Using a ResNet-18 Network to Detect Features of Alzheimer’s Disease on Functional Magnetic Resonance Imaging: A Failed Replication. Comment on Odusami et al. Analysis of Features of Alzheimer’s Disease: Detection of Early Stage from Functional Brain Changes in Magnetic Resonance Images Using a Finetuned ResNet18 Network. Diagnostics 2021, 11, 1071

PCA-WRKNN-assisted label-free SERS serum analysis platform enabling non-invasive diagnosis of Alzheimer's disease

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative brain disorder with significant economic and societal impacts, whereas early AD diagnosis remains a considerable challenge. Here, a robust and convenient surface-enhanced Raman scattering (SERS) analysis platform was fabricated on a microarray chip to dissect the variation in serum composition for AD diagnosis, eliminating the invasive cerebrospinal fluid (CSF)-based and costly instrument-dependent diagnostic methods. AuNOs array prepared by self-assembly at liquid-liquid interface enabled the acquirement of SERS spectra with excellent reproducibility. Moreover, a finite-difference time-domain (FDTD) simulation suggested the significant plasmon hybridization generated by AuNOs aggregation, resulting in high signal-to-noise ratio SERS spectra. We established an AD mice model with Aβ1-40 induction followed by recording the serum SERS spectra at different stages. A multivariate analysis method of principal component analysis (PCA)-weighted representation-based k-nearest neighbor (WRKNN) was applied for the characteristics extraction to improve the classification performance, with an accuracy of over 95 %, an AUC of over 90 %, a sensitivity of over 80 %, and a specificity of over 96.7 %. The results of this study demonstrate the potential of SERS application as a diagnostic screening method, following further validation and optimization, which may open up new exciting opportunities for future biomedical applications.

Endoscopic Image Classification Based on Explainable Deep Learning

Deep learning has achieved remarkably positive results and impacts on medical diagnostics in recent years. Due to its use in several proposals, deep learning has reached sufficient accuracy to implement; however, the algorithms are black boxes that are hard to understand, and model decisions are often made without reason or explanation. To reduce this gap, explainable artificial intelligence (XAI) offers a huge opportunity to receive informed decision support from deep learning models and opens the black box of the method. We conducted an explainable deep learning method based on ResNet152 combined with Grad-CAM for endoscopy image classification. We used an open-source KVASIR dataset that consisted of a total of 8000 wireless capsule images. The heat map of the classification results and an efficient augmentation method achieved a high positive result with 98.28% training and 93.46% validation accuracy in terms of medical image classification.

Integrated Video and Acoustic Emission Data Fusion for Intelligent Decision Making in Material Surface Inspection System

In the field of intelligent surface inspection systems, particular attention is paid to decision making problems, based on data from different sensors. The combination of such data helps to make an intelligent decision. In this research, an approach to intelligent decision making based on a data integration strategy to raise awareness of a controlled object is used. In the following article, this approach is considered in the context of reasonable decisions when detecting defects on the surface of welds that arise after the metal pipe welding processes. The main data types were RGB, RGB-D images, and acoustic emission signals. The fusion of such multimodality data, which mimics the eyes and ears of an experienced person through computer vision and digital signal processing, provides more concrete and meaningful information for intelligent decision making. The main results of this study include an overview of the architecture of the system with a detailed description of its parts, methods for acquiring data from various sensors, pseudocodes for data processing algorithms, and an approach to data fusion meant to improve the efficiency of decision making in detecting defects on the surface of various materials.