Multi-Class Diagnosis of Neurodegenerative Diseases Using Effective Deep Learning Models with Modified DenseNet-169 and Enhanced DeepLabV 3+

Abstract

Early detection lowers the death rate and allows for prompt treatment of the exhausted individual with neurodegenerative diseases. Most existing classification studies can either not generate probabilistic predictions or consider uncertainty, or do not reflect medical practice, where patients may have unusual variations, comorbidities, or early stages of the disease. This research proposes a novel method for classifying patients and healthy individuals from other distinctive neurodegenerative diseases that consider ambiguity and spatial information. Based on improved deep learning models, we presented a multi-class neurodegenerative disease classification in this research that accurately conducts multi-class or three-class classifications. First, we use various pre-processing methods to make the data suitable for analysis, such as noise reduction, contrast improvement, and data augmentation. The CapsNet model is then used to extract the images' valuable features. Then, the multi-class classifications of neurodegenerative diseases are classified using the Modified DenseNet-169 model. After classification, the accurate delineation of disease regions is effectively segmented using the Enhanced DeepLabV3+ model. Aided by the PPMI and ADNI datasets, this Multi-class Neurodegenerative Disease Dataset (MNDD) was generated. The outcomes of our experiments illustrate that the proposed model attains an exceptional accuracy of 99.27% on Dataset 1 and 99.14% on Dataset 2, surpassing the performance of several well-known existing deep learning models. Through advanced deep-learning techniques and image segmentation, this research improves early diagnosis and treatment outcomes in neurodegenerative disease classifications.