Scoping Review: The Application of Medical Image Processing in the Diagnosis of Kidney Cancer

Background and Aims: Kidney cancer is one of the most common urological malignancies, with early detection significantly improving patient outcomes. Medical image processing has emerged as a powerful tool for enhancing diagnostic accuracy. This scoping review explores the role of medical image processing techniques in the diagnosis of kidney cancer, focusing on their applications, advantages, and limitations. Methods: A scoping review was conducted following the PRISMA-Scar framework. Databases such as PubMed, IEEE Explore, and Science Direct were searched for relevant studies published between ۲۰۱۵ and ۲۰۲۳. Keywords included 'kidney cancer,' 'medical image processing,' 'machine learning,' and 'diagnosis.' Studies were selected based on their relevance to imaging techniques such as CT, MRI, and ultrasound, along with computational methods like deep learning and segmentation. Results: Recent studies highlight the integration of deep learning models with CT imaging for kidney cancer classification. For example, frameworks combining clinical metadata with CT scans have achieved high accuracy rates (۸۵.۶۶%) in tumor classification and surgical procedure prediction. Another approach employed fused deep features from CT images, achieving ۱۰۰% detection accuracy using K-Nearest Neighbor classifiers after pre-processing. Techniques such as threshold filtering and feature fusion have significantly improved diagnostic reliability. Conclusion: Image processing techniques have revolutionized kidney cancer diagnosis by enhancing precision and reducing manual intervention. The integration of artificial intelligence models with radiological data offers promising results, paving the way for personalized treatment strategies. Future research should focus on overcoming data imbalances and improving real-time applications in clinical settings.

کلیدواژه ها:

Kidney Cancer ، Medical Image Processing ، Computed