Abstract
According to a recent study, 1 million people died from colon cancer and approximately 2 million from lung cancer. Regardless of the type of cancer, identifying the tumor area is extremely important. The pathology method is the most trustworthy technique for locating the tumor. Nucleus detection and classification studies were performed on images obtained with the pathology method. The principal objective of this study is to ascertain the presence of the tumor and acquire insights into its behavior. There could be some complications while the pathology procedure is performed. On the other hand, it is also important that the samples obtained are examined correctly by experts. Within the scope of the study, the local binary pattern method was used as a highly effective method among image enhancement methods. Colon cancer was diagnosed with two valuable local binary pattern (LBP) methods derived from the local binary pattern (LBP) method. During the diagnosis procedure, the developed LBP methods were first evaluated with machine learning and some transfer learning (TL) methods. Within the scope of the study, the LC25000 dataset was used to analyze colon cancer histopathological images. The performance values for step LBP method analysis were, respectively, accuracy (96.87%), kappa (93.74%), precision (96.9%), recall (96.9%), F1 score (96.9%), and ROC (99.4%). The results obtained with the developed cross-over LBP method were, respectively, accuracy (94.57%), kappa (90.91%), precision (94.9%), recall (94.9%), F1 score (94.9%), and ROC (98.8%).