Search Results (479)

Penetrating keratoplasty (PK) is a corneal surgery that is employed to repair the full-thickness corneal lesion. This study aimed to survey the possible systemic risk factors of infectious keratitis after penetrating keratoplasty (PK) via the Taiwan National Health Insurance Research Database (NHIRD). A retrospective case–control study was conducted, and 327 patients who received the PK were enrolled after exclusion. The main outcome was the development of infectious keratitis, and people were divided into those with infectious keratitis and those without the outcome. Cox proportional hazard regression was conducted to produce adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) of specific demographic indexes and systemic diseases on infectious keratitis. There were 68 patients who developed infectious keratitis after the whole follow-up period. The diabetes mellitus (DM) (aHR: 1.440, 95% CI: 1.122–2.874, p = 0.0310) and chronic ischemic heart disease (aHR: 1.534, 95% CI: 1.259–3.464, p = 0.0273) groups demonstrated a significant association with infectious keratitis. The DM group also revealed significant influence on infectious keratitis development in all the subgroups (all p < 0.05). Nevertheless, the effect of chronic ischemic heart disease on infectious keratitis was only significant on those aged older than 60 years (p = 0.0094) and both sexes (both p < 0.05). In conclusion, the presence of DM and chronic ischemic heart disease are associated with infectious keratitis after PK. However, local risk factors for infectious keratitis developed in those receiving PK had not been evaluated. Full article

The integrity of the reconstructed human epidermis generated in vitro can be assessed using histological analyses combined with immunohistochemical staining of keratinocyte differentiation markers. Technical differences during the preparation and capture of stained images may influence the outcome of computational methods. Due to the specific nature of the analyzed material, no annotated datasets or dedicated methods are publicly available. Using a dataset with 598 unannotated images showing cross-sections of in vitro reconstructed human epidermis stained with DAB-based immunohistochemistry reaction to visualize four different keratinocyte differentiation marker proteins (filaggrin, keratin 10, Ki67, HSPA2) and counterstained with hematoxylin, we developed an unsupervised method for the detection and quantification of immunohistochemical staining. The pipeline consists of the following steps: (i) color normalization; (ii) color deconvolution; (iii) morphological operations; (iv) automatic image rotation; and (v) clustering. The most effective combination of methods includes (i) Reinhard’s normalization; (ii) Ruifrok and Johnston color-deconvolution method; (iii) proposed image-rotation method based on boundary distribution of image intensity; and (iv) k-means clustering. The results of the work should enhance the performance of quantitative analyses of protein markers in reconstructed human epidermis samples and enable the comparison of their spatial distribution between different experimental conditions. Full article

The accurate and efficient segmentation of the spine is important in the diagnosis and treatment of spine malfunctions and fractures. However, it is still challenging because of large inter-vertebra variations in shape and cross-image localization of the spine. In previous methods, convolutional neural networks (CNNs) have been widely applied as a vision backbone to tackle this task. However, these methods are challenged in utilizing the global contextual information across the whole image for accurate spine segmentation because of the inherent locality of the convolution operation. Compared with CNNs, the Vision Transformer (ViT) has been proposed as another vision backbone with a high capacity to capture global contextual information. However, when the ViT is employed for spine segmentation, it treats all input tokens equally, including vertebrae-related tokens and non-vertebrae-related tokens. Additionally, it lacks the capability to locate regions of interest, thus lowering the accuracy of spine segmentation. To address this limitation, we propose a novel Vertebrae-aware Vision Transformer (VerFormer) for automatic spine segmentation from CT images. Our VerFormer is designed by incorporating a novel Vertebrae-aware Global (VG) block into the ViT backbone. In the VG block, the vertebrae-related global contextual information is extracted by a Vertebrae-aware Global Query (VGQ) module. Then, this information is incorporated into query tokens to highlight vertebrae-related tokens in the multi-head self-attention module. Thus, this VG block can leverage global contextual information to effectively and efficiently locate spines across the whole input, thus improving the segmentation accuracy of VerFormer. Driven by this design, the VerFormer demonstrates a solid capacity to capture more discriminative dependencies and vertebrae-related context in automatic spine segmentation. The experimental results on two spine CT segmentation tasks demonstrate the effectiveness of our VG block and the superiority of our VerFormer in spine segmentation. Compared with other popular CNN- or ViT-based segmentation models, our VerFormer shows superior segmentation accuracy and generalization. Full article

Three-dimensional echocardiography (3DE) is currently the preferred method for monitoring left ventricular ejection fraction (LVEF) in cancer patients receiving potentially cardiotoxic anti-neoplastic therapy. In Denmark, however, the traditional standard for LVEF monitoring has been rooted in nuclear medicine departments utilizing equilibrium radionuclide angiography (ERNA). Although ERNA remains a principal modality, there is an emerging trend towards the adoption of echocardiography for this purpose. Given this context, assessing the reproducibility of 3DE among non-specialized medical personnel is crucial for its clinical adoption in such departments. To assess the feasibility of 3DE for LVEF measurements by technologists, we evaluated the repeatability and reproducibility of two moderately experienced technologists. They performed 3DE on 12 volunteers over two sessions, with a collaborative review of the results from the first session before the second session. Two-way intraclass correlation values increased from 0.03 to 0.77 across the sessions. This increase in agreement was mainly due to the recognition of false low measurements. Our findings underscore the importance of incorporating reproducibility exercises in the context of 3DE, especially when operated by technologists. Additionally, routine control of the acquisitions by physicians is deemed necessary. Ensuring these hurdles are adequately managed enables the adoption of 3DE for LVEF measurements by technologists. Full article

Brain tumors are a leading cause of death globally, with numerous types varying in malignancy, and only 12% of adults diagnosed with brain cancer survive beyond five years. This research introduces a hyperparametric convolutional neural network (CNN) model to identify brain tumors, with significant practical implications. By fine-tuning the hyperparameters of the CNN model, we optimize feature extraction and systematically reduce model complexity, thereby enhancing the accuracy of brain tumor diagnosis. The critical hyperparameters include batch size, layer counts, learning rate, activation functions, pooling strategies, padding, and filter size. The hyperparameter-tuned CNN model was trained on three different brain MRI datasets available at Kaggle, producing outstanding performance scores, with an average value of 97% for accuracy, precision, recall, and F1-score. Our optimized model is effective, as demonstrated by our methodical comparisons with state-of-the-art approaches. Our hyperparameter modifications enhanced the model performance and strengthened its capacity for generalization, giving medical practitioners a more accurate and effective tool for making crucial judgments regarding brain tumor diagnosis. Our model is a significant step in the right direction toward trustworthy and accurate medical diagnosis, with practical implications for improving patient outcomes. Full article

In this work, several machine learning (ML) algorithms, both classical ML and modern deep learning, were investigated for their ability to improve the performance of a pipeline for the segmentation and classification of prostate lesions using MRI data. The algorithms were used to perform a binary classification of benign and malignant tissue visible in MRI sequences. The model choices include support vector machines (SVMs), random decision forests (RDFs), and multi-layer perceptrons (MLPs), along with radiomic features that are reduced by applying PCA or mRMR feature selection. Modern CNN-based architectures, such as ConvNeXt, ConvNet, and ResNet, were also evaluated in various setups, including transfer learning. To optimize the performance, different approaches were compared and applied to whole images, as well as gland, peripheral zone (PZ), and lesion segmentations. The contribution of this study is an investigation of several ML approaches regarding their performance in prostate cancer (PCa) diagnosis algorithms. This work delivers insights into the applicability of different approaches for this context based on an exhaustive examination. The outcome is a recommendation or preference for which machine learning model or family of models is best suited to optimize an existing pipeline when the model is applied as an upstream filter. Full article

(1) Background: Identifying acute aortic syndrome (AAS) and thoracic aortic aneurysm (TAA) in busy emergency departments (EDs) is crucial due to their life-threatening nature, necessitating timely and accurate diagnosis. (2) Methods: This retrospective case-control study was conducted in the ED of three hospitals. Adult patients visiting the ED between 1 January 2010 and 1 January 2020 with a chief complaint of chest or back pain were enrolled in the study. The collected chest radiography (CXRs) data were divided into training (80%) and testing (20%) datasets. The training dataset was trained by four different convolutional neural network (CNN) models. (3) Results: A total of 1625 patients were enrolled in this study. The InceptionV3 model achieved the highest F1 score of 0.76. (4) Conclusions: Analysis of CXRs using a CNN-based model provides a novel tool for clinicians to interpret ED patients with chest pain and suspected AAS and TAA. The integration of such imaging tools into ED could be considered in the future to enhance the diagnostic workflow for clinically fatal diseases. Full article

Background and Objectives: Integrating large language models (LLMs) such as GPT-4 Turbo into diagnostic imaging faces a significant challenge, with current misdiagnosis rates ranging from 30–50%. This study evaluates how prompt engineering and confidence thresholds can improve diagnostic accuracy in neuroradiology. Methods: We analyze 751 neuroradiology cases from the American Journal of Neuroradiology using GPT-4 Turbo with customized prompts to improve diagnostic precision. Results: Initially, GPT-4 Turbo achieved a baseline diagnostic accuracy of 55.1%. By reformatting responses to list five diagnostic candidates and applying a 90% confidence threshold, the highest precision of the diagnosis increased to 72.9%, with the candidate list providing the correct diagnosis at 85.9%, reducing the misdiagnosis rate to 14.1%. However, this threshold reduced the number of cases that responded. Conclusions: Strategic prompt engineering and high confidence thresholds significantly reduce misdiagnoses and improve the precision of the LLM diagnostic in neuroradiology. More research is needed to optimize these approaches for broader clinical implementation, balancing accuracy and utility. Full article

Background and Purpose: This study aimed to identify the imaging characteristics and discriminate the etiology of acute internal carotid artery occlusion (ICAO) on computed tomography angiography (CTA) in patients with acute ischemic stroke. Materials and Methods: We retrospectively evaluated consecutive patients who underwent endovascular thrombectomy for acute ICAO. Contrast filling of the extracranial ICA in preprocedural CTA was considered apparent ICAO. Non-contrast filling of the extracranial ICA was evaluated according to the contrast-filled lumen configuration, lumen margin and location, Hounsfield units of the non-attenuating segment, and presence of calcification or an intimal flap. Digital subtraction angiography findings were the reference standard for ICAO etiology and the occlusion site. A diagnostic tree was derived using significant variables according to pseudo-occlusion, atherosclerotic vascular disease (ASVD), thrombotic occlusion, and dissection. Results: A total of 114 patients showed apparent ICAO (n = 21), pseudo-occlusion (n = 51), ASVD (n = 27), thrombotic occlusion (n = 9), or dissection (n = 6). Most pseudo-occlusions (50/51, 98.0%) showed dependent locations with ill-defined contrast column margins and classic flame or beak shapes. The most common occlusion site of pseudo-occlusion was the petro-cavernous ICA (n = 32, 62.7%). Apparent ICAO mainly appeared in cases with occlusion distal to the posterior communicating artery orifice. ASVD showed beak or blunt shapes in the presence of low-density plaques or dense calcifications. Dissection revealed flame- or beak-shaped appearances with circumscribed margins. Thrombotic occlusions tended to appear blunt-shaped. The decision-tree model showed a 92.5% overall accuracy. Conclusions: CTA characteristics may help diagnose ICAO etiology. We provide a simple and easy decision-making model to inform endovascular thrombectomy. Full article

Breast cancer diagnosis from histopathology images is often time consuming and prone to human error, impacting treatment and prognosis. Deep learning diagnostic methods offer the potential for improved accuracy and efficiency in breast cancer detection and classification. However, they struggle with limited data and subtle variations within and between cancer types. Attention mechanisms provide feature refinement capabilities that have shown promise in overcoming such challenges. To this end, this paper proposes the Efficient Channel Spatial Attention Network (ECSAnet), an architecture built on EfficientNetV2 and augmented with a convolutional block attention module (CBAM) and additional fully connected layers. ECSAnet was fine-tuned using the BreakHis dataset, employing Reinhard stain normalization and image augmentation techniques to minimize overfitting and enhance generalizability. In testing, ECSAnet outperformed AlexNet, DenseNet121, EfficientNetV2-S, InceptionNetV3, ResNet50, and VGG16 in most settings, achieving accuracies of 94.2% at 40×, 92.96% at 100×, 88.41% at 200×, and 89.42% at 400× magnifications. The results highlight the effectiveness of CBAM in improving classification accuracy and the importance of stain normalization for generalizability. Full article

Objectives: We aimed to provide data of nerve sizes and echogenicity reference values of the Lithuanian population. Methods: High-resolution ultrasound was bilaterally performed according to the Ultrasound Pattern Sum Score and Neuropathy ultrasound protocols for healthy Lithuanian adults. Cross-sectional area (CSA) measurement and echogenicity were used as the main parameters for investigation. Echogenicity was evaluated using ImageJ, and nerves were categorized in classes according to echogenicity. Results: Of 125 subjects enrolled, 63 were males (mean age 47.57 years, range 25–78 years) and 62 were females (mean age 50.50 years, range 25–80 years). Reference values of nerve sizes and values of echogenicity as a fraction of black in percentage of cervical roots, upper and middle trunks of the brachial plexus and the following nerves: vagal, median, ulnar, radial, superficial radial, tibial, fibular, and sural in standard regions were established. Mild to moderate correlations were found between nerves CSA, echogenicity values and anthropometric measurements with the differences according to sex. Inter-rater (ICC 0.93; 95% CI 0.92–0.94) and intra-rater (ICC 0.94; 95% CI 0.93–0.95) reliability was excellent. Conclusions: Reference values of nerve size and echogenicity of Lithuanians were presented for the first time as a novel such kind of publication from the Baltic countries. Full article

In this research, we introduce a network that can identify pneumonia, COVID-19, and tuberculosis using X-ray images of patients’ chests. The study emphasizes tuberculosis, COVID-19, and healthy lung conditions, discussing how advanced neural networks, like VGG16 and ResNet50, can improve the detection of lung issues from images. To prepare the images for the model’s input requirements, we enhanced them through data augmentation techniques for training purposes. We evaluated the model’s performance by analyzing the precision, recall, and F1 scores across training, validation, and testing datasets. The results show that the ResNet50 model outperformed VGG16 with accuracy and resilience. It displayed superior ROC AUC values in both validation and test scenarios. Particularly impressive were ResNet50’s precision and recall rates, nearing 0.99 for all conditions in the test set. On the hand, VGG16 also performed well during testing—detecting tuberculosis with a precision of 0.99 and a recall of 0.93. Our study highlights the performance of our deep learning method by showcasing the effectiveness of ResNet50 over traditional approaches like VGG16. This progress utilizes methods to enhance classification accuracy by augmenting data and balancing them. This positions our approach as an advancement in using state-of-the-art deep learning applications in imaging. By enhancing the accuracy and reliability of diagnosing ailments such as COVID-19 and tuberculosis, our models have the potential to transform care and treatment strategies, highlighting their role in clinical diagnostics. Full article

Computed tomography (CT) scans have recently emerged as a major technique for the fast diagnosis of lung diseases via image classification techniques. In this study, we propose a method for the diagnosis of COVID-19 disease with improved accuracy by utilizing graph convolutional networks (GCN) at various layer formations and kernel sizes to extract features from CT scan images. We apply a U-Net model to aid in segmentation and feature extraction. In contrast with previous research retrieving deep features from convolutional filters and pooling layers, which fail to fully consider the spatial connectivity of the nodes, we employ GCNs for classification and prediction to capture spatial connectivity patterns, which provides a significant association benefit. We handle the extracted deep features to form an adjacency matrix that contains a graph structure and pass it to a GCN along with the original image graph and the largest kernel graph. We combine these graphs to form one block of the graph input and then pass it through a GCN with an additional dropout layer to avoid overfitting. Our findings show that the suggested framework, called the feature-extracted graph convolutional network (FGCN), performs better in identifying lung diseases compared to recently proposed deep learning architectures that are not based on graph representations. The proposed model also outperforms a variety of transfer learning models commonly used for medical diagnosis tasks, highlighting the abstraction potential of the graph representation over traditional methods. Full article

Reduced lymphocyte counts in peripheral blood are one of the most common observations in acute phases of viral infections. Although many studies have already examined the impact of immune (dys)regulation during SARS-CoV-2 infection, there are still uncertainties about the long-term consequences for lymphocyte homeostasis. Furthermore, as persistent cellular aberrations have been described following other viral infections, patients with “Post-COVID-19 Condition” (PCC) may present similarly. In order to investigate cellular changes in the adaptive immune system, we performed a retrospective analysis of flow cytometric data from lymphocyte subpopulations in 106 patients with confirmed SARS-CoV-2 infection who received medical care at our institution. The patients were divided into three groups according to the follow-up date; laboratory analyses of COVID-19 patients were compared with 28 unexposed healthy controls. Regarding B lymphocyte subsets, levels of IgA + CD27+, IgG + CD27+, IgM + CD27− and switched B cells were significantly reduced at the last follow-up compared to unexposed healthy controls (UHC). Of the 106 COVID-19 patients, 56 were clinically classified as featuring PCC. Significant differences between PCC and COVID-19 convalescents compared to UHC were observed in T helper cells and class-switched B cells. However, we did not detect specific or long-lasting immune cellular changes in PCC compared to the non-post-COVID-19 condition. Full article