PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 5, 2026Cancer Research0 citations

Abstract 5468: Deep learning-based analysis reveals patient-level proton radiation therapy trajectories using single-cell PBMC chromatin images.

View Full Paper
HSHannah M. SchlüterTSTrinadha Rao SornapudiDLDominic Leiser

Key Result

Deep learning analysis of PBMC chromatin images revealed that patients whose profiles shifted toward healthy states after proton radiation therapy were less likely to experience disease recurrence.

Key Points

  • The aim is to evaluate if chromatin images from PBMCs can predict patient responses and trajectories during proton radiation therapy.
  • Blood samples collected at five timepoints from 150 cancer patients and 50 healthy controls.
  • PBMCs isolated, stained with DAPI, and imaged using a confocal microscope.
  • Applied machine learning techniques to classify patients and predict trajectories with a multiple-instance learning approach.
  • Identified cancer-specific changes in PBMC chromatin structure from patients.
  • Longitudinal analysis revealed three patient subgroups based on chromatin image profiles.
  • Patients whose profiles aligned more with healthy controls post-therapy showed lower recurrence rates.

Structured PICO

Does deep learning-based analysis of PBMC chromatin images predict patient trajectories and disease recurrence in cancer patients undergoing proton radiation therapy?

P
Population
150 patients across various cancers including Central Nervous System and Head & Neck cancers, and 50 healthy volunteers.
I
Intervention
Deep learning-based analysis (multiple-instance learning) of single-cell PBMC chromatin images obtained from blood samples at five timepoints (before, during, at the end of, and twice after PRT).
C
Comparator
Healthy volunteers (for baseline comparison)
O
Outcome
Patient trajectories (similarity-to-healthy scores) and prediction of disease recurrencesurrogate

Deep learning analysis of PBMC chromatin images offers a novel, non-invasive biomarker for monitoring patient response and predicting recurrence in cancer patients undergoing proton radiation therapy.

Abstract

Abstract Introduction: The development of non-invasive, simple, and accurate methods to predict patient response to cancer therapy remains an open challenge. Proton radiation therapy (PRT) is increasingly used for hard-to-reach tumors or those in sensitive areas. However, it remains more expensive than other radiation therapies and while considered safer than conventional radiation therapy, its short- and long-term side effects are still not well explored. Therefore, developing an early measure for patient response is a critical research direction. Here we sought to test whether chromatin images of peripheral blood mononuclear cells (PBMCs) contain sufficient information to track patients’ trajectories during and after PRT. Methods: We collected blood samples at five timepoints (before, during, at the end of, and twice after PRT) from 150 patients across various cancers including Central Nervous System and Head Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 5468.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Schlüter et al. (2026) studied this question. Deep learning analysis of PBMC chromatin images revealed that patients whose profiles shifted toward healthy states after proton radiation therapy were less likely to experience disease recurrence.

synapsesocial.com/papers/69d1fd9ca79560c99a0a3c33https://doi.org/10.1158/1538-7445.am2026-5468
Ask AI
Helpful
Bookmark
Share
View Full Paper