Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198011,
        author = {M.VIJAYA NAGA RAJYA LAKSHMI and K.THARUN SAI and M.CHANDRA SEKHAR and P.POLAIAH and DR.A.VIJAYA LAKSHMI},
        title = {SEGMENTATION-DRIVEN IMAGE REGISTRATION AND IDENTIFICATION OF DEFECTS IN THE KIDNEY USING ANFIS CLASSIFIER},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7295-7299},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198011},
        abstract = {The diagnostic assessment of renal pathologies necessitates high-precision computational frameworks to assist radiologists in identifying and localizing structural abnormalities. This research proposes an integrated methodology for the Segmentation-Driven Image Registration and Identification of Defects in the Kidney, leveraging the adaptive capabilities of an Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed system addresses the inherent challenges of medical imaging, such as low contrast, speckle noise, and anatomical variability, which often hinder accurate diagnosis in conventional modalities like Ultrasound or CT scans.
The framework begins with an advanced pre-processing stage designed to enhance image quality and normalize intensity distributions. Following enhancement, a segmentation-driven registration technique is employed to align temporal or multi-modal kidney images. Unlike traditional intensity-based registration, this approach utilizes segmented anatomical boundaries to ensure that morphological features are preserved during the spatial transformation process, significantly reducing registration errors in deformed renal tissues.
For the identification of defects—such as cysts, stones, or tumors—a hybrid feature extraction process is implemented to capture both textural and statistical attributes of the renal parenchyma. These features serve as inputs to the ANFIS classifier, which combines the learning prowess of neural networks with the linguistic transparency of fuzzy logic. By mimicking human-like reasoning, the ANFIS model effectively handles the uncertainty and imprecision associated with pathological boundaries.
Experimental results demonstrate that the proposed system achieves superior performance compared to traditional classification methods, showing high sensitivity, specificity, and overall accuracy in defect detection. The integration of segmentation-driven registration ensures that even subtle structural changes are detectable, providing a robust tool for early clinical intervention. This research contributes a scalable and reliable automated pipeline for renal health monitoring, potentially reducing the workload of medical professionals and minimizing the margin for human error in diagnostic radiology.},
        keywords = {Kidney Defect Identification, Image Registration, ANFIS Classifier, Medical Image Segmentation, Renal Pathology, Neuro-Fuzzy Systems.},
        month = {April},
        }