Equivariant Spatiotemporal Transformers with MDL-Guided Feature Selection for Malignancy Detection in Dynamic PET
Dadashkarimi, M.
Show abstract
Dynamic Positron Emission Tomography (PET) scans offer rich spatiotemporal data for detecting malignancies, but their high-dimensionality and noise pose significant challenges. We introduce a novel framework, the Equivariant Spatiotemporal Transformer with MDL-Guided Feature Selection (EST-MDL), which integrates group-theoretic symmetries, Kolmogorov complexity, and Minimum Description Length (MDL) principles. By enforcing spatial and temporal symmetries (e.g., translations and rotations) and leveraging MDL for robust feature selection, our model achieves improved generalization and interpretability. Evaluated on three realworld PET datasets--LUNG-PET, BRAIN-PET, and BREAST-PET--our approach achieves AUCs of 0.94, 0.92, and 0.95, respectively, outperforming CNNs, Vision Transformers (ViTs), and Graph Neural Networks (GNNs) in AUC, sensitivity, specificity, and computational efficiency. This framework offers a robust, interpretable solution for malignancy detection in clinical settings.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports 95%
- COSIME: Cooperative multi-view integration with Scalable and Interpretable Model Explainer 92%
- UDCT: Unsupervised data to content transformation with histogram-matching cycle-consistent generative adversarial networks 91%
Similar papers in this journal
- deepManReg: a deep manifold-regularized learning model for improving phenotype prediction from multi-modal data 93%
- Adversarial domain translation networks for fast and accurate integration of large-scale atlas-level single-cell datasets 90%
- Automated customization of large-scale spiking network models to neuronal population activity 89%
Similar papers in this journal
- Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognition 93%
- Cross-subject Mapping of Neural Activity with Restricted Boltzmann Machines 93%
- Quantifying the Brain Predictivity of Artificial Neural Networks with Nonlinear Response Mapping 91%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.