H-Detect: an Algorithm for Early Detection of Hydrocephalus

Abstract

Hydrocephalus is a central nervous system disorder which most commonly affects infants and toddlers. It starts as an abnormal build-up of cerebrospinal fluid in the ventricular system of the brain. Hence, early diagnosis becomes vital, which may be performed by Computed Tomography (CT), one of the most effective diagnostic methods for diagnosing Hydrocephalus (CT), where the enlarged ventricular system becomes apparent. However, most disease progression assessments rely on the radiologist's evaluation and physical measures, which are subjective, time-consuming, and inaccurate. This paper develops an automatic prediction utilizing the H-detect framework for enhanced accurate hydrocephalus prediction. This paper uses a pre-processing step to normalize the input image and remove unwanted noises, which can help extract valuable features easily. The feature extraction is done by segmenting the image based on edge detection using triangular fuzzy rules. Thereby, the exact information on the nature of CSF inside the brain is highlighted. These segmented images are saved and again given to the CatBoost algorithm. The Categorical feature processing allows for quicker training. When necessary, the overfitting detector will stop model training and thus efficiently predicts Hydrocephalus. The outcomes demonstrate that the new H-detect strategy outperforms the traditional approaches.