Expert Radiologists Research Articles

Usar una herramienta comercial de inteligencia artificial no entrenada para COVID-19 mejora ligeramente la interpretación de las radiografías con neumonía COVID-19, especialmente entre lectores inexpertos

IntroductionOur objective is to evaluate how useful an artificial intelligence (AI) tool is to chest radiograph readers with various levels of expertise for the diagnosis of COVID-19 pneumonia when the tool has been trained on a non-COVID-19 pneumonia pathology. MethodsData was collected for patients who had previously undergone a chest radiograph and digital tomosynthesis due to suspected COVID-19 pneumonia. The gold standard consisted of the readings of two expert radiologists who assessed the presence and distribution of COVID-19 pneumonia on the images. Six medical students, two radiology trainees, and two other expert thoracic radiologists participated as additional readers. Two radiograph readings and a third supported by the AI Thoracic Care Suite tool were performed. COVID-19 pneumonia distribution and probability were assessed along with the contribution made by AI. Agreement and diagnostic performance were analysed. ResultsThe sample consisted of 113 cases, of which 56 displayed lung opacities, 52.2% were female, and the mean age was 50.70±14.9. Agreement with the gold standard differed between students, trainees, and radiologists. There was a non-significant improvement for four of the six students when AI was used. The use of AI by students did not improve the COVID-19 pneumonia diagnostic performance but it did reduce the difference in diagnostic performance with the more expert radiologists. Furthermore, it had more influence on the interpretation of mild pneumonia than severe pneumonia and normal radiograph findings. AI resolved more doubts than it generated, especially among students (31.30 vs 8.32%), followed by trainees (14.45 vs 5.7%) and radiologists (10.05% vs 6.15%). ConclusionFor expert and lesser experienced radiologists, this commercial AI tool has shown no impact on chest radiograph readings of patients with suspected COVID-19 pneumonia. However, it aided the assessment of inexperienced readers and in cases of mild pneumonia.

Automatic 3D coronary artery segmentation based on local region active contour model.

Segmentation of coronary arteries in computed tomography angiography (CTA) images plays a key role in the diagnosis and treatment of coronary-related diseases. However, manually analyzing the large amount of data is time-consuming, and interpreting this data requires the prior knowledge and expertise of radiologists. Therefore, an automatic method is needed to separate coronary arteries from a given CTA dataset. Firstly, an anisotropic diffusion filter was employed to smooth the noise while preserving the vessel boundaries. The coronary skeleton was then extracted using a two-step process based on the intensity of the coronary. In the first step, the thick vessel skeleton was extracted by clustering, improved vesselness filtering and region growing, while in the second step, the thin vessel skeleton was extracted by the height ridge traversal method guided by the cylindrical model. Next, the vesselness measure, representing vessel a priori information, was incorporated into the local region active contour model based on the vessel geometry. Finally, the initial contour of the active contour model was generated using the coronary artery skeleton for effective segmentation of the three-dimensional (3D) coronary arteries. Experimental results on chest CTA images show that the method is able to segment coronary arteries effectively with an average precision, recall and dice similarity coefficient (DSC) of 86.64%, 91.26% and 79.13%, respectively, and has a good performance in thin vessel extraction. The method does not require manual selection of vessel seeds or setting of initial contours, and allows for the extraction of a successful coronary artery skeleton and eventual effective segmentation of the coronary arteries.

Evaluation of hepatosteatosis and gallstone disease in patients with chronic kidney disease.

The prevalence rates of hepatosteatosis and gallstones are increasing owing to the multifactorial causes of chronic kidney disease, and the prevalence may change with the availability of different forms of renal replacement therapy. We aimed to determine the incidence or prevalence rates of hepatosteatosis, cholelithiasis, and acute cholecystitis in patients with chronic kidney disease and compare them between renal replacement therapy modalities. A total of 270 patients (90 with chronic kidney disease stages III-V, 90 undergoing peritoneal dialysis, and 90 undergoing hemodialysis) were included and categorized into the pre-dialysis, hemodialysis, and peritoneal dialysis groups. The patients were questioned about previous gallbladder surgeries and chronic diseases. The results of abdominal ultrasonography, tomography, and magnetic resonance imaging were retrospectively evaluated with respect to the findings on the hepatobiliary system. Hepatosteatosis and cholelithiasis were diagnosed by expert radiologists on the basis of abdominal ultrasonography, tomography, and magnetic resonance imaging findings. The prevalence rates of hepatosteatosis, cholelithiasis, and other liver findings were compared between the groups. Hepatosteatosis and cholelithiasis were detected in 16.7% and 21.5% of the 270 cases, respectively. Hepatosteatosis was present in 17.8%, 25.6%, and 6.7% of patients in the pre-dialysis, hemodialysis, and peritoneal dialysis groups, respectively. The prevalence of hepatosteatosis was significantly higher in patients undergoing hemodialysis than in patients undergoing peritoneal dialysis (p = 0.002). However, no statistically significant difference was found between the peritoneal dialysis and pre-dialysis groups or between the hemodialysis and pre-dialysis groups (p >0.05). The prevalence rates of cholelithiasis were 15.6%, 28.9%, and 20.0%, in the pre-dialysis, hemodialysis, and peritoneal dialysis groups, respectively, and there were no statistically significant differences among the groups. The incidence of acute cholecystitis was significantly higher in the hemodialysis group than in the pre-dialysis group (p = 0.006). Our study showed that the hepatobiliary system is frequently affected in chronic kidney disease and that the findings may differ depending on the renal replacement therapy modality.

Multidisciplinary Team Approach in Prostate-Specific Membrane Antigen Theranostics for Prostate Cancer: A Narrative Review

In managing prostate cancer, the integration of multidisciplinary team (MDT) with prostate-specific membrane antigen (PSMA) theranostics marks a significant advancement, addressing the disease's spectrum from indolent forms to aggressive metastatic stages. MDTs, comprising urology, oncology, radiation oncology, pathology, radiology, and nuclear medicine experts, are pivotal in delivering tailored, evidence-based care, essential for the varied clinical presentations of prostate cancer. The introduction of PSMA-targeted theranostics and PSMA positron emission tomography imaging has impacted the approach to diagnosis and treatment, offering enhanced precision in disease localization and enabling more nuanced management strategies for conditions such as oligometastatic prostate cancer, metastatic hormone-sensitive prostate cancer, and metastatic castration-resistant prostate cancer. The collaborative approach of MDTs in utilizing PSMA-targeted radioligand therapy emphasizes meticulous patient selection, predictive assessment of therapy response, and careful management of therapy-related toxicities. Additionally, recent strategies, including combination therapies from ENZA-P and Lu-PARP trials, show potential for improving treatment efficacy. This unified approach showcases the critical role of MDTs in optimizing treatment outcomes, underscoring the importance of collaboration in advancing the treatment of prostate cancer with PSMAtargeted therapies, thereby setting a new paradigm in personalized prostate cancer management.

Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning

ObjectiveTo develop a deep learning (DL) model for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI and further develop a DL model for classifying axial spondyloarthritis (axSpA) and non-axSpA.Materials and methodsThis study retrospectively collected 706 patients with FM who underwent SIJ MRI from center 1 (462 axSpA and 186 non-axSpA) and center 2 (37 axSpA and 21 non-axSpA). Patients from center 1 were divided into the training, validation, and internal test sets (n = 455, 64, and 129). Patients from center 2 were used as the external test set. We developed a UNet-based model to segment FM. Based on segmentation results, a classification model was built to distinguish axSpA and non-axSpA. Dice Similarity Coefficients (DSC) and area under the curve (AUC) were used for model evaluation. Radiologists’ performance without and with model assistance was compared to assess the clinical utility of the models.ResultsOur segmentation model achieved satisfactory DSC of 81.86% ± 1.55% and 85.44% ± 6.09% on the internal cross-validation and external test sets. The classification model yielded AUCs of 0.876 (95% CI: 0.811–0.942) and 0.799 (95% CI: 0.696–0.902) on the internal and external test sets, respectively. With model assistance, segmentation performance was improved for the radiological resident (DSC, 75.70% vs. 82.87%, p < 0.05) and expert radiologist (DSC, 85.03% vs. 85.74%, p > 0.05).ConclusionsDL is a novel method for automatic and accurate segmentation of FM on SIJ MRI and can effectively increase radiologist’s performance, which might assist in improving diagnosis and progression of axSpA.Critical relevance statementDL models allowed automatic and accurate segmentation of FM on sacroiliac joint MRI, which might facilitate quantitative analysis of FM and have the potential to improve diagnosis and prognosis of axSpA.Key points• Deep learning was used for automatic segmentation of fat metaplasia on MRI.• UNet-based models achieved automatic and accurate segmentation of fat metaplasia.• Automatic segmentation facilitates quantitative analysis of fat metaplasia to improve diagnosis and prognosis of axial spondyloarthritis.Graphical

Detection of Pneumonia Using A Hybrid Approach Consisting of MobileNetV2 and Squeeze-and-Excitation Network

Pneumonia is a global health concern, responsible for a significant number of deaths. Its diagnostic challenge arises from visual similarities it shares with various respiratory diseases, such as tuberculosis, complicating accurate identification. Furthermore, the variability in acquiring and processing chest X-ray (CXR) images can impact image quality, posing a hurdle for dependable algorithm development. To address this, resilient data-centric algorithms, trained on comprehensive datasets and validated through diverse imaging methods and radiology expertise, are imperative. This study presents a deep learning approach designed to distinguish between normal and pneumonia cases. The model, a hybrid of MobileNetV2 and the Squeeze-and-Excitation (SE) block, aims to reduce learnable parameters while enhancing feature extraction and classification. Integration of the SE block enhances classification performance, despite a slight parameter increase. The model was trained and tested on a dataset of 5856 CXR images from Kaggle's medical imaging challenge. Results demonstrated the model's exceptional performance, achieving an accuracy of 98.81%, precision of 98.79%, recall rate of 98.24%, and F1-score of 98.51%. Comparative analysis with various Convolutional neural network-based pre-trained models and recent literature studies confirmed its superiority, solidifying its potential as a robust tool for pneumonia detection, thus addressing a critical healthcare need.

Assessment of Thyroid Gland in Children with Point-of-Care Ultrasound (POCUS): Radiological Performance and Feasibility of Handheld Ultrasound in Clinical Practice

Point-of-Care Ultrasound (POCUS) refers to the use of portable ultrasound machines to perform quick and focused ultrasound examinations at a patient’s bedside or point-of-care. POCUS can be performed by all health workers with specific training to use POCUS. The aim of this study was to investigate the radiological performance and feasibility of POCUS using a handheld ultrasound device (HHUSD) in children for examining the thyroid gland. A pediatric endocrinologist performed thyroid imaging in children referred to our hospital with suspected thyroid disease using an HHUSD. The same children underwent ultrasonography (US) imaging using the same device by the first radiologist, and a second radiologist performed thyroid US using an advanced high-range ultrasound device (AHUSD) (defined as the gold-standard method) within two hours. The data obtained by the three researchers were compared with each other. This study included 105 patients [68.6% girls (n=72)] with a mean age 12.8±3.6 years. When the thyroid volume was evaluated, a strong correlation was found between the measurements of the three researchers (AA vs. MG: r=0.963, AA vs. GT: r=0.969, MG vs. GT: r=0.963, p<0.001). According to the Bland-Altman analysis for total thyroid volume, AA measured 0.43 cc [95% confidence interval (CI): -0.89-0.03] smaller than MG, and 0.11 cc (95% CI: -0.30-0.52) larger than GT, whereas MG measured 0.52 cc (95% CI: 0.09-0.94) larger than GT. When evaluated for the presence of goiter and nodules, a near-perfect agreement was found between the results of the three researchers (AA vs. GT; κ=0.863, MG vs. GT; κ=0.887, p<0.001, and AA vs. GT; κ=1.000, MG vs. GT; κ=0.972, p<0.001, respectively). When evaluated in terms of the longest axis of nodules, a high correlation was found between the measurements of the three researchers (AA vs. MG; r=0.993, AA vs. GT; r=0.996, MG vs. GT; r=0.996, p<0.001). When evaluated in terms of the final diagnosis, the evaluations of the three researchers showed excellent agreement with each other (AA vs. GT; κ=0.893, MG vs. GT; κ=0.863, p<0.001, accuracy rate AA vs. GT: 93.3%; MG vs. GT: 91.4%). A pediatric endocrinologist, equipped with sufficient training in thyroid US evaluation, incorporated HHUSD examination as a routine clinical tool in an outpatient setting. It was shown that, they could effectively assess normal thyroid tissue in pediatric patients. Moreover, the HHUSD proved to be useful in detecting thyroid pathologies. However, it is important to note that for a more comprehensive evaluation of thyroid nodules, including detailed assessment and Thyroid Imaging Reporting and Data System (TIRADS) classification, patients should be referred to radiology departments equipped with AHUSD systems. These specialized devices, along with the expertise of radiologists, are essential for in-depth evaluations and accurate classification of thyroid nodules.

Alzheimer's MRI Recognition Based on Convolutional Neural Networks

Alzheimer's disease (AD) is a progressively worsening neurodegenerative disorder, where early diagnosis is crucial for implementing effective disease management strategies. In multimodal diagnostic pathways, Magnetic Resonance Imaging (MRI) plays a pivotal role as a non-invasive imaging technique in disease identification and progression monitoring. Deep learning, particularly Convolutional Neural Networks (CNN), can extract key biomarkers from complex imaging data. By training CNN models to automatically interpret MRI scans, radiology experts can utilize these advanced analytical tools for more efficient and consistent pathological assessments, thereby enhancing clinical decision support systems. This study develops a deep learning-based method for the automatic classification of Alzheimer's brain MRI images, using convolutional neural networks to categorize MRI images into four stages: no dementia, very mild dementia, mild dementia, and moderate dementia. A CNN model is constructed, learning distinctive features of the images through multi-level feature extraction and performing feature map visualization. Early stopping is employed to prevent overfitting. The model is trained on a training set and evaluated on a test set, with performance metrics including confusion matrix, accuracy, precision, recall, F1 score, Kappa coefficient, Matthew’s coefficient, ROC curve with AUC value, and PQ curve with AP value. The results show that the proposed model effectively differentiates between various categories of MRI images, providing valuable tools for early diagnosis and condition monitoring.

Abstract 894: Radiomics at baseline MRI are associated with tumor shrinkage in patients with unresectable renal cell carcinoma treated with neo-adjuvant Cabozantinib

Abstract Background: Neoadjuvant Cabozantinib targeted therapy (nCabo) has been shown to facilitate tumor size reduction in patients with renal cell carcinoma (RCC). However, there is unmet clinical need to identify pre-treatment markers predictive of response to nCabo to limit financial, dose-related toxicity. We investigated computationally derived radiomic signatures from baseline magnetic resonance imaging (MRI) for their association with response to tumor shrinkage following nCabo.Methods Seventeen patients with non-metastatic, clinical stage ≥T3, biopsy-confirmed clear cell RCC were enrolled in a phase II clinical trial (NCT04022343) examining primary tumor response to nCabo. Patients underwent 3 Tesla MRI at baseline, 6 and 12 weeks. Partial response (PR) or stable disease (SD) was determined per Response Evaluation Criteria in Solid Tumors at 12 weeks. Tumor regions of interest (ROI) were delineated on axial, arterial phase T1-weighted (T1W) series under the guidance of expert radiologist. T1W were normalized with respect to enhancement in cortex region of kidney. 75 radiomic features quantifying texture heterogeneity were derived from tumor ROI on a per-voxel basis at baseline. Wilcoxon ranksum test was used to evaluate significant differences in radiomics between patient groups PR and SD. Results: Following nCabo, 6/17 patients experienced PR. 22 radiomic features from T1W quantifying intensity based heterogeneity showed significant differences between patients with SD and PR after nCabo (p&amp;lt;0.05; top 3 in Table). None of the clinical variables showed significant differences between SD and PR. Conclusion: In this proof-of-concept preliminary study, we observed that radiomics at baseline MRI may allow for identifying RCC patients who would favorably respond to nCabo in terms of tumor shrinkage. Future studies will include analysis on longitudinal data, correlation against survival on large-scale datasets. Association between tumor shrinkage following nCabo and radiomic features, clinical variables Stable Disease (N=6) Partial Response (N=11) Category Feature P-value median IQR median IQR Radiomic Haralick 0.01 1.50 0.51 2.31 0.51 Gradient Filter 0.02 88.06 107.28 289.58 107.28 CoLlAGe 0.03 224.28 10.73 210.50 10.73 Clinical Age 0.12 56.00 14.00 52.50 14.00 BMI 0.48 29.90 8.50 27.30 8.50 modified Glasgow Prognostic Score 0.21 1.00 1.00 0.00 1.00 Baseline Tumor Size (cm) 0.48 9.50 5.15 9.50 5.15 ECOG PS at presentation 0.23 0.00 1.00 0.00 1.00 Charlson Comorbidity Index 0.72 6.00 6.00 4.00 6.00 Citation Format: Liping LI, Edouard Nicaise, Benjamin Schmeusser, Abhishek Midya, Amir Davarpanahfakhr, Anant Madabhushi, Mehmet Asim Bilen, Viraj A. Master, Rakesh Shiradkar. Radiomics at baseline MRI are associated with tumor shrinkage in patients with unresectable renal cell carcinoma treated with neo-adjuvant Cabozantinib [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 894.

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods.

Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters. A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150cc, small ≤ 25cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model. 683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1cc [9.05-329cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001). Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.

Abnormal Brachial Plexus Differentiation from Routine Magnetic Resonance Imaging: An AI-based Approach

Automatic abnormality identification of brachial plexus (BP) from normal magnetic resonance imaging to localize and identify a neurologic injury in clinical practice (MRI) is still a novel topic in brachial plexopathy. This study developed and evaluated an approach to differentiate abnormal BP with artificial intelligence (AI) over three commonly used MRI sequences, i.e. T1, FLUID sensitive and post-gadolinium sequences. A BP dataset was collected by radiological experts and a semi-supervised artificial intelligence method was used to segment the BP (based on nnU-net). Hereafter, a radiomics method was utilized to extract 107 shape and texture features from these ROIs. From various machine learning methods, we selected six widely recognized classifiers for training our Brachial plexus (BP) models and assessing their efficacy. To optimize these models, we introduced a dynamic feature selection approach aimed at discarding redundant and less informative features. Our experimental findings demonstrated that, in the context of identifying abnormal BP cases, shape features displayed heightened sensitivity compared to texture features. Notably, both the Logistic classifier and Bagging classifier outperformed other methods in our study. These evaluations illuminated the exceptional performance of our model trained on FLUID-sensitive sequences, which notably exceeded the results of both T1 and post-gadolinium sequences. Crucially, our analysis highlighted that both its classification accuracies and AUC score (area under the curve of receiver operating characteristics) over FLUID-sensitive sequence exceeded 90%. This outcome served as a robust experimental validation, affirming the substantial potential and strong feasibility of integrating AI into clinical practice.

Deep Learning-based Approach for Brainstem and Ventricular MR Planimetry: Application in Patients with Progressive Supranuclear Palsy.

Purpose To develop a fast and fully automated deep learning (DL)-based method for the MRI planimetric segmentation and measurement of the brainstem and ventricular structures most affected in patients with progressive supranuclear palsy (PSP). Materials and Methods In this retrospective study, T1-weighted MR images in healthy controls (n = 84) were used to train DL models for segmenting the midbrain, pons, middle cerebellar peduncle (MCP), superior cerebellar peduncle (SCP), third ventricle, and frontal horns (FHs). Internal, external, and clinical test datasets (n = 305) were used to assess segmentation model reliability. DL masks from test datasets were used to automatically extract midbrain and pons areas and the width of MCP, SCP, third ventricle, and FHs. Automated measurements were compared with those manually performed by an expert radiologist. Finally, these measures were combined to calculate the midbrain to pons area ratio, MR parkinsonism index (MRPI), and MRPI 2.0, which were used to differentiate patients with PSP (n = 71) from those with Parkinson disease (PD) (n = 129). Results Dice coefficients above 0.85 were found for all brain regions when comparing manual and DL-based segmentations. A strong correlation was observed between automated and manual measurements (Spearman ρ > 0.80, P < .001). DL-based measurements showed excellent performance in differentiating patients with PSP from those with PD, with an area under the receiver operating characteristic curve above 0.92. Conclusion The automated approach successfully segmented and measured the brainstem and ventricular structures. DL-based models may represent a useful approach to support the diagnosis of PSP and potentially other conditions associated with brainstem and ventricular alterations. Keywords: MR Imaging, Brain/Brain Stem, Segmentation, Quantification, Diagnosis, Convolutional Neural Network Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Mohajer in this issue.

OA-GAN: organ-aware generative adversarial network for synthesizing contrast-enhanced medical images

Contrast-enhanced computed tomography (CE-CT) images are vital for clinical diagnosis of focal liver lesions (FLLs). However, the use of CE-CT images imposes a significant burden on patients due to the injection of contrast agents and extended shooting. Deep learning-based image synthesis models offer a promising solution that synthesizes CE-CT images from non-contrasted CT (NC-CT) images. Unlike natural images, medical image synthesis requires a specific focus on certain organs or localized regions to ensure accurate diagnosis. Determining how to effectively emphasize target organs poses a challenging issue in medical image synthesis. To solve this challenge, we present a novel CE-CT image synthesis model called, Organ-Aware Generative Adversarial Network (OA-GAN). The OA-GAN comprises an organ-aware (OA) network and a dual decoder-based generator. First, the OA network learns the most discriminative spatial features about the target organ (i.e. liver) by utilizing the ground truth organ mask as localization cues. Subsequently, NC-CT image and captured feature are fed into the dual decoder-based generator, which employs a local and global decoder network to simultaneously synthesize the organ and entire CECT image. Moreover, the semantic information extracted from the local decoder is transferred to the global decoder to facilitate better reconstruction of the organ in entire CE-CT image. The qualitative and quantitative evaluation on a CE-CT dataset demonstrates that the OA-GAN outperforms state-of-the-art approaches for synthesizing two types of CE-CT images such as arterial phase and portal venous phase. Additionally, subjective evaluations by expert radiologists and a deep learning-based FLLs classification also affirm that CE-CT images synthesized from the OA-GAN exhibit a remarkable resemblance to real CE-CT images.

Editor's Choice – Development and Testing of Step, Error, and Event Frameworks to Evaluate Technical Performance in Peripheral Endovascular Interventions

Tools for endovascular performance assessment are necessary in competency based education. This study aimed to develop and test a detailed analysis tool to assess steps, errors, and events in peripheral endovascular interventions (PVI). A modified Delphi consensus was used to identify steps, errors, and events in iliac-femoral-popliteal endovascular interventions. International experts in vascular surgery, interventional radiology, cardiology, and angiology were identified, based on their scientific track record. In an initial open ended survey round, experts volunteered a comprehensive list of steps, errors, and events. The items were then rated on a 5-point Likert scale until consensus was reached with a pre-defined threshold (Cronbach's alpha > 0.7) and > 70% expert agreement. An experienced endovascular surgeon applied the finalised frameworks on ten previously videorecorded elective PVI cases. The expert consensus panel was formed by 28 of 98 invited proceduralists, consisting of three angiologists, seven interventional radiologists, five cardiologists, and 13 vascular surgeons, with 29% from North America and 71% from Europe. The Delphi process was completed after three rounds (Cronbach's alpha; αsteps = 0.79; αerrors = 0.90; αevents = 0.90), with 15, 26, and 18 items included in the final step (73 - 100% agreement), error (73 - 100% agreement), and event (73 - 100% agreement) frameworks, respectively. The median rating time per case was 4.3 hours (IQR 3.2, 5 hours). A median of 55 steps (IQR 40, 67), 27 errors (IQR 21, 49), and two events (IQR 1, 6) were identified per case. An evaluation tool for the procedural steps, errors, and events in iliac-femoral-popliteal endovascular procedures was developed through a modified Delphi consensus and applied to recorded intra-operative data to identify hazardous steps, common errors, and events. Procedural mastery may be promoted by using the frameworks to provide endovascular proceduralists with detailed technical performance feedback.

Emb-trattunet: a novel edge loss function and transformer-CNN architecture for multi-classes pneumonia infection segmentation in low annotation regimes

One of the primary challenges in applying deep learning approaches to medical imaging is the limited availability of data due to various factors. These factors include concerns about data privacy and the requirement for expert radiologists to perform the time-consuming and labor-intensive task of labeling data, particularly for tasks such as segmentation. Consequently, there is a critical need to develop novel approaches for few-shot learning tasks in this domain. In this work, we propose a Novel CNN-Transformer Fusion scheme to segment Multi-classes pneumonia infection from limited CT-scans data. In total, there are three main contributions: (i) CNN-Transformer encoders fusion, which allows to extract and fuse richer features in the encoding phase, which contains: local, global and long-range dependencies features, (ii) Multi-Branches Skip Connection (MBSC) is proposed to extract and fuse richer features from the encoder features then integrate them into the decoder layers, where MBSC blocks extract higher-level features related to the finer details of different infection types, and (iii) a Multi-classes Boundary Aware Cross-Entropy (MBA-CE) Loss function is proposed to deal with fuzzy boundaries, enhance the separability between classes and give more attention to the minority classes. The performance of the proposed approach is evaluated using two evaluation scenarios and compared with different baseline and state-of-the-art segmentation architectures for Multi-classes Covid-19 segmentation. The obtained results show that our approach outperforms the comparison methods in both Ground-Glass Opacity (GGO) and Consolidation segmentation. On the other hand, our approach shows consistent performance when the training data is reduced to half, which proves the efficiency of our approach in few-shot learning. In contrast, the performance of the comparison methods drops in this scenario. Moreover, our approach is able to deal with imbalanced data classes. These advantages prove the effectiveness and efficiency of the proposed EMB-TrAttUnet approach in a pandemic scenario where time is critical to save patient lives.

Breast cancer diagnosis model using stacked autoencoder with particle swarm optimization

Breast cancer (BrC) stands as the most prevalent cancer affecting women globally, comprising 24.5% of all female cancer diagnoses and contributing to 15.0% of total cancer-related fatalities. The timely detection and precise categorization of breast cancer play pivotal roles in enhancing patient prognosis and treatment outcomes. The main goal is to enhance the precision of classifying mammogram images, thus offering vital support to radiology experts in diagnosing BrCs. The proposed model encompasses several pivotal stages, including pre-processing, feature extraction, segmentation, and classification. To assess the model's efficacy, we employed the INBreast dataset. During pre-processing, mammogram images were enhanced through a customized contrast-limited adaptive histogram equalization (mCLAHE) technique coupled with data augmentation. Segmentation was executed utilizing the Res-SegNet model, and feature extraction employing the VGG-19 model. The classification was conducted via a stacked autoencoder (SAE) with particle swarm optimization (PSO). Our proposed model exhibited notably high performance compared to alternative models such as CNN, Yolo-v4, and Inception-v3. The results unveiled an accuracy of 98.33%, precision of 99.39%, recall of 98.78%, specificity of 93.75%, an F1-score of 99.08%, and an MCC score of 90.04%.

HIGH-RESOLUTION COMPUTED TOMOGRAPHY IN DIAGNOSING AND MONITORING VARIOUS INTERSTITIAL LUNG DISEASES

Objective: Interstitial lung diseases (ILDs) are difficult to diagnose and require accurate imaging methods. The purpose of this work is to investigate ILD patterns and their relationships to pulmonary function using high-resolution computed tomography (HRCT). The aim is to augment our comprehension of ILDs, thereby facilitating customized approaches to diagnosis and treatment Methods: We recruited 50 ILD patients with radiological and clinical issues for a single-center trial. Spirometric data, symptoms, and demographics were recorded on comprehensive patient proformas. An expert radiologist used a Siemens-Somatom 6-slice CT scanner to analyze the HRCT. Pulmonary function indices were obtained using spirometry, which was carried out using a Medisoft Spiro Air spirometer. Results: In fifty cases with ILD, common features on HRCT were uneven pleural borders, ground glass opacities, and septal/subpleural lines. The complex interaction between radiological symptoms and respiratory health was highlighted by the substantial correlations seen between HRCT severities; extent scores, and reduced pulmonary function. Conclusion: The study reinforces the necessity for individualized diagnostic and treatment methods in the ILD respiratory landscape by providing detailed insights into their disease patterns and relationships.

(271) Assessment of Varicocele Bilaterality in Infertile Men

Abstract Introduction Varicocele is the most common correctable cause of male factor infertility. It has always been a debatable subject as regard how it affects fertility and the best way to treat. However, there is a wide consensus nowadays that varicocelectomy improve male fertility potentials. Proper assessment of the disease bilaterality is crucial not to miss one side and not to jeopardize treatment outcome. Objective The primary outcome measure was to assess disease bilaterality and the secondary outcome measure was to report on improvement in semen 3 and 6 months post varicocelectomy and pregnancy rate 1 year post surgery. Methods This prospective study was conducted between January 2019 and January 2022. Infertile males with varicoceles underwent microsurgical subinguinal varicocelectomy by expert uroandrologists. Patients who were referred as unilateral varicoceles had their CDUS repeated for assessment of missed concomitant contralateral varicocele. Then, patients who were diagnosed with bilateral varicoceles underwent bilateral subinguinal ligation straight away. Those who were referred with unilateral varicocele had their palpable sides operated on first; then the contralateral side was also explored using an intraoperative Doppler device and the maximal vein diameter was measured. Patients came for follow for at least 6 months after surgery to evaluate any complications and assess improvement in semen parameters. Gynecologists also reported on normal pregnancy rate 1 year after surgery. Results A total of 329 cases completed the study. A hundred cases (30.4%) were initially referred as unilateral varicoceles and 229 (69.6%) as bilateral varicoceles. After reassessment of the study population, bilaterality of varicocele was found to be as high as 98.5% (324/329). This is statistically significantly higher than initial US (P&amp;lt;0.001). Repeat CDUS strongly correlated with the intraoperative measured varicocele diameter [r=0.9, P&amp;lt;0.001]. Moreover, sperm parameters showed significant improvement 3 and 6 months post varicocelectomy. Normal pregnancy after 1 year of surgery occurred in 118 cases (35.9%). Conclusions Varicocele bilaterality is underreported. Thorough assessment by expert radiologists and andrologists is of paramount importance not to miss significant pathology or hazard treatment outcome. Disclosure No.

Machine learning based prediction of image quality in prostate MRI using rapid localizer images.

Diagnostic performance of prostate MRI depends on high-quality imaging. Prostate MRI quality is inversely proportional to the amount of rectal gas and distention. Early detection of poor-quality MRI may enable intervention to remove gas or exam rescheduling, saving time. We developed a machine learning based quality prediction of yet-to-be acquired MRI images solely based on MRI rapid localizer sequence, which can be acquired in a few seconds. The dataset consists of 213 (147 for training and 64 for testing) prostate sagittal T2-weighted (T2W) MRI localizer images and rectal content, manually labeled by an expert radiologist. Each MRI localizer contains seven two-dimensional (2D) slices of the patient, accompanied by manual segmentations of rectum for each slice. Cascaded and end-to-end deep learning models were used to predict the quality of yet-to-be T2W, DWI, and apparent diffusion coefficient (ADC) MRI images. Predictions were compared to quality scores determined by the experts using area under the receiver operator characteristic curve and intra-class correlation coefficient. In the test set of 64 patients, optimal versus suboptimal exams occurred in 95.3% (61/64) versus 4.7% (3/64) for T2W, 90.6% (58/64) versus 9.4% (6/64) for DWI, and 89.1% (57/64) versus 10.9% (7/64) for ADC. The best performing segmentation model was 2D U-Net with ResNet-34 encoder and ImageNet weights. The best performing classifier was the radiomics based classifier. A radiomics based classifier applied to localizer images achieves accurate diagnosis of subsequent image quality for T2W, DWI, and ADC prostate MRI sequences.

Factors associated with radiological misstaging of pancreatic ductal adenocarcinoma: A retrospective observational study

PurposeAccurate staging of disease is vital in determining appropriate care for patients with pancreatic ductal adenocarcinoma (PDAC). It has been shown that the quality of scans and the experience of a radiologist can impact computed tomography (CT) based assessment of disease. The aim of the current study was to evaluate the impact of the rereading of outside hospital (OH) CT by an expert radiologist and a repeat pancreatic protocol CT (PPCT) on staging of disease. MethodsPatients evaluated at the our institute's pancreatic multidisciplinary clinic (2006 to 2014) with OH scan and repeat PPCT performed within 30 days were included. In-house radiologists staged disease using OH scans and repeat PPCT, and factors associated with misstaging were determined. ResultsThe study included 100 patients, with a median time between OH scan and PPCT of 19 days (IQR: 13–23 days.) Stage migration was mostly accounted for by upstaging of disease (58.8 % to 83.3 %) in all comparison groups. When OH scans were rereviewed, 21.5 % of the misstaging was due to missed metastases, however, when rereads were compared to the PPCT, occult metastases accounted for the majority of misstaged patients (62.5 %). Potential factors associated with misstaging were primarily related to imaging technique. ConclusionA repeat PPCT results in increased detection of metastatic disease that rereviews of OH scans may otherwise miss. Accessible insurance coverage for repeat PPCT imaging even within 30 days of an OH scan could help optimize delivery of care and alleviate burdens associated with misstaging.