
Purpose: This study aims to optimize neural networks for diagnosing and predicting lung cancer stages, leveraging advanced recurrent neural network architectures such as Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) networks. Materials and Methods: The research utilizes a comprehensive dataset of clinical data and high-resolution imaging to develop novel Deep Neural Networks (DNNs). These networks are optimized using sophisticated algorithms like Stochastic Gradient Descent with Momentum (SGDM) and Adaptive Moment Estimation (Adam). Transfer Learning (TL) techniques and big data analytics are integrated to enhance model precision and reliability. Additionally, early stopping is employed to prevent overfitting, k-fold cross-validation (k=5) is used to ensure robust model evaluation, and L2 regularization is applied to improve generalization by penalizing large weights. Results: The optimized GRU and LSTM networks demonstrate superior performance in detecting lung cancer stages, significantly improving diagnostic accuracy and prognostic predictions. The models effectively handle long-term dependencies and mitigate the vanishing gradient problem, common in simple RNNs. Using k-fold cross-validation (k=5), the optimized GRU network with SGDM achieved the following metrics in Fold 3: Test Loss of 0.0531, Test Accuracy of 0.97, Sensitivity (Recall) of 0.97, Precision of 0.98, and an F1 Score of 0.975. Conclusion: The study's findings underscore the potential of integrating advanced neural network models into clinical practice, revolutionizing AI-driven medical diagnostics and elevating the standard of patient care.
Purpose: This study aims to explore the effect of mean dose constraint in optimization shells on the reduction of normal lung dose in lung Stereotactic Body Radiation Therapy (SBRT) plans. Materials and Methods: This study investigated 28 VMAT-based lung SBRT plans optimized with three artificial shells, which were re-generated with the same setup and an additional mean dose constraint besides the maximum dose limit. Dosimetric measurements of target volume and Organs At Risk (OARs) were compared between the original plans and re-generated ones using the Wilcoxon signed-rank test at 5% level significance (two-tailed). Results: Replanning resulted in slight improvements in some parameters, such as R50% and the Gradient Measure (GM), which were reduced by 1.3% and 1.0%, respectively, with p < 0.05. However, there were slight increases in other parameters, such as D2cm and the maximum target dose, though these increases were not statistically significant. The Conformity Index (CI) remained nearly identical, with a mean value of 0.99 ± 0.03 for both original and re-optimized plans. Similarly, the V105% values were consistent, with mean values of 0.02 ± 0.13% in both groups. The parameters for dose deposited in normal lung tissue showed statistically significant reductions ranging from 1.0% to 1.7%. In addition, the mean dose to the spinal cord, esophagus, and skin was slightly reduced, but the mean dose to the heart showed a slight increase. Conclusion: The study found that adding mean dose constraints to optimization shells in lung SBRT plans can reduce normal lung dose while maintaining dose conformity to the target. However, there may be slight changes in some OARs such as the spinal cord, esophagus, and skin. These changes were not statistically significant.
Purpose: The objective of this study is to develop a hybrid model combining K-Nearest Neighbor (K-NN) and Bidirectional Convolutional Long Short-Term Memory (BiConvLSTM) for effective detection of lung cancer nodules in chest CT images. Materials and Methods: A dataset of 200 high-resolution CT images (100 nodular, 100 healthy controls) was utilized. Preprocessing steps, including wavelet-based noise reduction and GAN-enhanced contrast refinement, ensured standardized image quality. Spatial features were initially extracted using K-NN, optimized across multiple values of k. Temporal dependencies were processed through BiConvLSTM, supported by residual pathways to preserve information integrity. Evaluation metrics and advanced optimizers (Adam, Nadam, and AdamW) were compared to assess performance. Results: The hybrid model achieved peak accuracy (97.2% ± 1.1) with k = 7, while k-fold cross-validation with k = 5 maintained strong performance. AdamW optimizer outperformed others in generalization metrics and Dice similarity (0.93), while Nadam demonstrated faster convergence, reducing training epochs by 20%. Metrics such as AUROC (0.98) and the Jaccard index confirmed the robustness of the model compared to conventional architectures like U-Net. Additionally, the statistical significance of the proposed model was validated with a P-value of 1.2E-5. Conclusion: This proposed hybrid AI model addresses challenges in nodular identification and provides a scalable, reliable solution for lung cancer detection in clinical imaging workflows.
Purpose: This review aims to synthesize current literature on recent advances in the diagnosis and treatment of Brain and Spinal Cord Injuries (SCIs), focusing on molecular imaging, cell therapy, Brain-Computer Interfaces (BCIs), and Craniosacral Therapy (CST). Materials and Methods: A systematic search was done in PubMed/MEDLINE, Scopus, WoS, Cochrane Library, and Google Scholar to identify relevant articles published between 2015 and 2025. Keywords included "Brain Injury," "Spinal Cord Injury," "Molecular Imaging," "Cell Therapy," "Brain-Computer Interface," and "Craniosacral Therapy". Results: Molecular imaging techniques, such as functional Magnetic Resonance Imaging (fMRI), Diffusion Tensor Imaging (DTI), and Positron Emission Tomography (PET), enhance diagnostic accuracy by visualizing neural activity and structural integrity. Cell therapy, particularly with Mesenchymal Stem Cells (MSCs), promotes axon regeneration and reduces inflammation. BCIs offer the potential for restoring motor function and enhancing neural plasticity. The evidence for CST is mixed, with some studies suggesting benefits in pain relief and cognitive improvement, while others raise concerns about methodological limitations. Conclusion: Recent advances in molecular imaging, cell therapy, and BCIs offer hopeful avenues for improving the diagnosis and treatment of BSCI. However, further rigorous research is needed to validate the ability of these approaches and to address ethical considerations. While CST has gained attention as a complementary therapy, more high-quality studies are required to determine its effectiveness. This review highlights the need for interdisciplinary collaboration to translate scientific discoveries into clinical practice and to develop the quality of life for those affected by BSCI.
Purpose: Laryngeal cancer is a critical health issue, often treated using advanced radiation therapy techniques such as Intensity-Modulated Radiation Therapy (IMRT). The gamma index is a widely used metric for quality assurance in radiotherapy, assessing the agreement between planned and delivered dose distributions. This study aims to evaluate the feasibility and accuracy of laryngeal IMRT treatment plans using three gamma analysis algorithms and varying evaluation parameters, including Dose Difference (DD%), and Distance-To-Agreement (DTA). Materials and Methods: IMRT treatment plans for laryngeal cancer were generated using the Prowess Panther V5.5 Treatment Planning System (TPS). Patient-Specific Quality Assurance (PSQA) was conducted using EBT3 Gafchromic films scanned at 350 dpi and analyzed with RIT Complete 6.11 software. Dose distributions were evaluated using three gamma analysis algorithms under 3%/3 mm criteria and low-dose thresholds of 15%. Calibration of the films was performed to ensure accurate dose measurements. Results: Gamma Passing Rates (GPR) for the laryngeal IMRT plans demonstrated high accuracy, with over 90% of pixels passing the criteria in most cases. Composite gamma analysis showed 53.89% of pixels meeting both DD and DTA criteria simultaneously, while individual evaluation revealed the impact of stricter thresholds on GPR. Subtraction analysis identified dose discrepancies, emphasizing the need for accurate calibration. Conclusion: This study highlights the effectiveness of gamma analysis in ensuring the accuracy of IMRT treatment plans for laryngeal cancer. The findings underscore the importance of rigorous PSQA, parameter optimization, and advanced algorithms to enhance treatment precision.