Magnetic resonance imaging (MRI) is a real assistant for doctors. It provides rich information about anatomy of human body for precise diagnosis of a diseases or disorder. But it is quite challenging to extract relevant information from low contrast and poor quality MRI images. Poor visual interpretation is a hindrance in correct diagnosis of a disease. This creates a strong need for contrast enhancement of MRI images. Study of existing literature shows that conventional techniques focus on intensity histogram equalization. These techniques face the problems of over enhancement, noise and unwanted artifacts. Moreover, these are incapable to yield the maximum entropy and brightness preservation. Thus ineffective in diagnosis of a defect/disease such as tumor. This motivates the authors to propose the contrast enhancement model namely optimized double threshold weighted constrained histogram equalization. The model is a pipelined approach that incorporates Otsu's double threshold method, particle swarm optimized weighted constrained model, histogram equalization, adaptive gamma correction, and Wiener filtering. This algorithm preserves all essential information recorded in an image by automatically selecting an appropriate value of threshold for image segmentation. The proposed model is effective in detecting tumor from enhanced MRI images.

中文翻译：

---

优化的对比度增强功能可用于肿瘤检测

磁共振成像（MRI）是医生的真正助手。它提供了有关人体解剖结构的丰富信息，可以精确诊断疾病或失调。但是从低对比度和质量差的MRI图像中提取相关信息非常具有挑战性。视觉解释差是正确诊断疾病的障碍。这强烈要求增强MRI图像的对比度。对现有文献的研究表明，常规技术集中于强度直方图均衡化。这些技术面临过度增强，噪声和不想要的伪像的问题。而且，这些不能产生最大的熵和亮度保持。因此对缺陷/疾病例如肿瘤的诊断无效。这激励作者提出对比度增强模型，即优化的双阈值加权约束直方图均衡。该模型是一种流水线方法，结合了Otsu的双阈值方法，粒子群优化的加权约束模型，直方图均衡，自适应伽马校正和Wiener滤波。该算法通过自动选择合适的阈值进行图像分割，从而保留了记录在图像中的所有基本信息。所提出的模型可有效地从增强的MRI图像中检测肿瘤。和维纳过滤。该算法通过自动选择合适的阈值进行图像分割，从而保留了记录在图像中的所有基本信息。所提出的模型可有效地从增强的MRI图像中检测肿瘤。和维纳过滤。该算法通过自动选择合适的阈值进行图像分割，从而保留了记录在图像中的所有基本信息。所提出的模型可有效地从增强的MRI图像中检测肿瘤。