Fusion image is the method of extracting the relevant information from two or more identical input images into one scene and creating a new image. This method allows the new image to provide comprehensive information about the wand, leading to a visual understanding of the human being. Fusion image application in image processing is an important issue. Applications in many fields such as photography, microscopy, astronomy, medical imaging, satellite imagery, machine vision, biology are monitored. In this study first, an image fusion method, suggested recently based on transform empirical wavelet, was implemented in which coefficients were obtained by processing the input images. Then they were combined by applying the rules. The aim of this study is to investigate the noise effect and to remove the noise in the aforementioned suggested method. First, the noise was added to the images, and the images were decomposed into layers or coefficients. Second, by thresholding the coefficients, the noise was removed. Then the coefficients were combined based on the rules to obtain the final coefficients. In the end, the final coefficients were used to obtain the fused image. The results show that the noise removal of images during image fusion is much better and more effective than denoising before image fusion, and the demonstration of the method is proved by obtaining better results in comparison to some existing methods.

Given that breast cancer is one of the most difficult and dangerous cancers, the use of diagnostic methods in the early stages of its development can be very effective and important in the process of treating patients. This early diagnosis can help doctors treat patients, thus greatly reducing mortality. Many different features have been collected to diagnose and predict breast cancer, and it is very difficult for specialists to use all of these features for a large number of cancers. The aim of this study is to provide a new method for minimizing the process of breast cancer diagnosis through the Grasshopper optimization algorithm. The steps of the proposed method consist of three main parts: The first step after receiving the data is to normalize the pre-processed data. The second step is to reduce the features using the GOA. The final step is to select the optimal features and improve the parameters using the SVM Classifier. The experiments in this study were performed on three datasets, namely WBC (Wisconsin Breast Cancer), WDBC (Wisconsin Diagnosis Breast Cancer) and WPBC (Wisconsin Prognosis Breast Cancer). The results show that the accuracy of the proposed method is 99.51, 98.83 and 91.38 for the WBC, WDBC and WPBC datasets, respectively. In comparison with other methods, the results show that the proposed method has better performance.

Brain diseases are common causes of death and burns such as cancerous tumors. Nowadays, the use of automated computer techniques is quite common for faster extraction and better identification of tumor locations. The present study examines the diagnosis of brain tumors in MRI imaging through a super pixel-based clustering technique. In the proposed method, additional regions of MRI images were removed by pre-processing operations to eliminate noise and skull removal to increase the speed of tumor detection. Then, the super pixels were calculated by dividing the image into even blocks. Spectral clustering was performed on the ROI containing the tumor tissue information. Finally, adjacent blocks were identified by Filter Gabor to identify brain tumors in MRI images. Based on the results, the proposed method has shown better performance in terms of accuracy, sensitivity, and specificity in comparison to other methods. The function of brain tumor diagnosis can be useful in helping physicians identify more rapidly.

Today's, of the major cancers for both females and male is lung cancer. This type of cancer is the most common cause of mortality that accounts for up to 20% of all cancers. The incidence of this cancer has noticeably increased since the beginning of the 19th century. The current study aims to investigate and present a novel method to diagnose lung cancer using Optimization Algorithm (GOA) algorithm and KNN classification. The study method includes three steps. In the first step, pre-processing of lung cancer cell data is used to remove irrelevant and duplicate features. In the second step, the Grasshopper Optimization Algorithm (GOA) method is used to select the high-dimensional feature. In the third step, the selected features are classified into three categories, namely low, medium and high using the KNN nearest neighbor classifier. To evaluate the proposed method, the UCI dataset is used. The results indicate that this method has superior performance with the accuracy of 98.65, specificity of 96.7, and sensitivity of 94.10, demonstrating the superiority of this method over others. The results show that diagnosis of lung cancer using data mining techniques provides the physician with the most detailed and accurate information in the shortest possible time.