Radiology Information Research Articles

Multiparametric MRI-based radiomics combined with pathomics features for prediction of the efficacy of neoadjuvant chemotherapy in breast cancer

PurposeThe aim of this study is to investigate a new method that combines radiological and pathological breast cancer information to predict discrepancies in pathological responses for individualized treatment planning. We used baseline multiparametric magnetic resonance imaging and hematoxylin and eosin-stained biopsy slides to extract quantitative feature information and predict the pathological response to neoadjuvant chemotherapy in breast cancer patients. MethodsWe retrospectively collected data from breast cancer patients who received neoadjuvant chemotherapy in our hospital from August 2016 to January 2018; multiparametric magnetic resonance imaging (contrast-enhanced T1-weighted imaging and diffusion-weighted imaging) and whole slide image of hematoxylin and eosin-stained biopsy sections were collected. Quantitative imaging features were extracted from the multiparametric magnetic resonance imaging and the whole slide image were used to construct a radiopathomics signature model powered by machine learning methods. Models based on multiparametric magnetic resonance imaging or whole slide image alone were also constructed for comparison and referred to as the radiomics signature and pathomics signature models, respectively. Four modeling methods were used to establish prediction models. Model performances were evaluated using receiver operating characteristic curve analysis and the area under the curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. ResultsThe radiopathomics signature model had favourable performance for the prediction of pathological complete response in the training set (the best value: area under the curve 0.83, accuracy 0.84, and sensitivity 0.87), and in the test set (the best value: area under the curve 0.91, accuracy 0.90, and sensitivity 0.88). In the test set, the radiopathomics signature model also significantly outperformed the radiomics signature (the best value: area under the curve 0.83, accuracy 0.64, and sensitivity 0.62), pathomics signature (the best value: area under the curve 0.60, accuracy 0.74, and sensitivity 0.62) (p > 0.05). Decision curve analysis and calibration curves confirmed the excellent performance of these prediction models in discrimination, calibration, and clinical usefulness. ConclusionsThe results of this study suggest that radiopathomics, the combination of both radiological information regarding the whole tumor and pathological information at the cellular level, could potentially predict discrepancies in pathological response and provide evidence for rational treatment plans.

A CT-based diagnostic nomogram and survival analysis for differentiating grade 3 pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas.

To construct a CT-based diagnostic nomogram for distinguishing grade 3 pancreatic neuroendocrine tumors (G3 PNETs) from pancreatic ductal adenocarcinomas (PDACs) and assess their respective survival outcomes. Patients diagnosed with G3 PNETs (n = 30) and PDACs (n = 78) through surgery or biopsy from two medical centers were retrospectively identified. Demographic and radiological information, including age, gender, tumor diameter, shape, margin, dilatation of pancreatic duct, and invasive behavior, were carefully collected. A nomogram was established after univariate and multivariate logistic regression analyses. The Kaplan-Meier survival was performed to analyze their survival outcomes. Factors with a p-value <0.05, including age, CA 19-9, pancreatic duct dilatation, irregular shape, ill-defined margin, pancreatic atrophy, combined pancreatitis, arterial/portal enhancement ratio, were included in the multivariate logistic analysis. The independent predictive factors, including age (OR, 0.91; 95% CI, 0.85-0.98), pancreatic duct dilatation (OR, 0.064; 95% CI, 0.01-0.32), and portal enhancement ratio (OR, 1,178.08; 95% CI, 5.96-232,681.2) were determined to develop a nomogram. The internal calibration curve and decision curve analysis demonstrate that the nomogram exhibits good consistency and discriminative capacity in distinguishing G3 PNETs from PDACs. Patients diagnosed with G3 PNETs exhibited considerably better overall survival outcomes compared to those diagnosed with PDACs (median survival months, 42 vs. 9 months, p < 0.001). The nomogram model based on age, pancreatic duct dilatation, and portal enhancement ratio demonstrates good accuracy and discriminative ability effectively predicting the probability of G3 PNETs from PDACs. Furthermore, patients with G3 PNETs exhibit better prognosis than PDACs.

Cysts of the jaws and how to make their diagnoses under a microscope: a need for a better communication between clinicians and pathologists

Introduction: Cysts of the jaws constitute an heterogenous group of lesions occurring in the maxillofacial region. Their diagnosis is challenging and necessitating a meticulous correlation of clinical, radiological, and pathological features. Pathologists often face numerous difficulties stemming from inadequate clinical and radiological information, along with limited samples. Nevertheless, clinicians are not always aware of the pathologist's concerns, making difficult to know exactly which pertinent clinical information they should deliver in their request form. The objective of this article is to illustrate the microscopic diagnostic pitfalls associated with cystic lesions of the jaws and enhance communication between oral surgeons and oral pathologist. Corpus: This section starts by examining the essential clinical and radiological data necessary for a precise pathological diagnosis. Subsequently, we discuss about the differential diagnosis of jaw cystic lesions, categorizing them into five distinct subsets based on their microscopic features, particularly their histological lining. For each subset, we engage in a detailed discussion concerning the primary diagnostic challenges and their implications for treatment decisions. Conclusion: Pathologist and clinicians are not irreconcilables: improved communication, rooted in a mutual understanding of each other's concerns, leads to optimizing the diagnosis and subsequently the treatment of jaw cysts.

Immunohistochemistry Assay for Differentiating Liposarcoma and Its Mimickers

Introduction: Soft tissue tumors account for 1 – 1.5% of all cancer, which is the tenth most common cancer in referral oncology hospitals in Indonesia. Liposarcomas are a group of histologically diverse lesions, accounting for 12.8% – 20% of all soft tissue malignancies. Some soft tissue tumors may show similar histological appearance, making differentiating mesenchymal neoplasms a difficult challenge. Immunohistochemical examination is an advanced examination to refine and determine the diagnosis that cannot be established based on histopathological examination only. Methods: This study was an observational descriptive study with a retrospective approach. The data of patients with liposarcoma was obtained from immunohistochemistry examination results in Dr. Soetomo General Academic Hospital during 2020 – 2022 period, which includes the histopathology result. All cases were classified based on WHO. We considered only patients with immunohistochemistry examination proven diagnosis who underwent surgery or biopsy in the same institution. Results: The total number of liposarcoma cases was 20, with most patients were male (90%) and age group 40 – 49 years old (30%). The most common location was the abdominal region (55%), including intra-abdominal, mesentery, and retroperitoneal. The most common subtype was dedifferentiated liposarcoma with 10 cases (50%). Conclusions: Immunohistochemistry examination in malignant adipocytic tumors aims to confirm the diagnosis, with the most common subtype being dedifferentiated liposarcoma. It is necessary to consider the morphology in H&amp;E staining together with the immunohistochemistry profile as well as all clinical and radiology information to establish the most relevant diagnosis.

Generative Pre-trained Transformer 4 makes cardiovascular magnetic resonance reports easy to understand

BackgroundPatients are increasingly using Generative Pre-trained Transformer 4 (GPT-4) to better understand their own radiology findings. PurposeTo evaluate the performance of GPT-4 in transforming cardiovascular magnetic resonance (CMR) reports into text that is comprehensible to medical laypersons. MethodsChatGPT with GPT-4 architecture was used to generate three different explained versions of 20 various CMR reports (n = 60) using the same prompt: “Explain the radiology report in a language understandable to a medical layperson”. Two cardiovascular radiologists evaluated understandability, factual correctness, completeness of relevant findings, and lack of potential harm, while 13 medical laypersons evaluated the understandability of the original and the GPT-4 reports on a Likert scale (1 “strongly disagree”, 5 “strongly agree”). Readability was measured using the Automated Readability Index (ARI). Linear mixed-effects models (values given as median [interquartile range]) and intraclass correlation coefficient (ICC) were used for statistical analysis. ResultsGPT-4 reports were generated on average in 52 s ± 13. GPT-4 reports achieved a lower ARI score (10 [9–12] vs 5 [4–6]; p < 0.001) and were subjectively easier to understand for laypersons than original reports (1 [1] vs 4 [4,5]; p < 0.001). Eighteen out of 20 (90%) standard CMR reports and 2/60 (3%) GPT-generated reports had an ARI score corresponding to the 8th grade level or higher. Radiologists’ ratings of the GPT-4 reports reached high levels for correctness (5 [4, 5]), completeness (5 [5]), and lack of potential harm (5 [5]); with “strong agreement” for factual correctness in 94% (113/120) and completeness of relevant findings in 81% (97/120) of reports. Test-retest agreement for layperson understandability ratings between the three simplified reports generated from the same original report was substantial (ICC: 0.62; p < 0.001). Interrater agreement between radiologists was almost perfect for lack of potential harm (ICC: 0.93, p < 0.001) and moderate to substantial for completeness (ICC: 0.76, p < 0.001) and factual correctness (ICC: 0.55, p < 0.001). ConclusionGPT-4 can reliably transform complex CMR reports into more understandable, layperson-friendly language while largely maintaining factual correctness and completeness, and can thus help convey patient-relevant radiology information in an easy-to-understand manner.

A Novel Study for Automatic Two-Class and Three-Class COVID-19 Severity Classification of CT Images using Eight Different CNNs and Pipeline Algorithm

SARS-CoV-2 has caused a severe pandemic worldwide. This virus appeared at the end of 2019. This virus causes respiratory distress syndrome. Computed tomography (CT) imaging provides important radiological information in the diagnosis and clinical evaluation of pneumonia caused by bacteria or a virus. CT imaging is widely utilized in the identification and evaluation of COVID-19. It is an important requirement to establish diagnostic support systems using artificial intelligence methods to alleviate the workload of healthcare systems and radiologists due to the disease. In this context, an important study goal is to determine the clinical severity of the pneumonia caused by the disease. This is important for determining treatment procedures and the follow-up of a patient’s condition. In the study, automatic COVID-19 severity classification was performed using three-class (mild, moderate, and severe) and two-class (non-severe and severe). In the study, deep learning models were used for classification. Also, CT images were utilized as radiological images. A total of 483 COVID-19 CT-image slices, 267 mild, 156 moderate, and 60 severe, were used. These images and labels were used directly for the three classifications. In the two-class classification, the mild and moderate images were accepted as non-severe. A total of eight classifications were made with convolutional neural network (CNN) architectures. These architectures are MobileNetv2, ResNet101, Xception, Inceptionv3, GoogleNet, EfficientNetb0, DenseNet201, and DarkNet53. In the study, the results of the top four CNN architectures with the best performance were combined using a pipeline algorithm. In this way, it is seen that significant improvements have been achieved in the results of the study. Before using the pipeline algorithm for the three-class classification, the results of weighted recall-sensitivity (SNST), specificity (SPCF), accuracy (ACCR), F-1 score (F-1), area under the receiver operating characteristic curve (AUC), and overall ACCR were obtained: 0.7785, 0.8351, 0.8299, 0.7758, 0.9112 and 0.7785, respectively. After using the pipeline algorithm for the three-class classification, the results of these parameters were obtained: 0.8095, 0.8555, 0.8563, 0.8076, 0.9089, and 0.8095, respectively. Before using the pipeline algorithm for the two-class classification, the results of SNST, SPCF, ACCR, F-1, and AUC were obtained: 0.9740, 0.8500, 0.9482, 0.9703, and 0.9788, respectively. After using the pipeline algorithm for the two-class classification, the results of these parameters were obtained: 0.9811, 0.8333, 0.9627, 0.9788, and 0.9851, respectively.

The split apparent diffusion coefficient sign: A novel magnetic resonance imaging biomarker for cortical pathology with possible implications in autoimmune encephalitis.

MRI is the imaging modality of choice for assessing patients with encephalopathy. In this context, we discuss a novel biomarker, the "split ADC sign," where the cerebral cortex demonstrates restricted diffusion (high DWI signal and low ADC) and the underlying white matter demonstrates facilitated diffusion (high or low DWI signal and high ADC). We hypothesize that this sign can be used as a biomarker to suggest either acute encephalitis onset or to raise the possibility of an autoimmune etiology. A full-text radiological information system search of radiological reports was performed for all entities known to produce restricted diffusion in the cortex excluding stroke between January 2012 and June 2022. Initial MRI studies performed upon onset of clinical symptoms were screened for the split ADC sign. 25 subjects were encountered with a positive split ADC sign (15 female; median age = 57years, range 18-82). Diagnosis included six herpes simplex encephalitis, three peri-ictal MRI changes, eight PRES, two MELAS, and six autoimmune (3 anti-GABAAR, two seronegative, and one anti-Ma2/Ta). Subjects were imaged at a mean 1.8days after the onset of symptoms (range 0-8). We present a novel visual MRI biomarker, the split ADC sign, and highlight its potential usefulness in subjects with encephalopathy to suggest acute disease onset or to raise the possibility of an autoimmune etiology when location-based criteria are applied. When positive, the sign was present on the initial MRI and can therefore be used to help focus further clinical and laboratory workup.

Radiology weather forecast: A retrospective analysis of predictability of median daily polytrauma-CT occurrence based on weather data

ObjectivesResource planning is a crucial component in hospitals, particularly in radiology departments. Since weather conditions are often described to correlate with emergency room visits, we aimed to forecast the amount of polytrauma-CTs using weather information. DesignAll polytrauma-CTs between 01/01/2011 and 12/31/2022 (n = 6638) were retrieved from the radiology information system. Local weather data was downloaded from meteoblue.com. The data was normalized and smoothened. Daily polytrauma-CT occurrence was stratified into below median and above median number of daily polytrauma-CTs.Logistic regression and machine learning algorithms (neural network, random forest classifier, support vector machine, gradient boosting classifier) were employed as prediction models. Data from 2012 to 2020 was used for training, data from 2021 to 2022 for validation. ResultsMore polytrauma-CTs were acquired in summer compared with winter months, demonstrating a seasonal change (median: 2.35; IQR 1.60–3.22 vs. 2.08; IQR 1.36–3.03; p <.001).Temperature (rs = 0.45), sunshine duration (rs = 0.38) and ultraviolet light amount (rs = 0.37) correlated positively, wind velocity (rs = -0.57) and cloudiness (rs = -0.28) correlated negatively with polytrauma-CT occurrence (all p <.001).The logistic regression model for identification of days with above median number of polytrauma-CTs achieved an accuracy of 87 % on training data from 2011 to 2020.When forecasting the years 2021–2022 an accuracy of 65 % was achieved. A neural network and a support vector machine both achieved a validation accuracy of 72 %, whereas all classifiers regarded wind velocity and ultraviolet light amount as the most important parameters. ConclusionIt is possible to forecast above or below median daily number of polytrauma-CTs using weather data. Clincical Relevance statementPrediction of polytrauma-CT examination volumes may be used to improve resource planning.

Incidence and distribution of injuries associated with e-scooter use: a radiological perspective.

To investigate electric scooter (e-scooter)-associated radiological injury incidence and distribution of injuries. Retrospective cross-sectional study of radiological examinations related to e-scooter injuries at a major trauma centre in a small university city. The hospital radiology information system was searched for terms related to e-scooters between January 1, 2015, and October 31, 2022. E-scooter use was confirmed by review of the patients' electronic medical records. Specific injuries were divided based on site of injury using the Injury Severity Scale categorized groups. A total of 568 radiological studies related to e-scooter injuries were identified on 340 distinct patients (56% male, with an average age of 28 years). Peak incidence of e-scooter-related injuries was seen in the summer months, after a local scooter sharing system was introduced in October 2020. A total of 149 patients had radiologically diagnosed injuries, with extremity injuries being most frequent (80%). Facial (8%), head/neck (8%), and thorax/abdomen (4%) were less common. Radial head fractures were the most common injury (n = 27). Thirteen patients had multiple sites of injury, four of which had both upper limb and facial bone fractures described. We report a significant increase in radiological investigations and injuries in the context of e-scooter injuries, particularly since the introduction of an e-scooter sharing scheme. This study informs radiologists on common locations of injuries when reporting studies of patients that have had e-scooter-related injuries. This is the first UK-based study providing a comprehensive radiological perspective of the impact of e-scooter use and associated distribution of injuries, adding important data for many cities that are currently undertaking review of their e-scooter sharing schemes.

Artificial intelligence for discrimination of Crohn's disease and gastrointestinal tuberculosis: A systematic review.

Discrimination of gastrointestinal tuberculosis (GITB) and Crohn's disease (CD) is difficult. Use of artificial intelligence (AI)-based technologies may help in discriminating these two entities. We conducted a systematic review on the use of AI for discrimination of GITB and CD. Electronic databases (PubMed and Embase) were searched on June 6, 2022, to identify relevant studies. We included any study reporting the use of clinical, endoscopic, and radiological information (textual or images) to discriminate GITB and CD using any AI technique. Quality of studies was assessed with MI-CLAIM checklist. Out of 27 identified results, a total of 9 studies were included. All studies used retrospective databases. There were five studies of only endoscopy-based AI, one of radiology-based AI, and three of multiparameter-based AI. The AI models performed fairly well with high accuracy ranging from 69.6-100%. Text-based convolutional neural network was used in three studies and Classification and regression tree analysis used in two studies. Interestingly, irrespective of the AI method used, the performance of discriminating GITB and CD did not match in discriminating from other diseases (in studies where a third disease was also considered). The use of AI in differentiating GITB and CD seem to have acceptable accuracy but there were no direct comparisons with traditional multiparameter models. The use of multiple parameter-based AI models have the potential for further exploration in search of an ideal tool and improve on the accuracy of traditional models.

Radiological evaluation before and after treatment with an osseointegrated bone-anchor following major limb amputation-a guide for radiologists.

Osseointegrated implants have been developed to allow direct skeletal fixation of a prosthesis as an alternative to traditional socket-fitted prostheses for patients who have suffered from a major limb amputation. The implants contribute to improvements in functional outcome and quality of life and radiological evaluation plays a crucial role in pre- and post-operative assessment. This article acts as a guide for radiologists who may be tasked with providing the radiological information required by surgeons and prosthetists. We also look at the radiological appearances of complications that may arise in patients treated with an osseointegrated implant. Plain X-rays are used to screen patients who wish to undergo treatment. Limb-length X-rays are then used to measure the length of any residual bone, and comparisons can be made with the normal side (if present). From this, decisions about the likely size of the implant and the need for further amputation can be made. CT scans enable accurate assessment of the medullary cavity and cortical thickness. Post-operatively, plain X-rays form the mainstay of the routine monitoring of the bone-implant interface. Potential complications include infection, aseptic loosening, mechanical fracture of the implant and periprosthetic fracture. Infection and aseptic loosening can be seen as a lucency at the bone-implant interface which (if left untreated) can lead to loss of the implant. Implant and periprosthetic fractures are radiographically obvious. Radiologists involved in the care of patients undergoing treatment with an osseointegrated implant should become familiar with the imaging requirements so they can contribute to optimal patient outcomes.

Investigation of the capabilities of algorithms for automated quality assurance of DICOM metadata of chest X-ray examinations

Purpose. To evaluate the quality of filling DICOM tags responsible for the orientation, scanning area and photometric interpretation of the image, as well as to develop and test algorithms for automatically determining the true values of these tags for chest x-rays and fluorograms.Materials and methods. To assess the quality of filling DICOM tags, were used 1885 studies obtained from the Unified Radiological Information Service of the Unified Medical Information and Analysis System (ERIS EMIAS). For training and validation of algorithms for automatic determination of the true values of tags, were used datasets of radiographs in standard frontal and lateral projections, from open databases and from ERIS EMIAS (12,920 studies in total). The deep neural network architecture VGG 19 was chosen as the basis for creating algorithms.Results. We found that the frequency of missing values in DICOM tags can range from 6 to 75%, depending on the tag. At the same time, up to 70% of filled tag values have errors. We obtained next models: a model for determining the anatomical area of x-ray examination, a model for determining the projection on the chest x-ray, a model for determining the photometric interpretation of the image. All of the obtained algorithms have high classification quality indicators. The AUC for each of the obtained models was more than 0.99.Conclusions. Our study shows that a large number of studies in diagnostic practice contain incorrect values of DICOM tags, which can critically affect the implementation of software based on artificial intelligence technology in clinical practice. Our obtained algorithms can be integrated into the development process of such software and used in the preprocessing of images before their analysis.

Transcriptomic landscape based on annotated clinical features reveals PLPP2 involvement in lipid raft-mediated proliferation signature of early-stage lung adenocarcinoma

BackgroundImage-based screening improves the detection of early-stage lung adenocarcinoma (LUAD)but also highlights the issue of high false-positive diagnoses, which puts patients at a risk of unnecessary over-treatment. Therefore, more precise discrimination criteria are required to ensure that patients with early-stage LUAD receive appropriate treatments.MethodsWe integrated 158 early-stage LUAD cases from 2 independent cohorts, including 30 matched resected specimens with complete radiological and pathological information, and 128 retrospective pathological pair-samples with partial follow-up data. This integration allowed us to conduct a correlation analysis between clinical phenotype and transcriptome landscape. Immunohistochemistry was performed using tissue microarrays to examine the expression of phospholipid phosphatase 2 (PLPP2) and lipid-raft markers. Lipidomics analysis was used to determine the changes of lipid components in PLPP2-overexpressed cells. To assess the effects of PLPP2 on the malignant phenotypes of LUAD cells, we conducted mice tumor-bearing experiments and in vitro cellular experiments by knocking down PLPP2 and inhibiting lipid raft synthesis with MβCD, respectively.ResultsBioinformatics analysis indicated that the co-occurrence of lipid raft formation and rapid cell proliferation might exhibit synergistic effects in driving oncogenesis from lung preneoplasia to adenocarcinoma. The enhanced activation of the cell cycle promoted the transition from non-invasive to invasive status in early-stage LUAD, which was related to an increase in lipid rafts within LUAD cells. PLPP2 participated in lipid raft formation by altering the component contents of lipid rafts, such as esters, sphingomyelin, and sphingosine. Furthermore, elevated PLPP2 levels were identified as an independent prognostic risk factor for LUAD patients. Further results from in vivo and in vitro experiments confirmed that PLPP2 could induce excessive cell proliferation by enhancing lipid raft formation in LUAD cells.ConclusionsOur study has revealed the characteristics of gene expression profiles in early-stage LUAD patients with the different radiological and pathological subtypes, as well as deciphered transcriptomic evolution trajectory from preneoplasia to invasive LUAD. Furthermore, it suggests that PLPP2-mediated lipid raft synthesis may be a significant biological event in the initiation of early-stage LUAD, offering a potential target for more precise diagnosis and therapy in clinical settings.

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.

Anomalous Origin of Left Circumflex Artery from the Right Sinus of Valsalva in Cardiac Computed Tomography in a Group of 16,680 Patients—Radiologic and Clinical Characteristics

Background: Anomalous aortic origin of a coronary artery (AAOCA) is the most prevalent form of coronary anomaly. One variant of AAOCA is the anomalous origin of the left circumflex artery from the right sinus of Valsalva, which can be detected using cardiac computed tomography (CT). However, limited data are available regarding the natural history of this anomaly, its impact on myocardial function, and associated symptoms. Methods: We conducted a retrospective analysis of 16,680 CT exams (cardiac and chest) performed between 2015 and 2022 at our Heart Imaging Department, utilising a dual-source 128-slice CT scanner (SOMATOM Definition Flash, Siemens Healthineers, Forchheim, Germany). A registry of patients with anomalous origin of the circumflex artery from the right sinus of Valsalva (RCx) was established. The study included 56 cases of RCx (0.33%). Clinical information was obtained from medical records. RCx was defined as a circumflex artery originating from the right sinus of Valsalva (type I or II) or the right coronary artery (type III). Two researchers independently reevaluated each CT exam in our study group to ensure accurate radiologic descriptions and provide additional precise radiologic information regarding the anomaly, including high-risk features. Results: Our study comprised 56 patients, with approximately equal distribution between males (n = 30, 54%) and females (n = 26, 46%), and with a median age of 59 years. Coronary heart disease (CAD) was known in 23% of patients (n = 13), while 11% (n = 6) were obese (defined as a BMI &gt; 30 kg/m2), and 13% (n = 7) were diagnosed with type 2 diabetes. Only 9% of patients (n = 5) were smokers. Dyslipidemia was the most prevalent atherosclerotic risk factor, affecting approximately one third of patients (n = 17, 30%). In 14% (n = 8) of patients, heart failure was observed, while 13% (n = 7) were diagnosed with atrial fibrillation. Type I RCx was the most common subtype, identified in 48% of patients (n = 27) with this anomaly. Type II and Type III were found in 25% (n = 14) and 27% (n = 15) of patients, respectively. Conclusions: Our findings suggest that RCx is frequently encountered as an incidental finding, and we did not identify a consistent clinical characteristic in all patients with this type of anomaly. Furthermore, no gender predominance was associated with RCx. The natural history of this anomaly and its clinical implications seem benign. Further research is warranted to better understand this anomaly’s natural course and clinical implications.

Treatment with a flow diverter-assisted coil embolization for ruptured blood blister-like aneurysms of the internal carotid artery: a technical note and analysis of single-center experience with pooled data.

Treatment of blood blister-like aneurysms (BBAs) of the supraclinoid internal carotid artery (ICA) with flow diverters (FDs) has become widespread in recent years. However, ruptured blood blister-like aneurysm (BBA) of ICA treatment with flow diverter-assisted coil embolization (FDAC) remains controversial. Moreover, limited direct comparative studies have been conducted between the two treatment modalities, FDs and FDAC, for BBAs. The purpose of this study was to document our experience and evaluate the effectiveness and safety of FDAC. We conducted a retrospective analysis of clinical and radiological information from ten patients who experienced ruptured BBAs of the supraclinoid ICA at our center from January 2021 to February 2023. The technical details of FDAC for ruptured BBAs were described, and the technical steps were named "pipeline embolization device (PED)-Individualized shaping(microcatheter)-Semi deploying-Rivet(coils)-Massage(microwire)" as the PEISSERM technique. Clinical outcomes were assessed using the modified Rankin Scale (mRS), whereas radiological results were determined through angiography. A pooled analysis was implemented, incorporating data from literature sources that reported perioperative and long-term clinical and angiographic outcomes of ruptured BBAs treated with FD and FDAC strategies, along with our data. Data in our analysis pool were categorized into FD and FDAC strategy groups to explore the preferred treatment modalities for BBAs. The PEISSERM technique was utilized to treat ten patients, seven males, and three females, with an average age of 41.7years. A single PED was deployed in conjunction with coils in all ten patients. All PEDs were documented to have good wall apposition. The immediate postoperative angiograms demonstrated Raymond grade I in ten aneurysms. Angiographic follow-up of nine patients at 4-25months showed total occlusion of the aneurysms. At the most recent follow-up, the mRS scores of nine patients hinted at a good prognosis. Pooled analysis of 233 ICA-BBA cases of FD revealed a technical success rate of 91% [95% confidence interval (CI), 0.88 to 0.95], a rate of complete occlusion of 79% (95% CI, 0.73 to 0.84), a recurrence rate of 2% (95% CI, 0.00 to 0.04), a rebleed rate of 2% (95% CI, 0.00 to 0.04), and the perioperative stroke rate was 8% (95% CI, 0.04 to 0.11). The perioperative mortality was 4% (95% CI, 0.01 to 0.07). The long-term good clinical outcome rate was 85% (95% CI, 0.80 to 0.90). The mortality rate was 6% (95% CI, 0.03 to 0.09). Results from the subgroup analysis illustrated that the FDAC strategy for BBAs had a significantly higher immediate postoperative complete occlusion rate (P < 0.001), total occlusion rate (P = 0.016), and a good outcome rate (P = 0.041) compared with the FD strategy. The FDAC strategy can yield a higher rate of good outcomes than the FD strategy. The PEISSERM technique employed by the FDAC is a reliable and effective treatment approach as it can minimize the hemodynamic burden of BBA's fragile dome, thereby achieving an excellent occlusion rate. The PEISSERM technique in the FDAC strategy contributes to understanding the BBA's treatment and offers a potentially optimal treatment for BBA.

EGS P19 Do Waiting Times for Inpatient Magnetic Resonance Cholangiopancreatography Affect Total Length of Stay? – A Single Centre Experience

Abstract Background Magnetic resonance cholangiopancreatography (MRCP) is an important imaging modality in ruling out choledocholithiasis and thus guide management of patients. However, access to MRI remains limited, which may lead to delays in discharge. Our aim was to analyse the waiting time for inpatient MRCP and its impact on total length-of-stay (LOS). Methods A retrospective cohort study of all consecutive adult inpatients who underwent MRCP in a single surgical unit was conducted from September 2020 to September 2022. Patients being investigated for non-biliary indications including hepato-pancreato-biliary malignancies were excluded. Patient demographics, laboratory results, MRCP indications, results and timestamps from the hospital’s radiology information system were analysed. Peak liver function test (LFT) values before MRCP were used. P-values were calculated using Student T-test. This study was registered with Clinical Quality Project (LanQIP 14736). Results 677 patient has inpatient MRCPs; 22 were excluded. Median age was 66 years (IQR 51-76) and 401 (59.2%) were female. 281 (41.5%) MRCPs were urgent requests. 128 (18.9%) patients were clinically jaundiced and 115 (17.0%) had gallstone pancreatitis. 228 (33.7%) patients had choledocholithiasis on MRCP, of which 192 (84.2%) were known to have gallstones pre-MRCP. Median waiting time for urgent MRCPs from time of order was 1.0 days versus 1.3 for routine requests (p&amp;lt;0.001). Overall, median LOS was 6.7 days (IQR 4.1-10.9). This was 6.1 days (IQR 3.7-10.1) for urgent scans and 7.0 (IQR 4.5-11.5) for routine scans (p=0.106). Conclusions Inpatient MRCP does not significantly delay discharge in our centre. Patients screened for high-risk features of choledocholithiasis should have MRCPs marked as urgent to expedite clinical decision-making and mitigate complications from biliary obstruction. Therefore, it remains useful in determining the need for endoscopic retrograde cholangiopancreatography and/or intra-operative cholangiogram in patients with gallstone disease.

MANet: a multi-attention network for automatic liver tumor segmentation in computed tomography (CT) imaging

Automatic liver tumor segmentation is a paramount important application for liver tumor diagnosis and treatment planning. However, it has become a highly challenging task due to the heterogeneity of the tumor shape and intensity variation. Automatic liver tumor segmentation is capable to establish the diagnostic standard to provide relevant radiological information to all levels of expertise. Recently, deep convolutional neural networks have demonstrated superiority in feature extraction and learning in medical image segmentation. However, multi-layer dense feature stacks make the model quite inconsistent in imitating visual attention and awareness of radiological expertise for tumor recognition and segmentation task. To bridge that visual attention capability, attention mechanisms have developed for better feature selection. In this paper, we propose a novel network named Multi Attention Network (MANet) as a fusion of attention mechanisms to learn highlighting important features while suppressing irrelevant features for the tumor segmentation task. The proposed deep learning network has followed U-Net as the basic architecture. Moreover, residual mechanism is implemented in the encoder. Convolutional block attention module has split into channel attention and spatial attention modules to implement in encoder and decoder of the proposed architecture. The attention mechanism in Attention U-Net is integrated to extract low-level features to combine with high-level ones. The developed deep learning architecture is trained and evaluated on the publicly available MICCAI 2017 Liver Tumor Segmentation dataset and 3DIRCADb dataset under various evaluation metrics. MANet demonstrated promising results compared to state-of-the-art methods with comparatively small parameter overhead.

Clinical Value and Operational Risks of MRI in ICU patients - ARetrospective Analysis Performed at a University Medical Center.

Intensive care unit (ICU) patients have a high risk of developing complications when leaving the ICU for diagnostic procedures or therapeutic interventions. Our study examined the frequency of adverse events associated with magnetic resonance imaging (MRI) of intensive care patients and the extent of changes in therapy due to the MRI scan to weigh the risks associated with the scan against the potential benefits of an MR scan, using a change in therapy as an indicator of benefit. 4434 ICU patients (January to December 2015) were identified by Hospital Information System (SAP-R/3 IS-H, Walldorf, Germany), ICU patient data management system Metavision (iMDsoft, Israel), and Radiology Information System (Nexus.medRIS, Version 8.42, Nexus, Germany). All intensive care and medical records (HIS) and MRI reports (RIS) were matched and further evaluated in a retrospective case-to-case analysis for biometric data, mechanical ventilation, ICU requirements, planned postoperative vs. emergency diagnostic requirements, complications and impact on further diagnosis or therapy. Out of 4434 ICU patients, 322 ICU patients (7.3 %) underwent a total of 385 MRI examinations. 167 patients needed a total of 215 emergency scans, while 155 patients underwent 170 planned postoperative MRI exams. 158 (94.6 %) out of 167 emergency scan patients were ventilated under continuous intravenous medication and monitoring. In the planned postoperative group, only 6 (3.9 %) out of 155 were ventilated, but a total of 38 (24.5 %) were under continuous medication. 111 patients were accompanied by nurses only during MRI. Only one severe adverse event (0.3 %) was noted and was attributed to study preparation (n = 385). In 8MRI examinations (2.1 %), the examination was interrupted or cancelled due to the patients' condition. While all MRI examinations in the planned group were completed (n = 170, 100 %) (e. g., postoperative controls), only 207 out of 215 (96.3 %) could be performed for emergency diagnostic reasons. MRI influenced the clinical course with a change in diagnosis or therapy in 74 (19.2 %) of all 385 MRI examinations performed, and in the emergency diagnostic group it was 31.2 % (n = 67/215). Nearly 20 % of MRI examinations of ICU patients resulted in a change of therapy. With only one potentially life-threatening adverse event (0.3 %) during transport and the MRI examination, the risk seems to be outweighed by the diagnostic benefit. · The risk of adverse events associated with MRI scans in ICU patients is low.. · The rate of premature termination of ICU patients' MRI scans is low.. · Almost 20 % of ICU patients' MRI scans lead to a change of therapy..

The use of the flow-void sign on MRI: highly sensitive sign in detecting bone metastases from renal cell carcinoma.

To evaluate a range of pathologically proven malignant bone tumours, including primary bone sarcoma and metastatic bone lesions, referred to a tertiary referral centre for the presence of the flow-void sign on MR imaging. A retrospective search was performed using the radiology information system and oncology database in our institution to identify patients over the age of 40years referred with a solitary bone lesion. Patients with a range of pathologically proven malignant bone tumours, including primary bone tumours and metastatic bone lesions, were included in the study. MRI images were reviewed for the presence of the flow-void sign. The presence and type of the flow-void sign were correlated with lesion size. Two hundred and sixty-six cases were included in the study. Overall, the flow-void sign was identified in 40.9% of cases. The flow-void sign was most frequently seen in renal cell carcinoma metastasis (90.0%). The sign is highly sensitive (90%) for renal cell carcinoma metastases with a high negative predictive value (98.09%). When the flow-void sign is identified, the lesion is almost three times more likely to represent a renal cell carcinoma metastasis than any other malignant tumour in patients over the age of 40years with a solitary bone lesion. The flow-void sign is highly sensitive for renal cell carcinoma bone metastases and could negate the need for biopsy in patients with a known history of renal cell carcinoma or in whom an occult renal cell carcinoma is subsequently identified.