BACKGROUND: Gastrointestinal stromal tumors (GISTs) are clinically heterogeneous with various malignant potential in different individuals. It is crucial to explore a reliable method for preoperative risk stratification of gastric GISTs noninvasively.
OBJECTIVE: To establish and evaluate a machine learning model using the combination of computed tomography (CT) morphology, radiomics, and deep learning features to predict the risk stratification of primary gastric GISTs preoperatively.
METHODS: The 193 gastric GISTs lesions were randomly divided into training set, validation set, and test set in a ratio of 6:2:2. The qualitative and quantitative CT morphological features were assessed by two radiologists. The tumors were segmented manually, and then radiomic features were extracted using PyRadiomics and the deep learning features were extracted using pre-trained Resnet50 from arterial phase and venous phase CT images, respectively. Pearson correlation analysis and recursive feature elimination were used for feature selection. Support vector machines were employed to build a classifier for predicting the risk stratification of GISTs. This study compared the performance of models using different pre-trained convolutional neural networks (CNNs) to extract deep features for classification, as well as the performance of modeling features from single-phase and dual-phase images. The arterial phase, venous phase and dual-phase machine learning models were built, respectively, and the morphological features were added to the dual-phase machine learning model to construct a combined model. Receiver operating characteristic (ROC) curves were used to evaluate the efficacy of each model. The clinical application value of the combined model was determined through the decision curve analysis (DCA) and the net reclassification index (NRI) was analyzed.
RESULTS: The area under the curve (AUC) of the dual-phase machine learning model was 0.876, which was higher than that of the arterial phase model or venous phase model (0.813, 0.838, respectively). The combined model had best predictive performance than the above models with an AUC of 0.941 (95% CI: 0.887-0.974) (p = 0.012, Delong test). DCA demonstrated that the combined model had good clinical application value with an NRI of 0.575 (95% CI: 0.357-0.891).
CONCLUSIONS: In this study, we established a combined model that incorporated dual-phase morphology, radiomics, and deep learning characteristics, which can be used to predict the preoperative risk stratification of gastric GISTs.

BACKGROUND: The study of central nervous system (CNS) tumors is particularly relevant in the pediatric population because of their relatively high frequency in this demographic and the significant impact on disease- and treatment-related morbidity and mortality. While both morphological and non-morphological magnetic resonance imaging techniques can give important information concerning tumor characterization, grading, and patient prognosis, increasing evidence in recent years has highlighted the need for personalized treatment and the development of quantitative imaging parameters that can predict the nature of the lesion and its possible evolution. For this purpose, radiomics and the use of artificial intelligence software, aimed at obtaining valuable data from images beyond mere visual observation, are gaining increasing importance. This brief review illustrates the current state of the art of this new imaging approach and its contributions to understanding CNS tumors in children.
METHODS: We searched the PubMed, Scopus, and Web of Science databases using the following key search terms: (\"radiomics\" AND/OR \"artificial intelligence\") AND (\"pediatric AND brain tumors\"). Basic and clinical research literature related to the above key research terms, i.e., studies assessing the key factors, challenges, or problems of using radiomics and artificial intelligence in pediatric brain tumors management, was collected.
RESULTS: A total of 63 articles were included. The included ones were published between 2008 and 2024. Central nervous tumors are crucial in pediatrics due to their high frequency and impact on disease and treatment. MRI serves as the cornerstone of neuroimaging, providing cellular, vascular, and functional information in addition to morphological features for brain malignancies. Radiomics can provide a quantitative approach to medical imaging analysis, aimed at increasing the information obtainable from the pixels/voxel grey-level values and their interrelationships. The \"radiomic workflow\" involves a series of iterative steps for reproducible and consistent extraction of imaging data. These steps include image acquisition for tumor segmentation, feature extraction, and feature selection. Finally, the selected features, via training predictive model (CNN), are used to test the final model.
CONCLUSIONS: In the field of personalized medicine, the application of radiomics and artificial intelligence (AI) algorithms brings up new and significant possibilities. Neuroimaging yields enormous amounts of data that are significantly more than what can be gained from visual studies that radiologists can undertake on their own. Thus, new partnerships with other specialized experts, such as big data analysts and AI specialists, are desperately needed. We believe that radiomics and AI algorithms have the potential to move beyond their restricted use in research to clinical applications in the diagnosis, treatment, and follow-up of pediatric patients with brain tumors, despite the limitations set out.

Current psychotherapeutic treatments for OCD, while effective, have complex outcomes with mixed efficacy. Previous research has observed baseline brain activation patterns in OCD patients, elucidating some of the implications of this disorder. Observing the effects of evidence-based psychotherapeutics for OCD on brain activation (through MRI) may provide a more comprehensive outline of pathology. This systematic review and meta-analysis evaluated the effects of cognitive behavioural therapy (CBT) with exposure-response prevention (ERP) on brain activation in OCD patients. Academic databases were systematically searched, and the outcomes evaluated included changes in brain activation and symptom severity between baseline and post-treatment. Patients (n = 193) had confirmed OCD diagnosis and underwent protocolized CBT with ERP programs delivered by trained therapists. Participants in the CBT with ERP programs demonstrated significant improvements in symptom severity (Cohen\'s d = - 1.91). In general, CBT with ERP resulted in decreased activation post-treatment in the frontal (Cohen\'s d = 0.40), parietal (Cohen\'s d = 0.79), temporal (Cohen\'s d = 1.02), and occipital lobe (Cohen\'s d = 0.76), and cerebellum (Cohen\'s d = - 0.78). The findings support CBT with ERP\'s ability to improve brain activation abnormalities in OCD patients. By identifying regions that improved activation levels, psychotherapy programs may benefit from the addition of function-specific features that could improve treatment outcomes.

BACKGROUND: Anterior-posterior electrode placement is preferred in electrical cardioversion of atrial fibrillation. However, the optimal anterior-posterior electrode position in relation to the heart is not studied.
RESULTS: We performed a prospective observational study on patients presenting for cardioversion of atrial fibrillation. Electrodes were placed in the anterior-posterior position and shock was delivered in a step-up approach (100 J→200 J→360 J). Fluoroscopic images were obtained, and distances were measured from points A, midanterior electrode; and B, midposterior electrode, to midpoint of the cardiac silhouette. Patients requiring one 100 J shock for cardioversion success (group I) were compared with those requiring >1 shock/100 J (group II). Logistic regression was used to determine the impact of electrode distance on low energy (100 J) cardioversion success. Computed tomography scans from this cohort were analyzed for anatomic landmark correlation to the cardiac silhouette. Of the 87 patients included, 54 (62%) comprised group I and 33 (38%) group II. Group I had significantly lower distances from the mid-cardiac silhouette to points A (5.0±2.4 versus 7.4±3.3 cm; P<0.001) and B (7.3±3.0 versus 10.0±3.8 cm; P=0.002) compared with group II. On multivariate analysis, higher distances from the mid-cardiac silhouette to point A (odds ratio, 1.33 [95% CI, 1.07-1.70]; P=0.01) and B (odds rsatio, 1.24 [95% CI, 1.05-1.50]; P=0.01) were independent predictors of low energy (100 J) cardioversion failure. Based on review of computed tomography scans, we suggest that the xiphoid process may be an easy landmark to guide proximity to the myocardium.
CONCLUSIONS: In anterior-posterior electrode placement, closer proximity to the cardiac silhouette predicts successful 100 J cardioversion irrespective of clinical factors.

Purpose To investigate the ability of kilovolt-independent (hereafter, kV-independent) and tin filter spectral shaping to accurately quantify the coronary artery calcium score (CACS) and radiation dose reductions compared with the standard 120-kV CT protocol. Materials and Methods This prospective, blinded reader study included 201 participants (mean age, 60 years ± 9.8 [SD]; 119 female, 82 male) who underwent standard 120-kV CT and additional kV-independent and tin filter research CT scans from October 2020 to July 2021. Scans were reconstructed using a Qr36f kernel for standard scans and an Sa36f kernel for research scans simulating artificial 120-kV images. CACS, risk categorization, and radiation doses were compared by analyzing data with analysis of variance, Kruskal-Wallis test, Mann-Whitney test, Bland-Altman analysis, Pearson correlations, and κ analysis for agreement. Results There was no evidence of differences in CACS across standard 120-kV, kV-independent, and tin filter scans, with median CACS values of 1 (IQR, 0-48), 0.6 (IQR, 0-58), and 0 (IQR, 0-51), respectively (P = .85). Compared with standard 120-kV scans, kV-independent and tin filter scans showed excellent correlation in CACS values (r = 0.993 and r = 0.999, respectively), with high agreement in CACS risk categorization (κ = 0.95 and κ = 0.93, respectively). Standard 120-kV scans had a mean radiation dose of 2.09 mSv ± 0.84, while kV-independent and tin filter scans reduced it to 1.21 mSv ± 0.85 and 0.26 mSv ± 0.11, cutting doses by 42% and 87%, respectively (P < .001). Conclusion The kV-independent and tin filter research CT acquisition techniques showed excellent agreement and high accuracy in CACS estimation compared with standard 120-kV scans, with large reductions in radiation dose. Keywords: CT, Cardiac, Coronary Arteries, Radiation Safety, Coronary Artery Calcium Score, Radiation Dose Reduction, Low-Dose CT Scan, Tin Filter, kV-Independent Supplemental material is available for this article. © RSNA, 2024.

OBJECTIVE: Magnetic resonance imaging (MRI) findings in peroneal neuropathy are not well documented and the prognostic value of imaging remains uncertain. Upper limits of cross-sectional area (CSA) on ultrasound (US) have been established, but uncertainty regarding generalizability remains. We aimed to describe MRI findings of the peroneal nerve in patients and healthy controls and to compare these results to US findings and clinical characteristics.
METHODS: We prospectively included patients with foot drop and electrodiagnostically confirmed peroneal neuropathy, and performed clinical follow-up, US and MRI of both peroneal nerves. We compared MRI findings to healthy controls. Two radiologists evaluated MRI features in an exploratory analysis after images were anonymized and randomized.
RESULTS: Twenty-two patients and 38 healthy controls were included. Whereas significant increased MRI CSA values were documented in patients (mean CSA 20 mm2 vs. 13 mm2 in healthy controls), intra- and interobserver variability was substantial (variability of, respectively, 7 and 9 mm2 around the mean in 95% of repeated measurements). A pathological T2 hyperintense signal of the nerve was found in 52.6% of patients (50% interobserver agreement). Increased CSA measurements (MRI/US), pathological T2 hyperintensity of the nerve and muscle edema were not predictive for recovery.
CONCLUSIONS: Imaging is recommended in all patients with peroneal neuropathy to exclude compressive intrinsic and extrinsic masses but we do not advise routine MRI for diagnosis or prediction of outcome in patients with peroneal neuropathy due to high observer variability. Further studies should aim at reducing MRI observer variability potentially by semi-automation.

Cerebral Autosomal Dominant Arteriopathy with Subcortical Infarcts and Leukoencephalopathy (CADASIL) is a hereditary small vessel disease of the brain characterized by progressive white matter lesions, subcortical infarcts, and cognitive decline. This autosomal dominant disorder is caused by mutations in the NOTCH3 gene located on chromosome 19, resulting in the accumulation of granular osmiophilic material within the walls of small arteries and arterioles. Clinically, CADASIL typically manifests in mid-adulthood with recurrent ischemic events, migraine with aura, mood disturbances, and cognitive impairment. Neuroimaging plays a crucial role in the diagnosis of CADASIL, with characteristic findings including white matter hyperintensities particularly in the anterior temporal lobe and external capsule.

BACKGROUND: Motor function has correlated with longevity and functionality; however, there is limited research on those with Alzheimer\'s disease (AD). We studied the association between motor functionality and AD pathology in primary motor and medial temporal cortices.
METHODS: A total of 206 participants with a clinical diagnosis of cognitively healthy, AD, or mild cognitive impairment (MCI) underwent imaging and motor assessment. Linear regressions and analyses of variance were applied to test the prediction from AD imaging biomarkers to motor performance and the diagnosis group differences in motor performance.
RESULTS: Increased neurodegeneration was associated with worsening dexterity and lower walking speed, and increased amyloid and tau were associated with worsening dexterity. AD and MCI participants had lower motor performance than the cognitively healthy participants.
CONCLUSIONS: Increased AD pathology is associated with worsening dexterity performance. The decline in dexterity in those with AD pathology may offer an opportunity for non-pharmacological therapy intervention.
CONCLUSIONS: Noted worsening dexterity performance was associated with greater Alzheimer\'s disease (AD) pathology (tau, amyloid beta, and neurodegeneration) in primary motor cortices. Similarly, increased neurodegeneration and tau pathology in parahippocampal, hippocampal, and entorhinal cortices is associated with worsening dexterity performance. Motor performance declined in those with clinical and preclinical AD among an array of motor assessments.

OBJECTIVE: The aim of this study was to compare the differences between angles of bladder neck in girls with overactive bladder and those in healthy ones using transabdominal ultrasonography.
METHODS: This study consists of 28 girls complicated with overactive bladder (Group I) and 40 healthy girls (Group II). The anteroposterior vesical wall angle (APVA), urethroposterior vesical wall angle (UPVA), urethroanterior vesical wall angle (UAVA), thickness of bladder mucosa, distance of urethral orifices, and distance between ureter and urethra orifice were measured in supine position using transabdominal ultrasonography. The results were compared between the two groups.
RESULTS: UAVA in Group I was higher than Group II (135.2 ± 12.2 mm vs. 117.4 ± 14.0 mm; p = 0.009). UPVA was smaller in Group I than Group II (114.6 ± 19.5 mm vs. 135.3 ± 16.5 mm; p = 0.014). The distance between the ureteral orifices was 31.8 ± 8.5 mm in Group I and 17.0 ± 4.1 mm in Group II (p < 0.001). There was no statistically significant difference between groups in terms of APVA, bladder mucosa thickness, and distance between ureter and urethra orifice (p > 0.05).
CONCLUSIONS: Bladder neck dynamics may play an important role in overactive bladder pathophysiology due to differences in UPVA, UAV, and location of ureteral orifices in this patient population.

BACKGROUND: The retention of foreign bodies inside the body during ludic/sexual procedures or for traumatism represents one of the causes of visits to accident and emergency departments that often requires surgical removal of the foreign body. However, there are cases where the discovery of such foreign bodies takes place after many years, as in patients that are slightly compromised from a neuro-sociological point of view.
METHODS: A 76-year-old male presented to an outpatient urological examination due to an increase in scrotal volume. At the ultrasound check, an acoustic interference from a solid object was detected, for which computed tomography was requested. The computed tomography scan revealed the presence of an elongated metal body in the perineum. The removal of the foreign body in the operating theatre was then scheduled. A 10 cm long stainless-steel nail located within an abscessed foreign body granuloma was identified and removed via a scrotal access. Four days later, a new surgical toilet was performed due to minimal necrosis of the skin flaps. The patient then performed three more dressings in the operating theatre during the following week. Healing took place by secondary intention until a perfect healing of the surgical wound was obtained.
CONCLUSIONS: Removal of foreign bodies from the perineum in case of infection can be challenging. Careful attention and postoperative dressings are crucial for the success of the case.