An interpretable graph neural network for histological image analysis

Graph neural networks (GNNs) is an information - processing system that uses message passing among graph nodes. In recent years, GNN variants including graph attention network (GAT), graph convolutional network (GCN), and graph recurrent network (GRN) have shown revolutionary performance in computer vision applications using deep learning and artificial intelligence. These neural network model extensions, collect information in the form of graphs. GNN may be divided into three groups based on the challenges it solves: link prediction, node classification, graph classification. Machines can differentiate and recognise objects in image and video using standard CNNs. Extensive amount of research work needs to be done before robots can have same visual intuition as humans. GNN architectures, on the other hand, may be used to solve various image categorization and video challenges. The number of GNN applications in computer vision not limited, continues to expand. Human-object interaction, actin understanding, image categorization from a few shots and many more. In this paper use of GNN in image and video understanding, design aspects, architecture, applications and implementation challenges towards computer vision is described. GNN is a strong tool for analysing graph data and is still a relatively active area that needs further researches attention to solve many computer vision applications.

This study introduces a novel approach to drug discovery in regenerative medicine through the utilization of a graph neural network (GNN). The research methodology integrates the development and training of the GNN with a subsequent evaluation of its performance metrics. The first phase involves the generation of synthetic data simulating a biological network, employing networkX and NumPy libraries to construct a random graph with Erdos-Renyi topology. The data, representing cellular responses to biomaterials, is then converted into PyTorch tensors for compatibility with the GNN architecture. The GNN model, characterized by two fully connected layers with ReLU and log-softmax activations, captures intricate relationships within the graph-structured data. The second phase employs a stochastic gradient descent algorithm, specifically the Adam optimizer, to train the GNN over 100 epochs using the cross-entropy loss for multi-class classification. The research methodology extends to the evaluation phase, producing three distinct output graphs for analysis: Visualization of the graph structure, a comparison between predicted and true labels, and a plot illustrating training loss over epochs. Performance metrics, including accuracy, precision, recall, and F1-score, are computed to assess the model’s predictive capabilities quantitatively. The study concludes with a discussion on the nuances revealed by each graph and their implications for refining GNN models in the context of drug discovery for regenerative medicine.

This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced the performance across all models tested. For example, integrating the Louvain model with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains were noted when the Louvain model was paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent increase in performance—reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations—highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques.

In this paper we survey our recent results characterizing various graph neural network (GNN) architectures in terms of their ability to classify nodes over graphs, for classifiers based on unary logical formulas- or queries. We focus on the language FOC2, a well-studied fragment of FO. This choice is motivated by the fact that FOC2 is related to theWeisfeiler-Lehman (WL) test for checking graph isomorphism, which has the same ability as GNNs for distinguishing nodes on graphs. We unveil the exact relationship between FOC2 and GNNs in terms of node classification. To tackle this problem, we start by studying a popular basic class of GNNs, which we call AC-GNNs, in which the features of each node in a graph are updated, in successive layers, according only to the features of its neighbors. We prove that the unary FOC2 formulas that can be captured by an AC-GNN are exactly those that can be expressed in its guarded fragment, which in turn corresponds to graded modal logic. This result implies in particular that ACGNNs are too weak to capture all FOC2 formulas. We then seek for what needs to be added to AC-GNNs for capturing all FOC2. We show that it suffices to add readouts layers, which allow updating the node features not only in terms of its neighbors, but also in terms of a global attribute vector. We call GNNs with readouts ACR-GNNs. We also describe experiments that validate our findings by showing that, on synthetic data conforming to FOC2 but not to graded modal logic, AC-GNNs struggle to fit in while ACR-GNNs can generalise even to graphs of sizes not seen during training.

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we proposed a novel multi-view graph pooling operator dubbed as MVPool, which ranks nodes across different views with different contextual graph information. Meanwhile, attention mechanism is utilized to promote the collaboration of different views for generating robust node rankings. Then the pooling operation adaptively selects a subset of nodes to form an induced subgraph based on the ranking list. To preserve the underlying graph topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. The proposed MVPool operator is a general strategy that can be integrated into various graph neural network architectures. By combining MVPool operator with graph neural networks, we perform hierarchical representation learning for both node and graph level classification as well as clustering tasks. Experimental results on nine widely used benchmarks demonstrate the effectiveness of our proposed model.

Ovonic threshold switching (OTS) selectors are pivotal in nonvolatile memory devices due to their nonlinear electrical characteristics and polarity-dependent threshold voltages. However, the atomic-scale origins of the defect states responsible for these behaviors remain unclear. In this study, we systematically investigate defects in amorphous GeSe using molecular dynamics simulations accelerated by machine learning interatomic potentials (MLIPs). We first benchmark several MLIP architectures, including descriptor-based potentials and graph neural network (GNN)-based potentials. Our results demonstrate that capturing higher-order interactions, at least four-body correlations, and medium-range structural order is essential for accurately representing amorphous GeSe structures. Our analysis indicates that GNN architectures with multiple interaction layers effectively capture higher-order correlations and medium-range order, thereby preventing spurious defects easily introduced by less descriptive MLIPs. Utilizing the optimized GNN model, we identify two distinct defect motifs across 20 independent 960-atom amorphous GeSe structures: aligned Ge chains associated with defect states near the conduction band, and overcoordinated Ge chains linked to defect states near the valence band. Moreover, we establish correlations between electronic defect levels and specific structural features─namely, the average alignment of bond angles in aligned chains and the degree of local Peierls distortion around overcoordinated Ge atoms. These insights provide a theoretical framework for interpreting experimental observations and deepening the understanding of defect-driven OTS phenomena in amorphous GeSe.

Humanistic link oriented data (LOD) play a crucial role as they appear in technological and financial sectors including smart cities, social networks, and long supply chains. The primary difficulties in mining LOD are their volume, the rate of missing or corrupted values, the non-linear relationships, and its higher order nature. Therefore, deep learning approaches of comparable complexity should be used if meaningful knowledge is to be extracted from the LOD ocean. Tensor stack networks (TSNs) consist of layers with information flowing serially both between layers and within the same layer. TSNs natively handle multidimensional data such as images and graphs, preventing information loss from vectorization by preserving topological knowledge. Two TSNs have been implemented, one assessing the structural resilience of a graph based on connectivity patterns and one computing the correlation coefficient for graphs compressed with DCT2. In both cases TSNs achieved superior performance to baselines. Self organizing maps (SOMs) are unsupervised neural network architectures learning how to modify connections between two spaces, the data and the coordinate space. SOMs construct a low dimensional projection from the former to the latter while preserving up to an extent the primary topological properties. A tensor distance metric allows considerably more flexibility compared to vector-based ones as corroborated by clustering neuroimages from an open fMRI dataset. Graph neural networks (GNNs) have emerged as a versatile architectural paradigm. Through message passing and aggregation a global state eventually emerges from local ground truth stored at the vertices or at the edges. Research focuses on the conditions for the emergence of the steady state and the convergence rate. A GNN for discovering affective Twitter communities is proposed. Experiments on benchmark graphs suggest GNNs are more efficient than the baseline. Comparing the abovementioned architectures it follows that GNNs are the most flexible as they learn in an unsupervised and distributed way and they operate on irregular domains. However, they require a tensor distance metric to handle multidimensional data. Another conclusion is that GNNs offer higher explainability as they adjust to the underlying domain by naturally expressing its relationships no matter how complex they are without imposing any external structure on it.

Purpose To develop an explainable radiopathomic graph deep learning (RPGDL) system for multiscale spatial-contextual modeling of intratumoral heterogeneity and evaluate its performance for the prediction of pathologic complete response (pCR) to neoadjuvant therapy in breast cancer. Materials and Methods The RPGDL system was developed from dual-center retrospective analysis of patients with biopsy-proven invasive breast cancer (May 2018-August 2024). For each tumor, individual radiomic and pathomic graphs were generated from pretherapeutic MRI and hematoxylin-eosin-stained biopsy slide images, respectively. These graphs were then processed by three distinct graph neural networks (GNNs): radiomic, pathomic, and radiopathomic. GNN performance was assessed with the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). A multifaceted approach was used to explain the GNNs' predictions. Results The training set included 582 (mean age, 52 years ± 9 [SD]) patients and the external test set 468 (50 years ± 10) patients from centers 1 and 2, respectively. The radiomic GNN achieved AUCs of 0.89 (95% CI: 0.85, 0.93) in the training set and 0.84 (95% CI: 0.80, 0.89) in the external test set; the pathomic GNN achieved AUCs of 0.87 (95% CI: 0.83, 0.91) in the training set and 0.83 (95% CI: 0.78, 0.88) in the external test set, with no significant difference between them (P > .05). The radiopathomic GNN outperformed both single-modality GNNs (training set: AUC, 0.95 [95% CI: 0.92, 0.98]; external test set: AUC, 0.91 [95% CI: 0.87, 0.94]; P < .05; NRI and IDI confirmed). Pathomic graphs dominated probability increases for pCR predictions, while radiomic graphs drove probability decreases for non-pCR predictions. Multifaceted analyses verified GNNs' explainability. Conclusion The developed RPGDL system enabled multiscale spatial-contextual intratumoral heterogeneity modeling for high-performance, explainable prediction of pCR to neoadjuvant therapy in breast cancer. Keywords: Dynamic Contrast-enhanced MRI, Breast, Tumor Response, Radiology-Pathology Integration, Prognosis, Principal Component Analysis, Perception, Supervised Learning, Reconstruction Algorithm Supplemental material is available for this article. © RSNA, 2026.

Accurate and efficient simulation of photoinduced dynamics in materials remains a significant challenge due to the computational cost of excited-state electronic structure calculations and the necessity to account for excitonic effects. In this work, we present a machine learning (ML)-accelerated approach to nonadiabatic molecular dynamics simulations that incorporates excitonic effects by predicting excited-state wave functions via configuration interaction coefficients and excitation energies using a graph neural network (GNN) architecture. The GNN model leverages molecular orbital information from ground-state calculations to construct input graphs, enabling efficient and accurate prediction of relevant excited-state wave functions and energies required for ab initio-based fewest-switches surface hopping simulations. Benchmarking on a zinc phthalocyanine-fullerene (ZnPc-C60) donor-acceptor system reveals that these ML-predicted properties agree closely with those obtained from linear-response time-dependent density functional theory calculations while boosting the computational efficiency significantly. The ML-accelerated simulations reproduce excited-state dynamics with high fidelity, demonstrating the methodological capability to study complex photodynamical processes in large systems. This work provides a general and scalable framework for efficient excited-state dynamics simulations in materials where excitonic effects play a vital role.

Polypharmacy, the simultaneous use of multiple medications, significantly increases the risk of adverse Drug-Drug Interactions (DDIs), posing serious challenges to patient safety and healthcare systems. Traditional DDI detection methods are often binary and lack clinical interpretability, failing to provide actionable risk assessments for healthcare professionals. This survey comprehensively reviews computational approaches for DDI prediction, with a focus on Graph Neural Network (GNN) architectures and their integration with Large Language Models (LLMs) for enhanced clinical decision support. We analyze ten representative works spanning relational graph convolutional networks, meta path based heterogeneous networks, multimodal fusion frameworks, and hybrid approaches. Our analysis reveals that while GNN based methods show superior performance in capturing molecular relationships, significant gaps remain in clinical interpretability, risk level classification, and real world deployment. Building on these insights, we propose an integrated framework combining GNNs for molecular analysis with LLMs for contextual reasoning and recommendation refinement. The proposed system categorizes DDI risks into low, moderate, and high levels and suggests safer alternative drugs. We discuss the societal relevance of DDI prediction systems in promoting sustainable healthcare and their alignment with Sustainable Development Goals (SDGs). Finally, we outline future research directions including real time clinical integration, multimodal data fusion, and enhanced explainability for non-technical users.

The inherent complexity and heterogeneity of the Internet of Things (IoT) ecosystem present significant challenges for developing effective intrusion detection systems. While graph deep-learning-based methods have shown promise in cybersecurity applications, existing approaches primarily construct graphs based on physical network connections, which may not effectively capture node representations. This paper proposes a Top-K Similarity Graph Framework (TKSGF) for IoT network intrusion detection. Instead of relying on physical links, the TKSGF constructs graphs based on Top-K attribute similarity, ensuring a more meaningful representation of node relationships. We employ GraphSAGE as the Graph Neural Network (GNN) model to effectively capture node representations while maintaining scalability. Furthermore, we conducted extensive experiments to analyze the impact of graph directionality (directed vs. undirected), different K values, and various GNN architectures and configurations on detection performance. Evaluations on binary and multi-class classification tasks using the NF-ToN IoT and NF-BoT IoT datasets from the Machine-Learning-Based Network Intrusion Detection System (NIDS) benchmark demonstrated that our proposed framework consistently outperformed traditional machine learning methods and existing graph-based approaches, achieving superior classification accuracy and robustness.

This paper compares the performance of two graph neural network architectures on the emulation of a cardiac mechanic model of the left ventricle of the heart. These models can be applied directly on the same computational mesh of the left ventricle geometry that is used by the expensive numerical forward solver, precluding the need for a low-order approximation of the true geometry. Our results show that these emulation approaches incur negligible loss in accuracy compared in the forward simulator, while making predictions multiple orders of magnitude more quickly, raising the prospect for their use in both forward and inverse problems in cardiac modelling.

Theoretical models of galaxy formation and evolution are primarily investigated through cosmological simulations and semi-analytical models. The former method consumes O(106) core-hours explicitly modeling the dynamics of the galaxies, whereas the latter method only requires O(103) core-hours foregoing directly simulating internal structure for computational efficiency. In this work, we present a proof-of-concept machine learning regression model, using a graph neural network architecture, to predict the stellar mass of high-redshift galaxies solely from their dark matter merger trees, trained from a radiation hydrodynamics cosmological simulation of the first galaxies.

Graph Neural Networks have been popularly investigated and achieved promising performance in node-wise and graph-level tasks, like node classification and graph classification. For graph classification, correctly defining pooling operations to coarsen an input graph for distilling hierarchical knowledge from node representations is demanded. Some works have devised pooling strategies to summarize a graph by evaluating and gathering the ranked top-k representative nodes. Yet there is few literature to explicitly consider the node's degree-specific structure information in pooling procedure. One intuition is the larger the node's degree is, the more important it probably is in the entire graph. In this work, we propose a novel Degree-Induced Pooling (DIPool), which can be integrated into various graph neural network architectures. Specifically, the DIPool layer devises two approaches for explicitly incorporating the characteristics and degree-specific structures of nodes into a unified criterion to evaluate the importance of the nodes within an input graph. This setting permits to retain more representative nodes to generate the newly pooled graph. Experimental results on a collection of public benchmarks have demonstrated the effectiveness of the proposed DIPool operator. Especially, DIPool achieves relative improvements of 3.69% on NCI1 and 3.24% on NCI109 compared with the best baseline ASAP.

In smart cities, sustainable development depends on energy load prediction since it directs utilities in effectively planning, distributing and generating energy. This work presents a novel hybrid deep learning model including components of the Improved-convolutional neural network (CNN), bidirectional long short-term memory (Bi-LSTM), Graph neural network (GNN), Transformer and Fusion Layer architectures for precise energy load forecasting. Better feature extraction results from the Improved-CNN's dilated convolution and residual block accommodation of wide receptive fields reduced the vanishing gradient problem. By capturing temporal links in both directions, Bi-LSTM networks help to better grasp complicated energy use patterns. Graph neural networks improve predictive capacities across linked systems by characterizing the spatial relationships between energy-consuming units in smart cities. Emphasizing critical trends to guarantee reliable forecasts, transformer models use attention methods to manage long-term dependencies in energy consumption data. Combining CNN, Bi-LSTM, Transformer and GNN component predictions in a Fusion Layer synthesizes numerous data representations to increase accuracy. With Root Mean Square Error of 5.7532 Wh, Mean Absolute Percentage Error of 3.5001%, Mean Absolute Error of 6.7532 Wh and R 2 of 0.9701, the hybrid model fared better than other models on the ‘Electric Power Consumption’ Kaggle dataset. This work develops a realistic model that helps informed decision-making and enhances energy efficiency techniques, promoting energy load forecasting in smart cities.