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{194679,
        author = {S.V.Rajiga and Dr.M.Gunasekaran},
        title = {CLASSIFICATION OF HYDROCEPHALUS FROM MRI USING SUKUNET ALGORITHM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4967-4976},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194679},
        abstract = {Hydrocephalus is a broad term, which describes a range of pathologies characterized by an excessive build-up of the cerebrospinal fluid (CSF) in the CSF circulatory pathway of the brain. This paper addresses the challenge of accurately segmenting and classifying brain MRI scans for detecting conditions like hydrocephalus. Current methods struggle with noise interference and ineffective region extraction, which hinder performance. Deep Learning is being actively applied in a variety of practical and scientific sectors. Data mining refers to the process of finding patterns in large amounts of data and then using those patterns to generate predictions about fresh data sets or make accurate prediction in the face of uncertainty. In this paper, the research develops a deep learning classification using SukuNetmodel that is designed as a combination of dense neural network (DenseNet), where it initially uses morphological operators to improve the rate of classification. The model first preprocesses the input datasets and then utilizes morphological operators to extract relevant features. The classification results are further validated using fuzzy c-means (FCM) clustering. The proposed model achieves improved classification performance compared to other deep learning models such as Google Net, Alex Net, ResNet, and MobileNetV1. The model's accuracy, precision, recall, F1-measure, and mean absolute percentage error (MAPE) are evaluated, demonstrating its superior performance. The integration of regions beyond the affected areas, such as the ventricles, enhances the model's selectivity without compromising sensitivity to the disease environment.},
        keywords = {Hydrocephalus, DenseNet, Fuzzy C Means, Morphological operator},
        month = {March},
        }