There are different types of lesions that can be investigated with the hematoxylin–eosin staining protocol. Lymphoma is a type of malignant disease which affects one of the highest white blood cell populations responsible for the immunological defence system. There are lymphoma sub-types that can have similar features, which make their diagnoses a difficult task. In this study, we investigated algorithms based on multiscale and multidimensional fractal geometry with colour models for classification of lymphoma images. Fractal features were extracted from the colour models and separate channels from these models. These features were concatenated to form feature vectors. Finally, we investigated the Hermite polynomial classifier and machine learning algorithms in order to evaluate the performance of the proposed approach. We employed the tenfold cross-validation method and evaluated the lesion sub-types with the binary and multiclass classifications. The separated colour channels obtained from histological images achieved relevant values for the binary and multiclass classifications, with an accuracy rating between 91 and 97%. These results can contribute to the detection and classification of the lesions by supporting specialists in clinical practices.

可使用苏木精-伊红染色方案检查不同类型的病变。淋巴瘤是一种恶性疾病，会影响负责免疫防御系统的最高白细胞群体之一。有些淋巴瘤亚型可能具有相似的特征，这使其诊断很困难。在这项研究中，我们研究了基于多尺度和多维分形几何以及颜色模型的淋巴瘤图像分类算法。从颜色模型中提取了分形特征，并从这些模型中分离了通道。将这些特征连接起来以形成特征向量。最后，我们研究了Hermite多项式分类器和机器学习算法，以评估该方法的性能。我们采用了十倍交叉验证方法，并用二进制和多类分类评估了病变亚型。从组织学图像中获得的分离出的色彩通道达到了二元和多类分类的相关值，准确率介于91％和97％之间。这些结果可通过支持临床实践的专家来促进病变的检测和分类。