Autism Spectrum Disorder (ASD) encompasses various neurological disorders with symptoms varying by age, development, genetics, and other factors. Core symptoms include decreased pain sensitivity, difficulty sustaining eye contact, incorrect auditory responses, and social engagement issues. Diagnosing ASD poses challenges as signs can appear at early stages of life, leading to delayed diagnoses. Traditional diagnosis relies mainly on clinical observation, which is a subjective and time-consuming approach. However, AI-driven techniques, primarily those within machine learning and deep learning, are becoming increasingly prevalent for the efficient and objective detection and classification of ASD. In this work, we review and discuss the most relevant related literature between January 2016 and May 2024 by focusing on ASD detection or classification using diverse technologies, including magnetic resonance imaging, facial images, questionnaires, electroencephalogram, and eye tracking data. Our analysis encompasses works from major research repositories, including WoS, PubMed, Scopus, and IEEE. We discuss rehabilitation techniques, the structure of public and private datasets, and the challenges of automated ASD detection, classification, and therapy by highlighting emerging trends, gaps, and future research directions. Among the most interesting findings of this review are the relevance of questionnaires and genetics in the early detection of ASD, as well as the prevalence of datasets that are biased toward specific genders, ethnicities, or geographic locations, restricting their applicability. This document serves as a comprehensive resource for researchers, clinicians, and stakeholders, promoting a deeper understanding and advancement of AI applications in the evaluation and management of ASD.

Rising breast cancer incidence and mortality represent significant global challenges for women. Deep learning has demonstrated superior diagnostic performance in breast cancer classification compared to human experts. However, most deep learning methods have relied on unimodal features, potentially limiting the performance of diagnostic models. Additionally, most studies conducted so far have used a single view of digital mammograms, which significantly reduces model performance due to limited overall perspective and generalizability. To address these limitations, we collected a multiview multimodal dataset, including digital mammograms four views two craniocaudal (CC), two mediolateral oblique (MLO) one for each breast, and textual data extracted from radiological reports. We propose a multimodal deep learning architecture for breast cancer classification, utilizing images (digital mammograms) and textual data (radiological reports) from our new in-house dataset. In addition, various augmentation techniques are applied to both imaging and textual data to enhance the training data size. In our investigation, we explored the performance of six state-of-the-art (SOTA) deep learning architectures: VGG16, VGG19, ResNet34, MobileNetV3, EfficientNetB7, and a vision transformer (ViT) as an imaging feature extractors. For textual feature extraction, we employed an artificial neural network (ANN). Afterwards, features were fused using an early fusion and late fusion strategy. The fused imaging and textual features were then inputted into an ANN classifier for breast cancer classification. We evaluated various feature extractors and an ANN classifier combinations, finding that VGG19 in association with ANN achieved the highest accuracy at 0.951. In terms of precision, again VGG19 and ANN combination surpassed other SOTA CNN and attention-based architectures, achieving a score of 0.95. The best sensitivity score of 0.893 was recorded by VGG16+ANN, followed by VGG19+ANN with 0.884. The highest F1 score of 0.922 was achieved by VGG19+ANN. VGG16+ANN achieved the best area under the curve (AUC) score of 0.929, closely followed by VGG19+ANN with a score of 0.915.

Autism Spectrum Disorder is a long-term neurodevelopmental disorder. Early diagnosis is crucial for timely rehabilitation and intervention. Recently, machine learning and deep learning techniques have been widely explored and have produced encouraging results using eye-tracking scanpath images for the early detection of ASD. However, these approaches exhibit inconsistent performance and classification error rates, as well as limited generalization, due to differences in learning approaches and architectural designs across individual models. To address these problems, we employed a weighted-average ensemble of deep learning models using eye-tracking scanpath images. In this work, two different pretrained convolutional neural networks were selected, including Xception and VGG16, based on their proven efficacy and performance. Moreover, we fine-tuned each model individually and evaluated them on a dataset containing eye-tracking scanpath images. We implemented a weighted-average ensemble technique to combine the diverse predictions of the two models. It reduces classification errors and improves the model’s generalization and overall performance. The adopted weighted-average ensemble technique achieved an accuracy of 98.18%, with a perfect recall, and a competitive Area Under the Curve (AUC) of 99.59%. These findings highlight that applying a weighted average to integrate multiple models’ predictions strengthens the generalization and reliability of ASD detection.