Background/Objectives: Parkinson’s disease (PD) is a progressive neurodegenerative disorder in ageing populations, yet early diagnosis before motor symptoms remains critical. Reliable identification of subtle nigral alterations at early stages of the disease on magnetic resonance imaging (MRI) remains challenging. This limitation is mainly attributed to the subjective and low sensitivity of manual image interpretation in early PD. Here, we demonstrate a deep learning-based framework to enhance early PD detection. The study’s novelty is a lightweight deep learning framework that captures spatial, textural, and frequency-domain PD biomarkers without heavy network architectures or manual region delineation. Methods: The model integrates GhostNet with ensemble learning to combine local and global spatial information. This model employs wavelet-based frequency feature extraction rather than downsampling and incorporates an attention module to focus on relevant image regions, particularly changes in the substantia nigra (SN) region. Segmentation is employed solely as an auxiliary intermediate step to localize the SN and guide discriminative feature extraction. The final output is a binary classification that distinguishes PD patients from healthy controls. T2-weighted MRI data from the PPMI database are employed. Results: The proposed model achieved an F1-score of 0.8762, demonstrating robust performance under class imbalance, outperforming state-of-the-art models with only 2.03 million parameters and 4.36 Giga Floating Point Operations (GFLOPs). The architecture uncovered texture and frequency patterns previously inaccessible with conventional CNN pipelines. Model comparisons demonstrated consistent gains across all evaluated metrics (all p < 0.001), establishing robust diagnostic improvement. Conclusions: These findings establish an efficient, high-performing framework for reliable MRI-based PD identification. The approach provides automated early detection and supports clinically scalable, computationally lightweight screening tools.

Todays, facial and vocal emotional expression recognition is considered one of the most important ways of human communication and responding to the ambient and the attractive fields of machine vision. This application can be used in different cases, including emotion analysis. This article uses six basic emotional expressions (anger, disgust, fear, happiness, sadness, and surprise), and its main goal is to present a new method in cognitive science, based on the functioning of the human brain system. The stages of the proposed model include four main parts: pre-processing, feature extraction, feature selection, and classification. In the pre-processing stage, facial images and verbal signals are extracted from videos taken from the enterface’05 dataset, noise removal and resizing is performed on them. In the feature extraction stage, PCA is applied to the images, and the 3D-CNN network is used to find the best features of the images. Moreover, MFCC is applied to emotional verbal signals, and the CNN Network will also be applied to find the best features. Then, fusion is performed on the resulted features and finally Soar classification will be applied to the fused features, to calculate the recognition rate of emotional expression based on face and speech. This model will be compared with competing models in order to examine the performance of the proposed model. The highest rate of recognition based on audio-image was related to the emotional expression of disgust with a rate of 88.1%, and the lowest rate of recognition was related to fear with a rate of 73.8%.

Flatfoot is a common musculoskeletal disorder that, if not detected in its early stages, can lead to impaired posture, reduced mobility, and diminished qua