In the field of medical sciences, automatic detection of tumor using magnetic resonance (MR) brain images is a major research area. The goal of the proposed work is to identify the tumors in MR images using segmentation methods and to locate the affected regions of the brain more accurately. Medical images have vast information but they are difficult to examine with lesser computational time. An innovative process is proposed to extract tumor cells using the discrete wavelet transform (DWT). After extracting features with DWT feature reduction is carried out with the principal component analysis (PCA). Modified fuzzy C means (MFCM) technique is used for segmenting the tumor cells. The efficiency of the proposed method to identify different abnormalities in real MR images for intracranial neoplasm detection, tuberculoma, and bilateral thalamic fungal granulomas identification is tested. The results obtained are shown in‐terms of Accuracy, Dice Similarity Index (DSI), and Jaccard Index (JI) measures. The performance of the proposed method is tested in terms of performance measures like Accuracy, DSI, and JI. These results are compared with the conventional fuzzy C means (FCM) method.

中文翻译：

---

使用基于 PCA 的改进模糊 C 均值算法对 MR 脑图像进行肿瘤分割

在医学科学领域，使用磁共振（MR）脑图像自动检测肿瘤是一个主要的研究领域。拟议工作的目标是使用分割方法识别 MR 图像中的肿瘤，并更准确地定位大脑的受影响区域。医学图像具有大量信息，但很难以较少的计算时间进行检查。提出了一种使用离散小波变换 (DWT) 提取肿瘤细胞的创新过程。用 DWT 提取特征后，用主成分分析（PCA）进行特征约简。改进的模糊 C 均值 (MFCM) 技术用于分割肿瘤细胞。所提出的方法识别真实 MR 图像中不同异常的效率，用于颅内肿瘤检测、结核瘤、并测试双侧丘脑真菌肉芽肿鉴定。获得的结果以准确度、骰子相似性指数 (DSI) 和 Jaccard 指数 (JI) 措施显示。所提出的方法的性能在诸如准确性、DSI 和 JI 等性能指标方面进行了测试。这些结果与传统的模糊 C 均值 (FCM) 方法进行了比较。