for the derivation set and 106 for the testing set) performed between March 2013 and October 2019. The area-under-receiver-operating characteristics curve by machine learning on the testing cohort (0.89) was significantly higher than the areas under the curve of traditional logit analysis based on the degree of stenosis (0.51, P<0.001), presence of intraplaque hemorrhage (0.69, P<0.001), and plaque composition (0.78, P<0.001), respectively. Comparable performance was obtained on internal validation. The identified plaque components and associated cutoff values that were significantly associated with a higher likelihood of symptomatic status after adjustment were the ratio of intraplaque hemorrhage to lipid volume (≥50%, 38.5 [10.1-205.1]; odds ratio, 95% CI) and percentage of intraplaque hemorrhage volume (≥10%, 18.5 [5.7-69.4]; odds ratio, 95% CI). CONCLUSIONS: This study presented an interpretable machine learning model that accurately identifies symptomatic carotid plaques using computed tomography angiography derived plaque composition features, aiding clinical decision-making.

The left atrial appendage: An enigmatic friend or foe and implications of closure.

The left atrial appendage (LAA) is often thought of as a vestigial organ serving as a nidus for clot formation in those with atrial fibrillation (A-fib). The LAA, however, has unique anatomy which allows it to serve special functions in the human body. Closing the LAA has been shown to decrease the risk of thromboembolic events in patients who cannot tolerate anticoagulation. Several methods of closure exist including percutaneous endocardial closure, epicardial closure, and surgical clipping. In addition to decreasing stroke risk, there appears to be physiologic changes that occur after LAA closure. This comprehensive review aims to describe the functions of the LAA, compare the different methods of closure, and propose a new method for identifying which patients may benefit from LAA closure versus anticoagulation based on each patients' individual comorbidities rather than their contraindications.

Radiomics and artificial intelligence: General notions and applications in the carotid vulnerable plaque.

Carotid atherosclerosis plays a substantial role in cardiovascular morbidity and mortality. Given the multifaceted impact of this disease, there has been increasing interest in harnessing artificial intelligence (AI) and radiomics as complementary tools for the quantitative analysis of medical imaging data. This integrated approach holds promise not only in refining medical imaging data analysis but also in optimizing the utilization of radiologists' expertise. By automating time consuming tasks, AI allows radiologists to focus on more pertinent responsibilities. Simultaneously, the capacity of AI in radiomics to extract nuanced patterns from raw data enhances the exploration of carotid atherosclerosis, advancing efforts in terms of (1) early detection and diagnosis, (2) risk stratification and predictive modeling, (3) improving workflow efficiency, and (4) contributing to advancements in research. This review provides an overview of general concepts related to radiomics and AI, along with their application in the field of carotid vulnerable plaque. It also offers insights into various research studies conducted on this topic across different imaging techniques.

Carotid artery calcium score: Definition, classification, application, and limits.

INTRODUCTION: In the current paper, the "carotid artery calcium score" method is presented with the target to offer a metric method to quantify the amount of calcification in the carotid artery. MODEL AND DEFINITION: The Volume of Interest (VOI) should be extracted and those voxels, with a Hounsfield Unit (HU) value ≥130, should be considered. The total weight value is determined by calculating the sum of the HU attenuation values of all voxels with values ≥130 HU. This value should be multiplied by the conversion factor ("or voxel size") and divided by a weighting factor, the attenuation threshold to consider a voxel as calcified (and therefore 130 HU): this equation determines the Carotid Artery Calcium Score (CACS). RESULTS: In order to provide the demonstration of the potential feasibility of the model, the CACS was calculated in 131 subjects (94 males; mean age 72.7 years) for 235 carotid arteries (in 27 subjects, unilateral plaque was present) considered. The CACS value ranged from 0.67 to 11716. A statistically significant correlation was found (rho value = 0.663, p value = .0001) between the CACS in the right and left carotid plaques. Moreover, a statistically significant correlation between the age and the total CACS was present (rho value = 0.244, p value = .005), whereas no statistically significant difference was found in the distribution of CACS by gender (p = .148). The CACS was also tested at baseline and after contrast and no statistically significant difference was found. CONCLUSION: In conclusion, this method is of easy application, and it weights at the same time the volume and the degree of calcification in a unique parameter. This method needs to be tested to verify its potential utility, similar to the coronary artery calcium score, for the risk stratification of the occurrence of cerebrovascular events of the anterior circulation. Further studies using this new diagnostic tool to determine the prognostic value of carotid calcium quantification are needed.

SNAPSHOT USA 2021: A third coordinated national camera trap survey of the United States.

SNAPSHOT USA is a multicontributor, long-term camera trap survey designed to survey mammals across the United States. Participants are recruited through community networks and directly through a website application (https://www.snapshot-usa.org/). The growing Snapshot dataset is useful, for example, for tracking wildlife population responses to land use, land cover, and climate changes across spatial and temporal scales. Here we present the SNAPSHOT USA 2021 dataset, the third national camera trap survey across the US. Data were collected across 109 camera trap arrays and included 1711 camera sites. The total effort equaled 71,519 camera trap nights and resulted in 172,507 sequences of animal observations. Sampling effort varied among camera trap arrays, with a minimum of 126 camera trap nights, a maximum of 3355 nights, a median 546 nights, and a mean 656 ± 431 nights. This third dataset comprises 51 camera trap arrays that were surveyed during 2019, 2020, and 2021, along with 71 camera trap arrays that were surveyed in 2020 and 2021. All raw data and accompanying metadata are stored on Wildlife Insights (https://www.wildlifeinsights.org/), and are publicly available upon acceptance of the data papers. SNAPSHOT USA aims to sample multiple ecoregions in the United States with adequate representation of each ecoregion according to its relative size. Currently, the relative density of camera trap arrays varies by an order of magnitude for the various ecoregions (0.22-5.9 arrays per 100,000 km2), emphasizing the need to increase sampling effort by further recruiting and retaining contributors. There are no copyright restrictions on these data. We request that authors cite this paper when using these data, or a subset of these data, for publication. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the US Government.

Impact of SUSAN Denoising and ComBat Harmonization on Machine Learning Model Performance for Malignant Brain Neoplasms.

BACKGROUND AND PURPOSE: Feature variability in radiomics studies due to technical and magnet strength parameters is well known and may be addressed through various pre-processing methods. However, very few studies have evaluated downstream impact of variable pre-processing on model classification performance in a multi-class setting. We sought to evaluate the impact of SUSAN denoising and ComBat harmonization on model classification performance. MATERIALS AND METHODS: A total of 493 cases (410 internal and 83 external dataset) of glioblastoma (GB), intracranial metastatic disease (IMD) and primary CNS lymphoma (PCNSL) underwent semi-automated 3D-segmentation post baseline image processing (BIP) consisting of resampling, realignment, co-registration, skull stripping and image normalization. Post BIP, two sets were generated, one with and another without SUSAN denoising (SD). Radiomics features were extracted from both datasets and batch corrected to produce four datasets: (a) BIP, (b) BIP with SD, (c) BIP with ComBat and (d) BIP with both SD and ComBat harmonization. Performance was then summarized for models using a combination of six feature selection techniques and six machine learning models across four mask-sequence combinations with features derived from one-three (multi-parametric) MRI sequences. RESULTS: Most top performing models on the external test set used BIP+SD derived features. Overall, use of SD and ComBat harmonization led to a slight but generally consistent improvement in model performance on the external test set. CONCLUSIONS: The use of image pre-processing steps such as SD and ComBat harmonization may be more useful in a multiinstitutional setting and improve model generalizability. Models derived from only T1-CE images showed comparable performance to models derived from multiparametric MRI.

Radiology-pathology correlation: Giant tumefactive perivascular spaces.

Dilated perivascular spaces (PVSs) are common and easily recognized on imaging. However, rarer giant tumefactive PVSs (GTPVSs) can have unusual multilocular cystic configurations, and are often confused for other pathologic entities, including neoplasms, cystic infarctions, and neuroepithelial cysts. Because GTPVSs are scarcely encountered and even more infrequently operated upon, many radiologists are unaware of the imaging and pathologic features of these lesions. Here, a case of a resected GTPVS is presented, highlighting both its radiologic and histologic characteristics, and discussing how such lesions can be differentiated from their closest mimickers on imaging.

A review of histopathologic and radiologic features of non-atherosclerotic pathologies of the extracranial carotid arteries.

Diseases of the carotid arteries can be classified into different categories based on their origin. Atherosclerotic carotid disease remains the most encountered arterial wall pathology. However, other less-common non-atherosclerotic diseases can have detrimental clinical consequences if not appropriately recognized. The underlying histological features of each disease process may result in imaging findings that possess features that are obvious of the disease. However, some carotid disease processes may have histological characteristics that manifest as non-specific radiologic findings. The purpose of this manuscript is to review various non-atherosclerotic causes of carotid artery disease as well as their histologic-radiologic characteristics to aid in the appropriate recognition of these less-commonly encountered pathologies.

High yield clinical applications for photon counting CT in neurovascular imaging.

Photon-counting CT (PCCT) uses a novel X-ray detection mechanism that confers many advantages over that used in traditional energy integrating CT. As PCCT becomes more available, it is important to thoroughly understand its benefits and highest yield areas for improvements in diagnosis of various diseases. Based on our early experience, we have identified several areas of neurovascular imaging in which PCCT shows promise. Here, we describe the benefits in diagnosing arterial and venous diseases in the head, neck, and spine. Specifically, we focus on applications in head and neck CT angiography (CTA), spinal CT angiography, and CT myelography for detection of CSF-venous fistulas. Each of these applications highlights the technological advantages of PCCT in neurovascular imaging. Further understanding of these applications will not only benefit institutions incorporating PCCT into their practices but will also help guide future directions for implementation of PCCT for diagnosing other pathologies in neuroimaging.

Benefits of Photon-Counting CT Myelography for Localization of Dural Tears in Spontaneous Intracranial Hypotension.

Photon-counting CT is an increasingly used technology with numerous advantages over conventional energy-integrating detector CT. These include superior spatial resolution, high temporal resolution, and inherent spectral imaging capabilities. Recently, photon-counting CT myelography was described as an effective technique for the detection of CSF-venous fistulas, a common cause of spontaneous intracranial hypotension. It is likely that photon-counting CT myelography will also have advantages for the localization of dural tears, a separate type of spontaneous spinal CSF leak that requires different myelographic techniques for accurate localization. To our knowledge, prior studies on photon-counting CT myelography have been limited to techniques for detecting CSF-venous fistulas. In this technical report, we describe our technique and early experience with photon-counting CT myelography for the localization of dural tears.

Imaging Findings Post-Stereotactic Radiosurgery for Vestibular Schwannoma: A Primer for the Radiologist.

Noninvasive tumor control of vestibular schwannomas through stereotactic radiosurgery allows high rates of long-term tumor control and has been used primarily for small- and medium-sized vestibular schwannomas. The posttreatment imaging appearance of the tumor, temporal patterns of growth and treatment response, as well as extratumoral complications can often be both subtle or confusing and should be appropriately recognized. Herein, the authors present an imaging-based review of expected changes as well as associated complications related to radiosurgery for vestibular schwannomas.

Intracranial findings in spontaneous intracranial hypotension: Does the severity of abnormalities correspond with certainty and/or multifocality of cerebrospinal fluid leaks?

BACKGROUND AND PURPOSE: Spontaneous intracranial hypotension (SIH) is caused by spinal cerebrospinal fluid (CSF) leaks. This study assessed whether the certainty and/or multifocality of CSF leaks is associated with the severity of intracranial sequelae of SIH. MATERIALS AND METHODS: A retrospective review was completed of patients with suspected SIH that underwent digital subtraction myelogram (DSM) preceded by brain MRI. DSMs were evaluated for the presence or absence of a CSF leak, categorized both as positive/negative/indeterminate and single versus multifocal. Brain MRIs were assessed for intracranial sequelae of SIH based on two probabilistic scoring systems (Dobrocky and Mayo methods). For each system, both an absolute "numerical" score (based on tabulation of findings) and "categorized" score (classification of probability) were tabulated. RESULTS: 174 patients were included; 113 (64.9%) were female, average age 52.0 ± 14.3 years. One or more definite leaks were noted in 76 (43.7%) patients; an indeterminate leak was noted in 22 (12.6%) patients. 16 (16.3%) had multiple leaks. There was no significant difference in the severity of intracranial findings between patients with a single versus multiple leaks (p values ranged from .36 to .70 using categorized scores and 0.22-0.99 for numerical scores). Definite leaks were more likely to have both higher categorized intracranial scores (Mayo p = .0008, Dobrocky p = .006) and numerical scores (p = .0002 for Mayo and p = .006 for Dobrocky). CONCLUSIONS: Certainty of a CSF leak on diagnostic imaging is associated with severity of intracranial sequelae of SIH, with definite leaks having significantly more intracranial findings than indeterminate leaks. Multifocal leaks do not cause greater intracranial abnormalities.