Convolutional neural networks for vision neuroscience: significance, developments, and outstanding issues

Visual cortical networks for "What" and "Where" to the human hippocampus revealed with dynamical graphs

Key questions for understanding hippocampal function in memory and navigation in humans are the type and source of visual information that reaches the human hippocampus. We measured bidirectional pairwise effective connectivity with functional magnetic resonance imaging between 360 cortical regions while 956 Human Connectome Project participants viewed scenes, faces, tools, or body parts. We developed a method using deterministic dynamical graphs to define whole cortical networks and the flow in both directions between their cortical regions over timesteps after signal is applied to V1. We revealed that a ventromedial cortical visual "Where" network from V1 via the retrosplenial and medial parahippocampal scene areas reaches the hippocampus when scenes are viewed. A ventrolateral "What" visual cortical network reaches the hippocampus from V1 via V2-V4, the fusiform face cortex, and lateral parahippocampal region TF when faces/objects are viewed. There are major implications for understanding the computations of the human vs rodent hippocampus in memory and navigation: primates with their fovea and highly developed cortical visual processing networks process information about the location of faces, objects, and landmarks in viewed scenes, whereas in rodents the representations in the hippocampal system are mainly about the place where the individual is located and self-motion between places.

Prediction of barberry witches' broom rust disease using artificial intelligence models: a case study in South Khorasan, Iran

The South Khorasan Province in Iran is the main producer of seedless barberry, accounting for 98% of the country's production. This has led to significant economic growth in the region. However, the cultivation of barberry is threatened by the rust fungus Puccinia arrhenatheri, which causes witches' brooms on Berberis vulgaris L. var. asperma. Our research aims to detect infected leaves containing this fungal pathogen using deep learning (DL)-based artificial intelligence (AI) techniques on an available dataset. We captured healthy and infected barberry foliage images and used conventional laboratory methods to label them. We developed a convolutional neural network (CNN) deep learning model using TensorFlow's Keras API to detect and classify barberry broom rust disease. A cross-validation technique is used to check the robustness of the proposed model. The results imply that the proposed model successfully distinguished between healthy specimens and those affected by broom rust disease. The model achieved an impressive accuracy rate of 98% in automatically identifying the disease type and its severity. This interdisciplinary research demonstrates the practical application of AI in agriculture, providing timely intervention strategies to protect crop yields and maintain economic viability in the face of plant diseases.

Predicting PD-L1 status in NSCLC patients using deep learning radiomics based on CT images

Radiomics refers to the utilization of automated or semi-automated techniques to extract and analyze numerous quantitative features from medical images, such as computerized tomography (CT) or magnetic resonance imaging (MRI) scans. This study aims to develop a deep learning radiomics (DLR)-based approach for predicting programmed death-ligand 1 (PD-L1) expression in patients with non-small cell lung cancer (NSCLC). Data from 352 NSCLC patients with known PD-L1 expression were collected, of which 48.29% (170/352) were tested positive for PD-L1 expression. Tumor regions of interest (ROI) were semi-automatically segmented based on CT images, and DL features were extracted using Residual Network 50. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature selection and dimensionality reduction. Seven algorithms were used to build models, and the most optimal ones were identified. A combined model integrating DLR with clinical data was also developed. The predictive performance of each model was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve analysis. The DLR model, based on CT images, demonstrated an AUC of 0.85 (95% confidence interval (CI), 0.82-0.88), sensitivity of 0.80 (0.74-0.85), and specificity of 0.73 (0.70-0.77) for predicting PD-L1 status. The integrated model exhibited superior performance, with an AUC of 0.91 (0.87-0.95), sensitivity of 0.85 (0.82-0.89), and specificity of 0.75 (0.72-0.80). Our findings indicate that the DLR model holds promise as a valuable tool for predicting the PD-L1 status in patients with NSCLC, which can greatly assist in clinical decision-making and the selection of personalized treatment strategies.

Visual search and real-image similarity: An empirical assessment through the lens of deep learning

The ability to predict how efficiently a person finds an object in the environment is a crucial goal of attention research. Central to this issue are the similarity principles initially proposed by Duncan and Humphreys, which outline how the similarity between target and distractor objects (TD) and between distractor objects themselves (DD) affect search efficiency. However, the search principles lack direct quantitative support from an ecological perspective, being a summary approximation of a wide range of lab-based results poorly generalisable to real-world scenarios. This study exploits deep convolutional neural networks to predict human search efficiency from computational estimates of similarity between objects populating, potentially, any visual scene. Our results provide ecological evidence supporting the similarity principles: search performance continuously varies across tasks and conditions and improves with decreasing TD similarity and increasing DD similarity. Furthermore, our results reveal a crucial dissociation: TD and DD similarities mainly operate at two distinct layers of the network: DD similarity at the intermediate layers of coarse object features and TD similarity at the final layers of complex features used for classification. This suggests that these different similarities exert their major effects at two distinct perceptual levels and demonstrates our methodology's potential to offer insights into the depth of visual processing on which the search relies. By combining computational techniques with visual search principles, this approach aligns with modern trends in other research areas and fulfils longstanding demands for more ecologically valid research in the field of visual search.

Advancing non-target analysis of emerging environmental contaminants with machine learning: Current status and future implications

Emerging environmental contaminants (EECs) such as pharmaceuticals, pesticides, and industrial chemicals pose significant challenges for detection and identification due to their structural diversity and lack of analytical standards. Traditional targeted screening methods often fail to detect these compounds, making non-target analysis (NTA) using high-resolution mass spectrometry (HRMS) essential for identifying unknown or suspected contaminants. However, interpreting the vast datasets generated by HRMS is complex and requires advanced data processing techniques. Recent advancements in machine learning (ML) models offer great potential for enhancing NTA applications. As such, we reviewed key developments, including optimizing workflows using computational tools, improved chemical structure identification, advanced quantification methods, and enhanced toxicity prediction capabilities. It also discusses challenges and future perspectives in the field, such as refining ML tools for complex mixtures, improving inter-laboratory validation, and further integrating computational models into environmental risk assessment frameworks. By addressing these challenges, ML-assisted NTA can significantly enhance the detection, quantification, and evaluation of EECs, ultimately contributing to more effective environmental monitoring and public health protection.

Learning to fear novel stimuli by observing others in the social affordance framework

Fear responses to novel stimuli can be learned directly, through personal experiences (Fear Conditioning, FC), or indirectly, by observing conspecific reactions to a stimulus (Social Fear Learning, SFL). Although substantial knowledge exists about FC and SFL in humans and other species, they are typically conceived as mechanisms that engage separate neural networks and operate at different levels of complexity. Here, we propose a broader framework that links these two fear learning modes by supporting the view that social signals may act as unconditioned stimuli during SFL. In this context, we highlight the potential role of subcortical structures of ancient evolutionary origin in encoding social signals and argue that they play a pivotal function in transforming observed emotional expressions into adaptive behavioural responses. This perspective extends the social affordance hypothesis to subcortical circuits underlying vicarious learning in social contexts. Recognising the interplay between these two modes of fear learning paves the way for new empirical studies focusing on interspecies comparisons and broadens the boundaries of our knowledge of fear acquisition.

Artificial Intelligence and Neuroscience: Transformative Synergies in Brain Research and Clinical Applications

The convergence of Artificial Intelligence (AI) and neuroscience is redefining our understanding of the brain, unlocking new possibilities in research, diagnosis, and therapy. This review explores how AI's cutting-edge algorithms-ranging from deep learning to neuromorphic computing-are revolutionizing neuroscience by enabling the analysis of complex neural datasets, from neuroimaging and electrophysiology to genomic profiling. These advancements are transforming the early detection of neurological disorders, enhancing brain-computer interfaces, and driving personalized medicine, paving the way for more precise and adaptive treatments. Beyond applications, neuroscience itself has inspired AI innovations, with neural architectures and brain-like processes shaping advances in learning algorithms and explainable models. This bidirectional exchange has fueled breakthroughs such as dynamic connectivity mapping, real-time neural decoding, and closed-loop brain-computer systems that adaptively respond to neural states. However, challenges persist, including issues of data integration, ethical considerations, and the "black-box" nature of many AI systems, underscoring the need for transparent, equitable, and interdisciplinary approaches. By synthesizing the latest breakthroughs and identifying future opportunities, this review charts a path forward for the integration of AI and neuroscience. From harnessing multimodal data to enabling cognitive augmentation, the fusion of these fields is not just transforming brain science, it is reimagining human potential. This partnership promises a future where the mysteries of the brain are unlocked, offering unprecedented advancements in healthcare, technology, and beyond.

NeoSLAM: Long-Term SLAM Using Computational Models of the Brain

Simultaneous Localization and Mapping (SLAM) is a fundamental problem in the field of robotics, enabling autonomous robots to navigate and create maps of unknown environments. Nevertheless, the SLAM methods that use cameras face problems in maintaining accurate localization over extended periods across various challenging conditions and scenarios. Following advances in neuroscience, we propose NeoSLAM, a novel long-term visual SLAM, which uses computational models of the brain to deal with this problem. Inspired by the human neocortex, NeoSLAM is based on a hierarchical temporal memory model that has the potential to identify temporal sequences of spatial patterns using sparse distributed representations. Being known to have a high representational capacity and high tolerance to noise, sparse distributed representations have several properties, enabling the development of a novel neuroscience-based loop-closure detector that allows for real-time performance, especially in resource-constrained robotic systems. The proposed method has been thoroughly evaluated in terms of environmental complexity by using a wheeled robot deployed in the field and demonstrated that the accuracy of loop-closure detection was improved compared with the traditional RatSLAM system.