Saved in:
Bibliographic Details
Main Authors: Janíčková, Ivana, Tan, Yen Y., Helbich, Thomas H., Miloserdov, Konstantin, Bago-Horvath, Zsuzsanna, Heber, Ulrike, Langs, Georg
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.14872
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914045640048640
author Janíčková, Ivana
Tan, Yen Y.
Helbich, Thomas H.
Miloserdov, Konstantin
Bago-Horvath, Zsuzsanna
Heber, Ulrike
Langs, Georg
author_facet Janíčková, Ivana
Tan, Yen Y.
Helbich, Thomas H.
Miloserdov, Konstantin
Bago-Horvath, Zsuzsanna
Heber, Ulrike
Langs, Georg
contents Effective therapy decisions require models that predict the individual response to treatment. This is challenging since the progression of disease and response to treatment vary substantially across patients. Here, we propose to learn a representation of the early dynamics of treatment response from imaging data to predict pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NACT). The longitudinal change in magnetic resonance imaging (MRI) data of the breast forms trajectories in the latent space, serving as basis for prediction of successful response. The multi-task model represents appearance, fosters temporal continuity and accounts for the comparably high heterogeneity in the non-responder cohort.In experiments on the publicly available ISPY-2 dataset, a linear classifier in the latent trajectory space achieves a balanced accuracy of 0.761 using only pre-treatment data (T0), 0.811 using early response (T0 + T1), and 0.861 using four imaging time points (T0 -> T3). The code will be made available upon paper acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14872
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer
Janíčková, Ivana
Tan, Yen Y.
Helbich, Thomas H.
Miloserdov, Konstantin
Bago-Horvath, Zsuzsanna
Heber, Ulrike
Langs, Georg
Computer Vision and Pattern Recognition
Effective therapy decisions require models that predict the individual response to treatment. This is challenging since the progression of disease and response to treatment vary substantially across patients. Here, we propose to learn a representation of the early dynamics of treatment response from imaging data to predict pathological complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NACT). The longitudinal change in magnetic resonance imaging (MRI) data of the breast forms trajectories in the latent space, serving as basis for prediction of successful response. The multi-task model represents appearance, fosters temporal continuity and accounts for the comparably high heterogeneity in the non-responder cohort.In experiments on the publicly available ISPY-2 dataset, a linear classifier in the latent trajectory space achieves a balanced accuracy of 0.761 using only pre-treatment data (T0), 0.811 using early response (T0 + T1), and 0.861 using four imaging time points (T0 -> T3). The code will be made available upon paper acceptance.
title Temporal Representation Learning of Phenotype Trajectories for pCR Prediction in Breast Cancer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.14872