Dr. Sivanthi Aditanar College of Engineering

This review examines the critical role of neuroimaging technologies, including Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and Single Photon Emission Computed Tomography (SPECT), in advancing central nervous system (CNS) drug development and translational medicine. The focus is on their applications in understanding disease mechanisms, identifying biomarkers, and supporting therapeutic interventions for major CNS disorders, including Parkinson’s disease, Alzheimer’s disease, depression, and schizophrenia. The review synthesizes recent findings from peer-reviewed literature, clinical trials, and preclinical studies to highlight advancements in neuroimaging technologies and their integration into translational medicine frameworks. Trends in imaging usage, challenges in biomarker validation, and future directions, including technological innovations and artificial intelligence (AI) integration, were analyzed to provide a comprehensive overview of the field. Neuroimaging has proven invaluable in CNS drug development by enabling early diagnosis, patient stratification, and therapeutic monitoring. PET imaging has advanced molecular targeting, particularly with amyloid and tau tracers for Alzheimer’s disease, while MRI has provided insights into structural and functional brain changes across disorders. Despite these advancements, challenges such as the lack of validated biomarkers, high costs, and regulatory hurdles limit the full potential of neuroimaging. Emerging innovations, including ultra-high-field MRI, advanced tracers, multimodal imaging, and AI-driven analysis, show promise for overcoming these barriers and advancing precision medicine. Neuroimaging exemplifies the principles of translational medicine, bridging preclinical discoveries with clinical applications. Its role in CNS drug development is transformative, providing tools for more efficient and targeted therapeutic strategies. As neuroimaging technologies continue to evolve, they will further enhance our ability to address the complexities of CNS disorders and improve patient outcomes. Neuroimaging technologies like MRI, PET, and SPECT are revolutionizing how we study and treat brain disorders such as Alzheimer’s, Parkinson’s, and depression. These tools help scientists understand disease processes, find biomarkers, and monitor how well treatments work. While challenges like high costs and limited biomarkers remain, new technologies and artificial intelligence are making imaging more powerful and accessible. This review highlights how neuroimaging is shaping the future of personalized medicine and paving the way for better treatments for brain disorders.

Hybridization of natural fiber composite is on the rise to improve the performance of the materials by the synergistic effect of multiple fibres. The wear resistance of hybrid composite has greatly been enhanced by the addition of filler materials. This paper will look at the mechanical and wear properties of a special hybrid composite reinforced with 6 wt. percent of Peepal Fiber (PF), and different weight percentages of Okra Fiber (OF) and Madar Fiber (MF). The artificial specimens were evaluated with mechanical characterizations such as hardness, impact resistance, flexural strength, interlaminar shear strength, and tensile strength. As a filler material to improve the tribological performance, different weight percentages (2, 4, 6 and 8 wt. %) of Titanium Dioxide (TiO2) nano powder were added. The mechanical properties of the filler-free composite samples that were composed of 15 wt. % Okra and 15 wt. % Madar fibers were better compared to those of the other samples. Furthermore, out of all the configurations studied, the sample with 6 wt. % TiO2 filler showed the lowest wear rate, which is a significant increase in the wear resistance. This paper highlights the potential of TiO2 reinforced hybrid natural fiber composite in sophisticated structural and abrasive applications.

In recent years Quantum computers have been widely used for image manipulation. Similarly, NLP helps understand text and spoken language as humans do. The application of quantum computing to Natural Language Processing has yielded a new field of research, which is known as quantum natural language processing. This paper focuses on listing all the NLP approaches and categorize them based on theoretical work and those implemented on classical or quantum hardware; and also based on task, i.e., general purpose syntax-semantic representation or specific NLP tasks, like sentiment analysis or question answering,and finally by the resources used in the evaluation phase, i.e., whether a benchmark dataset or a custom one has been used.

Background Knee osteoarthritis (OA) is a degenerative, progressive joint disease with narrowing of the joint space, formation of osteophytes, and sclerosis of the subchondral regions, which results in disability and loss of mobility and quality of life. Radiographic images are critical in the assessment of OA severity to enable early diagnosis and treatment planning. Nevertheless, the traditional assessment of the Kellgren-Lawrence (KL) grading system is not objective and may have inter-observer reliability. Objective Current automated techniques cannot consistently predict the localization of the knee joint and have a low capability of representing features, which may impact classification. To address these constraints, this work proposes a state-of-the-art convolutional neural network (CNN)-based model to train automated knee OA severity classification based on radiographs. Work Design & Methods The proposed solution combines accurate localization of the knee joints and deep feature learning to improve the accuracy of classification. A YOLOv2-based model was first used to automatically locate and extract the knee joint region to guarantee accurate localization of the region of interest. A CNN consisting of AlexNet was then employed to extract and classify the features into KL grades (0-4). Results Training and evaluation were conducted using 3,000 knee radiographic images, resulting in performance metrics of 85% accuracy, 84% precision, and 83% recall. Conclusions The suggested approach enhances the reliability and consistency of OA severity measurements, indicating its potential role in facilitating clinical decision-making and early diagnosis.

Manual inspection of fish quality is often subjective, time-consuming, and prone to inconsistency. This work proposes an intelligent fish quality analysis system leveraging computer vision and deep learning to enable automated, accurate, and reproducible evaluation. A U-Net semantic segmentation network is employed to isolate key anatomical regions of fish, including fins, trunk, eye, and jaw, allowing the extraction of biologically relevant features such as flexibility, rigidity, brightness, and morphological dimensions. These features are then analyzed using a K-Nearest Neighbor (KNN) classifier to categorize fish as Fresh or Infected, while damage severity is quantified using region-specific metrics. By combining deep learning-based segmentation with featurebased classification, the proposed framework provides a reliable, interpretable, and scalable solution for automated fish quality monitoring. The findings reveal a strong correlation between damage indicators and infection status, validating the effectiveness of the proposed assessment methodology. This approach provides a reliable and practical solution for fish quality evaluation and has potential applications in automated inspection systems, quality control processes, and food safety monitoring.