Objective: To establish a machine learning model based on radiomics and clinical features derived from non-contrast CT to predict futile recanalization (FR) in patients with anterior circulation acute ischemic stroke (AIS) undergoing endovascular treatment.
Methods: A retrospective analysis was conducted on 174 patients who underwent endovascular treatment for acute anterior circulation ischemic stroke between January 2020 and December 2023. FR was defined as successful recanalization but poor prognosis at 90 days (modified Rankin Scale, mRS 4-6). Radiomic features were extracted from non-contrast CT and selected using the least absolute shrinkage and selection operator (LASSO) regression method. Logistic regression (LR) model was used to build models based on radiomic and clinical features. A radiomics-clinical nomogram model was developed, and the predictive performance of the models was evaluated using area under the curve (AUC), accuracy, sensitivity, and specificity.
Results: A total of 174 patients were included. 2016 radiomic features were extracted from non-contrast CT, and 9 features were selected to build the radiomics model. Univariate and stepwise multivariate analyses identified admission NIHSS score, hemorrhagic transformation, NLR, and admission blood glucose as independent factors for building the clinical model. The AUC of the radiomics-clinical nomogram model in the training and testing cohorts were 0.860 (95%CI 0.801-0.919) and 0.775 (95%CI 0.605-0.945), respectively.
Conclusion: The radiomics-clinical nomogram model based on non-contrast CT demonstrated satisfactory performance in predicting futile recanalization in patients with anterior circulation acute ischemic stroke.
Medical imaging stands as a critical component in diagnosing various diseases, where traditional methods often rely on manual interpretation and conventional machine learning techniques. These approaches, while effective, come with inherent limitations such as subjectivity in interpretation and constraints in handling complex image features. This research paper proposes an integrated deep learning approach utilizing pre-trained models-VGG16, ResNet50, and InceptionV3-combined within a unified framework to improve diagnostic accuracy in medical imaging. The method focuses on lung cancer detection using images resized and converted to a uniform format to optimize performance and ensure consistency across datasets. Our proposed model leverages the strengths of each pre-trained network, achieving a high degree of feature extraction and robustness by freezing the early convolutional layers and fine-tuning the deeper layers. Additionally, techniques like SMOTE and Gaussian Blur are applied to address class imbalance, enhancing model training on underrepresented classes. The model's performance was validated on the IQ-OTH/NCCD lung cancer dataset, which was collected from the Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases over a period of three months in fall 2019. The proposed model achieved an accuracy of 98.18%, with precision and recall rates notably high across all classes. This improvement highlights the potential of integrated deep learning systems in medical diagnostics, providing a more accurate, reliable, and efficient means of disease detection.
Background: Cancer pathology shows disease development and associated molecular features. It provides extensive phenotypic information that is cancer-predictive and has potential implications for planning treatment. Based on the exceptional performance of computational approaches in the field of digital pathogenic, the use of rich phenotypic information in digital pathology images has enabled us to identify low-level gliomas (LGG) from high-grade gliomas (HGG). Because the differences between the textures are so slight, utilizing just one feature or a small number of features produces poor categorization results.
Methods: In this work, multiple feature extraction methods that can extract distinct features from the texture of histopathology image data are used to compare the classification outcomes. The successful feature extraction algorithms GLCM, LBP, multi-LBGLCM, GLRLM, color moment features, and RSHD have been chosen in this paper. LBP and GLCM algorithms are combined to create LBGLCM. The LBGLCM feature extraction approach is extended in this study to multiple scales using an image pyramid, which is defined by sampling the image both in space and scale. The preprocessing stage is first used to enhance the contrast of the images and remove noise and illumination effects. The feature extraction stage is then carried out to extract several important features (texture and color) from histopathology images. Third, the feature fusion and reduction step is put into practice to decrease the number of features that are processed, reducing the computation time of the suggested system. The classification stage is created at the end to categorize various brain cancer grades. We performed our analysis on the 821 whole-slide pathology images from glioma patients in the Cancer Genome Atlas (TCGA) dataset. Two types of brain cancer are included in the dataset: GBM and LGG (grades II and III). 506 GBM images and 315 LGG images are included in our analysis, guaranteeing representation of various tumor grades and histopathological features.
Results: The fusion of textural and color characteristics was validated in the glioma patients using the 10-fold cross-validation technique with an accuracy equals to 95.8%, sensitivity equals to 96.4%, DSC equals to 96.7%, and specificity equals to 97.1%. The combination of the color and texture characteristics produced significantly better accuracy, which supported their synergistic significance in the predictive model. The result indicates that the textural characteristics can be an objective, accurate, and comprehensive glioma prediction when paired with conventional imagery.
Conclusion: The results outperform current approaches for identifying LGG from HGG and provide competitive performance in classifying four categories of glioma in the literature. The proposed model can help stratify patients in clinical studies, choose patient
Renal tumors are one of the common diseases of urology, and precise segmentation of these tumors plays a crucial role in aiding physicians to improve diagnostic accuracy and treatment effectiveness. Nevertheless, inherent challenges associated with renal tumors, such as indistinct boundaries, morphological variations, and uncertainties in size and location, segmenting renal tumors accurately remains a significant challenge in the field of medical image segmentation. With the development of deep learning, substantial achievements have been made in the domain of medical image segmentation. However, existing models lack specificity in extracting features of renal tumors across different network hierarchies, which results in insufficient extraction of renal tumor features and subsequently affects the accuracy of renal tumor segmentation. To address this issue, we propose the Selective Kernel, Vision Transformer, and Coordinate Attention Enhanced U-Net (STC-UNet). This model aims to enhance feature extraction, adapting to the distinctive characteristics of renal tumors across various network levels. Specifically, the Selective Kernel modules are introduced in the shallow layers of the U-Net, where detailed features are more abundant. By selectively employing convolutional kernels of different scales, the model enhances its capability to extract detailed features of renal tumors across multiple scales. Subsequently, in the deeper layers of the network, where feature maps are smaller yet contain rich semantic information, the Vision Transformer modules are integrated in a non-patch manner. These assist the model in capturing long-range contextual information globally. Their non-patch implementation facilitates the capture of fine-grained features, thereby achieving collaborative enhancement of global-local information and ultimately strengthening the model's extraction of semantic features of renal tumors. Finally, in the decoder segment, the Coordinate Attention modules embedding positional information are proposed aiming to enhance the model's feature recovery and tumor region localization capabilities. Our model is validated on the KiTS19 dataset, and experimental results indicate that compared to the baseline model, STC-UNet shows improvements of 1.60%, 2.02%, 2.27%, 1.18%, 1.52%, and 1.35% in IoU, Dice, Accuracy, Precision, Recall, and F1-score, respectively. Furthermore, the experimental results demonstrate that the proposed STC-UNet method surpasses other advanced algorithms in both visual effectiveness and objective evaluation metrics.
Background: It is extremely essential to accurately differentiate pheochromocytoma from Adrenal incidentalomas (AIs) before operation, especially biochemical tests were inconclusive. We aimed to evaluate the value of magnetic resonance imaging (MRI) features to differentiate pheochromocytomas among adrenal tumors, among which the consequences of biochemical screening tests of catecholamines and/or catecholamine metabolites are positive.
Methods: With institutional review board approval, this study retrospectively compared 35 pheochromocytoma (PHEO) patients with 27 non-pheochromocytoma(non-PHEO) patients between January 2022 to September 2023, among which the consequences of biochemical screening tests of catecholamines and/or catecholamine metabolites are positive. T test was used for the independent continuous data and the chi-square test was used for categorical variables. Univariate and multivariate logistic regression were applied to find the independent variate of the features to differentiate PHEO from non-PHEO and ROC analysis was applied to evaluate the diagnostic value of the independent variate.
Results: We found that the T2-weighted (T2W) signal intensity in patients with pheochromocytoma was higher than other adrenal tumors, with greatly significant (p < 0.001). T2W signal intensity ratio (T2W nodule-to-muscle SI ratio) was an independent risk factor for the differential diagnosis of adrenal PHEOs from non-PHEOs. This feature alone had 91.4% sensitivity and 81.5% specificity to rule out pheochromocytoma based on optimal threshold, with an area under the receiver operating characteristics curve (AUC‑ROC) of 0.910(95% C I: 0.833-0.987).
Conclusion: Our study confirms that T2W signal intensity ratio can differentiate PHEO from non-PHEO, among which the consequences of biochemical screening tests of catecholamines and/or catecholamine metabolites are positive.
Polypharmacy involves an individual using many medications at the same time and is a frequent healthcare technique used to treat complex medical disorders. Nevertheless, it also presents substantial risks of negative medication responses and interactions. Identifying and addressing adverse effects caused by polypharmacy is crucial to ensure patient safety and improve healthcare results. This paper introduces a new method using Graph Convolutional Networks (GCN) to identify polypharmacy side effects. Our strategy involves developing a medicine interaction graph in which edges signify drug-drug intuitive predicated on pharmacological properties and hubs symbolize drugs. GCN is a well-suited profound learning procedure for graph-based representations of social information. It can be used to anticipate the probability of medicate unfavorable impacts and to memorize important representations of sedate intuitive. Tests were conducted on a huge dataset of patients' pharmaceutical records commented on with watched medicate unfavorable impacts in arrange to approve our strategy. Execution of the GCN show, which was prepared on a subset of this dataset, was evaluated through a disarray framework. The perplexity network shows the precision with which the show categories occasions. Our discoveries demonstrate empowering advance within the recognizable proof of antagonistic responses related with polypharmaceuticals. For cardiovascular system target drugs, GCN technique achieved an accuracy of 94.12%, precision of 86.56%, F1-Score of 88.56%, AUC of 89.74% and recall of 87.92%. For respiratory system target drugs, GCN technique achieved an accuracy of 93.38%, precision of 85.64%, F1-Score of 89.79%, AUC of 91.85% and recall of 86.35%. And for nervous system target drugs, GCN technique achieved an accuracy of 95.27%, precision of 88.36%, F1-Score of 86.49%, AUC of 88.83% and recall of 84.73%. This research provides a significant contribution to pharmacovigilance by proposing a data-driven method to detect and reduce polypharmacy side effects, thereby increasing patient safety and healthcare decision-making.
Background: This study aims to investigate the role of shear wave elastography (SWE) and connective tissue growth factor (CTGF) in the assessment of papillary thyroid carcinoma (PTC) prognosis.
Methods: CTGF expression was detected with immunohistochemistry. Clinical and pathological data were collected. Parameters of conventional ultrasound combined with SWE were also collected. The relationship among CTGF expression, ultrasound indicators, the elastic modulus and the clinicopathological parameters were analyzed.
Results: Univariate analysis showed that patients with high risk of PTC were characterized with male, Uygur ethnicity, increased expression of CTGF, convex lesions, calcified, incomplete capsule, intranodular blood flow, rear echo attenuation, cervical lymph node metastasis, lesions larger than 1 cm, psammoma bodies, advanced clinical stage, increased TSH and high value in the shear modulus (P < 0.05). Multivariate analysis demonstrated that the risk factors of high expression of CTGF according to contribution size order were irregular shape, aspect ratio ≥ 1, and increased TSH. The logistic regression model equation was Logit (P) = 1.153 + 1.055 × 1 + 0.926 × 2 + 1.190 × 3 and the Area Under Curve value of the logistic regression was calculated to be 0.850, with a 95% confidence interval of 0.817 to 0.883.
Conclusion: SWE and CTGF are of great value in the risk assessment of PTC. The degree of fibrosis of PTC is closely related to the prognosis. The hardness of PTC lesions and the expression level of CTGF are correlated with the main indexes of conventional ultrasound differentiating benign or malignant nodules. Irregular shape, aspect ratio ≥ 1, and increased TSH are independent factors of CTGF.