An intellectual autism spectrum disorder classification framework in healthcare industry using ViT-based adaptive deep learning model

Abstract

Autism Spectrum Disorder (ASD) is a brain disease that mostly affects communication ability, object identification, cognitive capacity, interpersonal skills, and speech comprehension. Its primary origin is genetics, and intervention and diagnosis in an early stage can alleviate the requirement for expensive medical approaches and lengthy tests for ASD patients. Neuroimaging methods can be used to distinguish the composite biomarkers within the ASD based on functional connectivity abnormalities. However, the identification of ASD adopts symptom-based conditions through medical examination. Traditional automated techniques based on extensive aggregated datasets are likely to attain undependable diagnostic classification. Hence, it is essential to establish an efficient ASD classifier system with a deep learning approach to overcome the limitations of the classical models. The innovation of the developed work lies in the implementation of a novel deep learning approach named ViT-ARDNet-LSTM for classifying ASD utilizing MRI images. This framework integrates the merits of ViT, adaptive residual densenets, and LSTM models for efficiently classifying ASD. The developed model rectifies some issues such as the requirement for effective and accurate ASD diagnosis, the problems of conventional models, and the complexities of validating the complex MRI images. Especially, the suggested work resolves the problems of variability in the MRI images, the requirement of robust feature extraction, and the importance of optimizing the model parameters. By offering an effective and novel solution for ASD classification, the suggested work has the potential to improve the diagnosis accuracy, minimize the diagnosis time, and improve patient care. In the developed work, at first, significant MRI images are accumulated from benchmark resources and it is offered as input to the preprocessing stage. In this phase, Contrast Limited Adaptive Histogram Equalization (CLAHE) and bilateral filtering mechanisms are introduced to pre-process the gathered MRI images. Next, the pre-processed images are offered to the ASD classification stage. In this phase, an implemented mechanism named Vision Transformer-based Adaptive Residual Densenet with Long Short Term Memory layer (ViT-ARDNet-LSTM) is utilized to classify the ASD. Moreover, the parameters in ViT-ARDNet-LSTM are optimized using the Modified Zebra Optimization Algorithm (MZOA) for enhancing the functionality of classification. Lastly, the experimental validations are carried out for the developed work. The experimental results displayed that the suggested model attained 94% accuracy, precision, specificity, and sensitivity values when considering the sigmoid activation function. Also, the developed model achieved 5% FPR values. These results elucidate that the designed ASD classification framework outperforms the conventional models and improves timely diagnosis.