Diagnosis of Histopathological Images to Distinguish Types of Malignant Lymphomas Using Hybrid Techniques Based on Fusion Features

Malignant lymphoma is one of the types malignant tumors that can lead to death. The diagnostic method for identifying a histopathological analysis tissue images. Because similar morphological characteristics types, it difficult doctors and specialists manually distinguish lymphomas. Therefore, deep automated learning techniques aim solve this problem help clinicians reconsider their decisions. similarity between study aimed extract features using various algorithms models combine them together into feature vectors. Two datasets have been applied, each with two different systems reliable diagnosis lymphoma. first system was hybrid DenseNet-121 ResNet-50 reduce dimensions by principal component (PCA) method, support vector machine (SVM) algorithm classifying low-dimensional features. second based on extracting combining hand-crafted extracted gray level co-occurrence matrix (GLCM), fuzzy color histogram (FCH), discrete wavelet transform (DWT), local binary pattern (LBP) feed-forward neural network (FFNN) classifier. All achieved superior results in diagnosing An FFNN classifier reached an accuracy 99.5%, specificity 100%, sensitivity 99.33%, AUC 99.86% dataset. In contrast, same technique 100% all measures diagnose