Lung cancer is the leading cause of cancer-related deaths worldwide, making early diagnosis from CT images critically important for patient outcomes. In this study, a unique dataset was collected at Inönü University Turgut Özal Medical Center, consisting of 3526 CT slices from 210 patients manually annotated by expert physicians. The lesions, classified into benign, malignant, and cystic categories, were segmented using seven different deep learning architectures: U-Net, VGG16UNet, EFF-UNet, UNet++, FPNet, PSPNet, and EFF-PSPNet. The models were evaluated based on metrics such as Dice, Jaccard, precision, recall, and FPS. The most successful results were achieved by the EFF-UNet (Dice: 92.14%) and U-Net (Dice: 92.25%) models. While cystic lesions were detected with high accuracy, benign lesions presented the lowest results due to their morphological variability. Visual analyses indicated that some models exhibited uncertainty in class differentiation, and the quality of annotations was found to directly influence model performance. This study demonstrates the potential of deep learning-based segmentation for clinical decision support systems and contributes to the field with its original dataset.

Background/Objectives: Lung cancer (LC) is the leading cause of cancer-related mortality worldwide, making early and accurate diagnosis crucial for improving patient outcomes. Although chest computed tomography (CT) enables detailed assessment of lung abnormalities, manual interpretation is time-consuming, requires expert expertise, and is prone to diagnostic variability. To address these challenges, this study proposes DE-SAMNet, a hybrid deep learning framework for automated multi-class LC classification from CT scans. Methods: The model integrates two pre-trained convolutional neural networks—DenseNet121 and EfficientNetB0—operating in parallel to extract complementary multi-scale features. A Spatial Attention Module (SAM) is applied to each feature stream to emphasize clinically important regions. Final classification is performed through a compact fusion mechanism involving global average pooling, batch normalization, and a fully connected layer. DE-SAMNet was evaluated on two datasets: a public dataset (IQ-OTH/NCCD) with benign, malignant, and normal cases, and a private clinical dataset including benign, malignant, cystic, and healthy cases. Results: On the public dataset, the model achieved a 99.00% F1-score, 98.41% recall, 99.64% precision, and 99.54% accuracy. On the private dataset, it obtained 95.96% accuracy, 95.99% precision, 96.04% F1-score, and 96.21% recall, outperforming existing approaches. To enhance reliability, explainable AI (XAI) techniques such as Grad-CAM were used to visualize the model’s decision rationale. The resulting heatmaps effectively highlight lesion-specific regions, offering transparency and supporting clinical interpretability. Conclusions: This explainability strengthens trust in automated predictions and demonstrates the clinical potential of the proposed system. Overall, DE-SAMNet delivers a highly accurate and interpretable solution for early LC detection.

Lung cancer remains one of the leading causes of cancer-related deaths worldwide, and early detection plays a crucial role in improving treatment success and patient survival. In this study, the problem of lesion segmentation in lung computed tomography (CT) images was addressed, and the performance of different U-Net-based deep learning architectures was comparatively evaluated. The dataset used in this study consisted of 22,782 CT slices obtained from 223 patients. Among these images, 3,584 slices contained lesions, while 19,198 slices were healthy images. To investigate the impact of class imbalance in the dataset on model performance, three different experimental scenarios were applied: using only lesion-containing images, using all images together, and using a balanced training dataset. Segmentation performance was analyzed using both image-based and patient-based evaluation approaches. The results indicate that data distribution has a significant impact on segmentation performance. In particular, balancing the training dataset improved the results, especially in patient-based evaluations.

Background/Objectives: Thymoma is a rare epithelial neoplasm originating from the thymus gland, and its accurate detection and classification using computed tomography (CT) images remain diagnostically challenging due to subtle morphological similarities with other mediastinal pathologies. This study presents a deep learning (DL)-based model designed to improve diagnostic accuracy for both thymoma detection and subtype classification (benign vs. malignant). Methods: The proposed approach integrates a pre-trained VGG16 network for efficient feature extraction—capitalizing on its capacity to capture hierarchical spatial features—and an MLP-Mixer-based feature enhancement module, which effectively models both local and global feature dependencies without relying on conventional convolutional mechanisms. Additionally, customized preprocessing and post-processing methods are employed to enhance image quality and suppress redundant data. The model’s performance was evaluated on two classification tasks: distinguishing thymoma from healthy cases and discriminating between benign and malignant thymoma. Comparative analysis was conducted against state-of-the-art DL models including ResNet50, ResNet34, SEResNeXt50, InceptionResNetV2, MobileNetV2, VGG16, InceptionV3, and DenseNet121 using metrics such as F1 score, accuracy, recall, and precision. Results: The model proposed in this study obtained its best performance in thymoma vs. healthy classification, with an accuracy of 97.15% and F1 score of 80.99%. In the benign vs. malignant task, it attained an accuracy of 79.20% and an F1 score of 78.51%, outperforming all baseline methods. Conclusions: The integration of VGG16’s robust spatial feature extraction and the MLP-Mixer’s effective feature mixing demonstrates superior and balanced performance, highlighting the model’s potential for clinical decision support in thymoma diagnosis.

Background: Pleurodesis is a treatment method that aims to create permanent adhesion between the pleural layers to prevent recurrent fluid or air accumulation in the pleural cavity. Talc, one of the most commonly preferred agents in this procedure, is widely used in clinical practice. In this study, a new talc formulation with a modified surface to impart antibacterial and analgesic properties was experimentally evaluated for the first time. The main objective of the study was to comparatively assess the inflammatory and fibrotic responses following standard talc and modified talc applications. Methods: Thirty-six 12-week-old female Wistar albino rats were simply randomly divided into three different groups: control (n = 12), standard talc (n = 12), and modified talc (n = 12). Under anesthesia, 1 mL of physiological saline containing 17 mg of talc was injected intrapleurally into the right hemithorax. The presence of pneumothorax after the procedure was assessed by chest radiography. After a 12-day follow-up period, the animals were euthanized. Bronchoalveolar lavage (BAL) fluid samples, blood samples, and lung and pleural tissue samples were collected for biochemical, histopathological, and immunohistochemical analyses. Results: Modified talc application resulted in a significant increase in both visceral and parietal pleural thickness (p < 0.05). Granulation tissue formation and collagen deposition were significantly higher in the modified talc group. In addition, TGF-β expression and CD68-positive macrophage count increased significantly in the modified talc group (p < 0.05). Inflammatory changes in the lung parenchyma were limited and not statistically significant. Conclusions: The modified talc formulation enriched with lidocaine and antibacterial agents produced a stronger inflammatory and fibrotic response compared to standard talc. These findings indicate that modified talc may increase the effectiveness of pleurodesis. Furthermore, the absence of significant lung parenchymal damage suggests that this treatment is locally effective and feasible. However, further long-term and advanced studies are needed to translate these results into clinical use.