BARG: A Boosted Adaptive Radial Proximity Method for Graph Modelling in Breast Cancer Hormonal Status Classification
Bibliographic record
Abstract
Graph Convolutional Networks (GCNs) perform best on homophilic graphs, where connected nodes share similar features; however, histopathology images pose a challenge due to their heterogeneous tissue patterns and diverse morphological structures.In such images, ensuring homophily is crucial because, in non-homophilic graphs, message passing can cause oversmoothing, where features from dissimilar tissue regions become mixed, reducing the ability to distinguish distinct patterns.To address this, we introduce Boosted Adaptive Radius Graph (BARG), a novel graph modelling strategy tailored for Haematoxylin and Eosin (H&E)-stained Tissue MicroArray (TMA) images.BARG improves upon the traditional Fixed Radius Graph (FRG) approach by incorporating an adaptive, tissue-specific edge threshold and a two-hop edge promotion mechanism to enhance message passing and maintain connectivity without compromising homophily.The adaptive threshold, termed Adaptive Radial Proximity (ARP), is determined for each graph using statistical analysis of Local Density Features (LDFs) derived from FRG-based graphs and is further refined using a globally optimised scaling factor across the dataset.We evaluate BARG using a dataset of 1000 TMA images with balanced positive and negative samples for training and a test set of 554 images (287 positive and 257 negative), with each patient contributing one image.Graph node features are extracted via a pre-trained VGG16 Convolutional Neural Network (CNN) by processing small image patches centred at nucleus detection peaks.Compared to the FRG-based models, BARG yields notable performance gains, achieving 78% accuracy, 75% sensitivity, and 81% specificity, marking a 4% improvement in accuracy and an 8% increase in sensitivity.BARG also reaches an AUC-ROC of 0.85, a 3% enhancement over FRG, while preserving structural and contextual tissue relevance.These results position BARG as a robust, scalable solution for graph modelling in histopathology image analysis, suitable for broader applications in computational pathology.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".