Enhanced Detection of Kidney Stones using Level Set Segmentation and Kernel-ELM

To optimize treatment and avoid severe kidney stone sickness, early detection of renal calculi and size estimation are of utmost importance. The results of comparing kidney stones using volumetric measurements rather than linear ones are more accurate and dependable. Automatic identification and reduction of labor-intensive manual stone volume estimation could be achieved with the use of deep learning-based systems that employ abdominal non-contrast CT scans. The three primary steps are as follows: preprocessing the photos, training the model, and extracting features from level sets. Restoration, smoothing, sharpening, and contrast enhancement are all steps in getting photos suitable for final goods. Level set segmentation finds widespread application in numerous domains, including object tracking, motion segmentation, and image segmentation. Here, GLCM is utilized for feature extraction. The Kernal-ELM was used for training the model. Compared to Kernal and ELM, the proposed technique achieves a higher average accuracy of 90.73 percent.