# Graph Representation Learning of Longitudinal Medical Imaging Trajectories for Treatment Response Prediction

arXiv: https://arxiv.org/abs/2607.04912 · HTML: https://mlsanity.com/paper/2607.04912/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Longitudinal detection of radiological abnormalities with time-modulated LSTM](https://mlsanity.com/paper/1807.06144/) (2018)
- [Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer](https://mlsanity.com/paper/2509.14872/) (2025)
- [SSL-AD: Spatiotemporal Self-Supervised Learning for Generalizability and Adaptability Across Alzheimer's Prediction Tasks and Datasets](https://mlsanity.com/paper/2509.10453/) (2025)

## Abstract (arXiv)

In patients with breast cancer, pathological complete response (pCR) has been established as a clinically meaningful surrogate marker for long-term outcomes. While commonly treated with neoadjuvant chemotherapy (NACT), effective treatment decision-making remains challenging, as therapeutic response can vary substantially across patients, calling for predictive models capable of accurately estimating individualized treatment response. To address this, we propose an imaging-based 3D spatio-temporal framework for treatment response prediction that integrates a state-of-the-art graph neural network with relational modeling of temporal interactions across timepoints alongside three novel complementary self-supervised treatment trajectory representation learning objectives. Experiments across a cohort of 585 patients from the public ISPY-2 dataset demonstrate that our method substantially outperforms both vision and self-supervised learning baselines across several classification metrics. Alongside establishing a breast cancer pCR prediction benchmark, we include a principled ablation of our method and further introduce and empirically assess the impact of the available number of DCE-MRI timepoints per patient trajectory and the inclusion of inter-scan time-differences. Overall, our study substantiates the utility of clinically meaningful longitudinal medical imagaging modeling for predicting NACT-induced pCR. We will publicly share our code repository and a user-friendly PyPI library for dataset curation upon publication, effectively promoting reproducible open-source research.