Citra medis adalah suatu pola atau gambar dua dimensi bagian dalam tubuh manusia yang digunakan oleh ahli kesehatan untuk mendeteksi dan menganalisa penyakit pasien. Pada bidang radiologi citra yang sering digunakan saat ini adalah  citra Magnetic resonance Imaging (MRI). Keunggulan citra MRI adalah kemampuan menampilkan detail anatomi secara jelas dalam berbagai potongan (multiplanar) tanpa mengubah posisi pasien.  Citra MRI ini akan digunakan oleh dokter ataupun peneliti untuk melakukan analisis ada tidaknya suatu tumor, kanker, atau kelainan pada pasien. Penelitian ini mengusulkan metode Contrast Stretching, Histogram Equalization dan Adaptive Histogram Equalization untuk meningkatkan kualitas citra medis. Batasan masalah penelitian ini adalah citra medis MRI yang digunakan sebagai obyek penelitian adalah citra medis MRI Otak baik yang normal atau yang mengalami lesi (gangguan). Dari hasil kualitas citra dan analisa kuantitatif menunjukkan bahwa metode contrast stretching menghasilkan hasil kualitas citra MRI jauh lebih baik dibandingkan dengan metosde histogram equalization, dan adaptive histogram equalization. Nilai MSE yang paling rendah adalah pada metode contrast stretching yaitu 0,00346. Sedangkan nilai MSE yang paling besar dihasilkan oleh metode histogram equalization. Kualitas citra dengan metode contrast stretching menghasilkan nilai PSNR yang paling besar yaitu 22,0677. Ini menandakan bahwa kualitas citra dari metode contrast stretching jauh lebih baik dibandingkan metode histogram equalization, dan adaptive histogram equalization.

This research has an objective to implement histogram equalization technique in the evaluation of characteristics medical images, especially for statistical characterization of medical images. Implementation starting with the pre-processing of the image by converting RGB medical images into grayscale images, followed by determination of the Region of Interest (ROI) and cropping methods. The next process was to increase the quality of medical images by implementing histogram equalization technique. The medical image characteristic was evaluated using characteristic statistical methods with their parameters are mean value, standard deviation, entropy, skewness, and kurtosis. The Medical image was used in this research is a medical image of advanced breast cancer. This research compared the characteristics statistical characterization of medical images obtained with the original medical image which has enhanced use histogram equalization technique. The results of implementation histogram equalization obtain medical image feature extraction results for the value of mean, entropy, skewness, and kurtosis become smaller and standard deviation value was increase.

<p><em style="text-align: justify; text-indent: 14.2pt;"><span style="font-family: 'Times New Roman',serif; mso-ansi-language: EN;" lang="EN">In pattern recognition, image processing plays a role in automatically separating objects from the background. In addition, the object will be processed by the pattern classifier. In the medical world, image processing plays a very important role. CT Scan (Computed Tomography) or CAT Scan (Computed Axial Tomography) is an example of an image processing application that can be used to view fragments or cross sections of parts of the human body. Tomography is the process of producing two-dimensional images from three-dimensional film through several one-dimensional scans. Magnetic resonance imaging (MRI) is the image most often used in the field of radiology. MRI images can display the anatomical details of objects clearly in multiple sections (multiplanar) without changing the patient's position. In this study, two methods were compared, namely K-Means and Fuzzy C Means, in a segmentation process with the aim of separating between normal areas or areas with disturbances (lesions). The images used are brain and chest MRI images with a total of 10 MRI images. The image quality of the segmentation results is compared with the quality test using the Variation of Information (VOI) parameters, Global Consistency Error (GCE), MSE (Mean Square Error), PSNR (Peak Signal to Noise Ratio) and segmentation time.</span></em></p><pre style="text-align: justify; text-indent: 14.2pt;"><em><span style="font-family: 'Times New Roman',serif; mso-ansi-language: EN;" lang="EN">In pattern recognition, image processing plays a role in automatically separating objects from the background. In addition, the object will be processed by the pattern classifier. In the medical world, image processing plays a very important role. CT Scan (Computed Tomography) or CAT Scan (Computed Axial Tomography) is an example of an image processing application that can be used to view fragments or cross sections of parts of the human body. Tomography is the process of producing two-dimensional images from three-dimensional film through several one-dimensional scans. Magnetic resonance imaging (MRI) is the image most often used in the field of radiology. MRI images can display the anatomical details of objects clearly in multiple sections (multiplanar) without changing the patient's position. In this study, two methods were compared, namely K-Means and Fuzzy C Means, in a segmentation process with the aim of separating between normal areas or areas with disturbances (lesions). The images used are brain and chest MRI images with a total of 10 MRI images. The image quality of the segmentation results is compared with the quality test using the Variation of Information (VOI) parameters, Global Consistency Error (GCE), MSE (Mean Square Error), PSNR (Peak Signal to Noise Ratio) and segmentation time.</span></em></pre>

MRI medical image processing require large amounts of memory. Due to limited bandwidth and storage capacity, the image must be compressed prior to transmission and stored. This paper has the objective to implement the algorithm k means the MRI medical image compression. Implementation begins with the Pre post. At this stage, L-dimensional vector of the image will be made. L is the block - a measure used for clustering technique, but is set back in the form of an array. Then the process of clustering. At this stage, every pixel of the image is represented by the centroid of the cluster. And the last stage is the Main Compression, the pixels that do not contain important information will be removed. The study compared the quality of the original image and compressed image. Based on manual observation, there is no significant difference in quality between the original image and the compressed one.