Nowadays, brain tumors have become a leading cause of mortality worldwide. The brain cells in the tumor grow abnormally and badly affect the surrounding brain cells. These cells could be either cancerous or non-cancerous types, and their symptoms can vary depending on their location, size, and type. Due to its complex and varying structure, detecting and classifying the brain tumor accurately at the initial stages to avoid maximum death loss is challenging. This research proposes an improved fine-tuned model based on CNN with ResNet50 and U-Net to solve this problem. This model works on the publicly available dataset known as TCGA-LGG and TCIA. The dataset consists of 120 patients. The proposed CNN and fine-tuned ResNet50 model are used to detect and classify the tumor or no-tumor images. Furthermore, the U-Net model is integrated for the segmentation of the tumor regions correctly. The model performance evaluation metrics are accuracy, intersection over union, dice similarity coefficient, and similarity index. The results from fine-tuned ResNet50 model are IoU: 0.91, DSC: 0.95, SI: 0.95. In contrast, U-Net with ResNet50 outperforms all other models and correctly classified and segmented the tumor region.

A brain tumor is a significant health concern that directly or indirectly affects thousands of people worldwide. The early and accurate detection of brain tumors is vital to the successful treatment of brain tumors and the improved quality of life of the patient. There are several imaging techniques used for brain tumor detection. Among these techniques, the most common are MRI and CT scans. To overcome the limitations associated with these traditional techniques, computer-aided analysis of brain images has gained attention in recent years as a promising approach for accurate and reliable brain tumor detection. In this study, we proposed a fine-tuned vision transformer model that uses advanced image processing and deep learning techniques to accurately identify the presence of brain tumors in the input data images. The proposed model FT-ViT involves several stages, including the processing of data, patch processing, concatenation, feature selection and learning, and fine tuning. Upon training the model on the CE-MRI dataset containing 5712 brain tumor images, the model could accurately identify the tumors. The FT-Vit model achieved an accuracy of 98.13%. The proposed method offers high accuracy and can significantly reduce the workload of radiologists, making it a practical approach in medical science. However, further research can be conducted to diagnose more complex and rare types of tumors with more accuracy and reliability.

This paper presents a comprehensive study on the classification of brain tumor images using five pre-trained vision transformer (ViT) models, namely R50-ViT-l16, ViT-l16, ViT-l32, ViT-b16, and ViT-b32, employing a fine-tuning approach. The objective of this study is to advance the state-of-the-art in brain tumor classification by harnessing the power of these advanced models. The dataset utilized for experimentation consists of a total of 4855 images in the training set and 857 images in the testing set, encompassing four distinct tumor classes. The performance evaluation of each model is conducted through an extensive analysis encompassing precision, recall, F1-score, accuracy, and confusion matrix metrics. Among the models assessed, ViT-b32 demonstrates exceptional performance, achieving a high accuracy of 98.24% in accurately classifying brain tumor images. Notably, the obtained results outperform existing methodologies, showcasing the efficacy of the proposed approach. The contributions of this research extend beyond conventional methods, as it not only employs cutting-edge ViT models but also surpasses the performance of existing approaches for brain tumor image classification. This study not only demonstrates the potential of ViT models in medical image analysis but also provides a benchmark for future research in the field of brain tumor classification.

Accurate classification of brain tumors is essential for effective medical diagnosis and treatment planning. Traditional approaches rely on convolutional neural networks (CNNs) for tumor detection, but they often suffer from high computational demands due to the large number of parameters. In this paper, we propose a novel approach for brain tumor classification using involutional neural networks (InvNets), which are designed to mitigate the parameter-intensive nature of CNNs. Unlike the spatial-agnostic and channel-specific convolution kernel, the involution kernel is location-specific and channel-agnostic. This location-specific operation allows the network to adapt to various visual patterns with respect to different spatial locations, enhancing its ability to capture intricate features within the medical images. Our study focuses on a four-class brain tumor classification problem, aiming to differentiate between different tumor types based on medical imaging data. In a comparative analysis, we demonstrate that conventional CNNs require over 4 million parameters, whereas our proposed InvNets require less than 0.2 million parameters, making them more efficient and resource-friendly. The evaluation of both CNNs and InvNets is carried out using standard performance matrices: accuracy, precision, recall, F1 score, and AUC-ROC values. Our findings reveal that the InvNets consistently outperform traditional CNNs. The InvNet architecture achieves an impressive 92% accuracy rate, showcasing its potential for accurate brain tumor classification. This improved accuracy, combined with the reduced parameter count, highlights the effectiveness of InvNets for medical image analysis tasks, especially in scenarios with limited computational resources.

Breast cancer is a global health concern where early and accurate diagnosis is crucial. Mammogram scans provide detailed imaging but require expert interpretation, which is time-consuming. While deep learning shows promise in medical image analysis, the prevalence of imbalanced datasets in medical diagnosis hinders the development of accurate and reliable classification models. We propose a novel deep-learning framework for breast cancer classification from Mammogram scans. The framework addresses imbalanced data through a unique two-module pipeline incorporating the Synthetic Minority Over-sampling Technique (SMOTE). One module employs SMOTE on the entire dataset to balance class distribution. At the same time, the second separates a portion (20%) of the original imbalanced data for evaluation and applies SMOTE to the remaining 80%. The framework incorporates a blockwise Convolutional Neural Network (CNN), utilizing VGG16 preprocessing for input standardization and ResNet50 for feature extraction. A fully conntected classification model, consisting of multiple dense layers with batch normalization and dropout for regularization, was developed to assess the extracted features. The model architecture was iteratively refined to combat overfitting, with the final version incorporating three dense layers (128, 256, and 128 neurons) with dropout rates of 0.5. Our model achieved 99% accuracy on a balanced dataset and 90% on an imbalanced portion. The framework includes an interpretable visualization technique for randomly selected predictions across all classes. Our approach significantly improves diagnostic accuracy in breast cancer classification from Mammogram scans, effectively addressing the challenge of imbalanced data in medical image analysis. This work contributes to medical image analysis and computer-aided diagnosis. The proposed techniques for handling imbalanced data and providing interpretable results can be extended to improve diagnostic accuracy across various medical conditions.

The success rate of extracorporeal shock wave lithotripsy (ESWL) is influenced by various factors, including stone density, and is determined through computed tomography scans in terms of Hounsfield units (HU). Materials and Methods: This retrospective single-center study was conducted in the King Fahad Hospital. Sixty-seven adult patients with renal and ureteric stones were selected randomly and enrolled in the study. Their ages ranged from 20 to 69 years. The patients were examined with non-contrast enhancement (NCCT) to assess the HU of their stones and were consequently treated with ESWL. Results: Of the 67 patients, 37.3% had stones that were completely fragmented, while 62.7% had stones that were partially fragmented. The HU, location of the stone, multiplicity of the stone, and patient age were found to be significant factors contributing to stone fragility (p-values < 0.05). The HU data were found to have a positive significant linear correlation with serum calcium (r = 0.28, p-value = 0.036), while serum acid had a negative correlation (r = −0.55, p-value < 0.001). Thus, the probability of calcium-containing stone formation increases with increased HU. In contrast, uric acid stone formation likely develops with decreasing HU with serum uric acid. Renal stones in patients with diabetes mellitus and hypertension were not completely fragmented compared to those without clinical history. Conclusions: Mean HU, location of the stone, laterality, stone status, and the number of ESWL sessions are the most significant factors affecting stone fragility. CT attenuation values can predict the composition of stones from serum calcium and uric acid examinations. Hypertension and diabetes mellitus are risk factors for renal stone fragmentation.