Image Enhancement using linear filters for Rectal Cancer Diagnosis using MR Images

Computer-aided diagnosis (CAD) is an efficient tool in analyzing medical images for the diagnosis and staging of rectal cancer. Magnetic Resonance Imaging (MRI) plays a crucial role in the detection and evaluation of rectal cancer due to its high-resolution imaging capabilities. This paper discusses the pre-processing methods for MR images of rectal cancer, which facilitate further image analysis for diagnosing the stage of cancer. Pre-processing is a critical step for MR images, aiding in subsequent steps of segmentation and classification. This paper investigates the impact of widely used pre-processing techniques. Initially, pelvic DICOM images are provided as input. By combining three filters—mean, median, and adaptive median filters—the noise is removed from the image. Image enhancement techniques such as Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to enhance the quality of the image. Statistical parameters like Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Structural Similarity Index Measure (SSIM) are used to evaluate performance. Results indicate that CLAHE provides superior outcomes.