Classification of brain tumors based on the brain magnetic resonance imaging (MRI) results of patients has become an important problem in medical image processing. A computer program that can efficiently analyze brain MRI images of patients in real time and generate accurate classification results of the tumors in these images can significantly reduce the amount of time needed for diagnosis, which may increase the chances for patients to survive. This paper proposes a new statistical method that can accurately classify three types of brain tumors based on MRI images, the three types of tumors considered include pituitary tumor, glioma, and meningioma. The features for a pixel in an MRI image are obtained by applying a set of convolutional operators to the neighborhood area of the pixel. For training, a hidden Markov model (HMM) is constructed and trained from a training dataset by computing a statistical profile for the feature vectors for pixels in the tumor regions of each type of brain tumors. In addition, a statistical profile is also obtained for pixels that are in the background of a tumor. For classification, the trained HMM is used to assign labels to pixels in an MRI image with a dynamic programming approach and the classification result of the image is obtained from the labels assigned to the tumor region. Both the training and classification processes can be efficiently performed in linear time and does not require the availability of a large amount of computational resources. Experimental results on a large dataset of MRI images show that the proposed method can provide classification results with high accuracy for all three types of brain tumors. A comparison with state-of-the-art methods for brain tumor classification suggests that the proposed method can achieve improved classification accuracy. In addition, real-time analysis also reveals that the proposed approach can probably be used for real-time classification of brain tumors.

基于患者的脑磁共振成像（MRI）结果对脑肿瘤进行分类已经成为医学图像处理中的重要问题。可以实时有效地分析患者的脑部MRI图像并在这些图像中生成肿瘤的准确分类结果的计算机程序可以显着减少诊断所需的时间，这可能会增加患者生存的机会。本文提出了一种新的统计方法，该方法可以基于MRI图像准确地对三种类型的脑肿瘤进行分类，所考虑的三种肿瘤包括垂体瘤，神经胶质瘤和脑膜瘤。MRI图像中像素的特征是通过将一组卷积运算符应用于像素的邻域来获得的。为了训练，通过计算每种脑肿瘤类型的肿瘤区域中像素的特征向量的统计轮廓，从训练数据集中构造和训练隐藏的马尔可夫模型（HMM）。此外，还获得了位于肿瘤背景中的像素的统计轮廓。为了进行分类，使用训练有素的HMM通过动态编程方法将标签分配给MRI图像中的像素，然后从分配给肿瘤区域的标签中获得图像的分类结果。训练和分类过程都可以在线性时间内有效地执行，并且不需要大量计算资源的可用性。在大型MRI图像数据集上的实验结果表明，该方法可以为所有三种类型的脑肿瘤提供高精度的分类结果。与最新技术进行脑肿瘤分类的比较表明，该方法可以提高分类精度。此外，实时分析还表明，所提出的方法可能可以用于脑肿瘤的实时分类。