Improving the Accuracy of Detecting Cancerous Tumors Based on Deep Learning on MRI Images

The continuous progress of photography technologies as well as the increase in the number of images and their applications requires the emergence of new algorithms with new and different capabilities. Among the various processes on medical images, the segmentation of medical images has a special place and has always been considered and investigated as one of the important issues in the processing of medical images. Based on this, in this research, a solution to diagnose the tumor through the use of a combined method based on watershed algorithm, co-occurrence matrix and neural networks has been presented, so that through the use of this combined solution, the tumor can be detected with high accuracy. Medical images diagnosed. According to the method used in this research, as well as the implementation of the solution in the Python environment and through the use of CV2 and SimpleITK modules, it is possible to set parameters such as accuracy, correctness, recall and Fscore criteria. which are always important parameters that are investigated in researches, improved compared to the past and achieved favorable results. This will increase the improvement of tumor detection in the brain compared to Thersholding and TKMeans methods.