OSCR

Multimodal DeepSurv model with SHAP-based interpretation for predicting local failure in patients with brain metastases undergoing hypofractionated stereotactic radiotherapy.

Overview

Authors: Long Jin1, Qifan Zhao2, Ying Xiao1, Yuan Hu1, Jie Wu1, Gaofei Zhang1
  1. Department of Radiation Oncology, Shaanxi Provincial People's Hospital, Xi'an, China
  2. School of Computing and Data Science, The University of Hong Kong, Hong Kong, China
Institutions: Shaanxi Provincial People's Hospital (China); University of Hong Kong (Hong Kong SAR China)
Journal: Frontiers in neuroscience, volume 20, article 1908548
Dates: received 14 June 2026; accepted 17 July 2026; published online 12 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3389/fnins.2026.1908548 · PMID 42656372 · PMCID PMC13506756 · OpenAlex W7202262347
Open access: gold, a free copy (OpenAlex)
Categories: structural MRI / diffusion (modality), human (organism), other condition (population), clinical / translational (subfield)
Methods: Connectivity, Machine learning, fMRI & imaging, Statistics
Keywords: brain metastases, explainable AI, MRI, multimodal, radiomics
Topic: Brain Metastases and Treatment (Oncology, Medicine), according to OpenAlex
Citations: not cited yet (Europe PMC); 20 references in the paper

Abstract

Objective: Local Progression-Free Survival (LPFS) is an important clinical endpoint following hypofractionated stereotactic radiotherapy (HSRT) for brain metastases (BMs). However, accurate prediction of local failure risk remains challenging because conventional clinical factors do not fully capture tumor heterogeneity. Therefore, we aimed to develop and validate an explainable radiomics-based deep learning survival model to predict LPFS after HSRT and identify patients at elevated risk of local failure.

Methods: This retrospective study included 100 patients with BMs treated with HSRT between 2019 and 2023 as training dataset, while utilized medical images and clinical features from 40 patients from publicly available dataset PROTEAS project. Radiomic features were extracted from the contrast-enhancing BM (T1-weighted contrast-enhanced MRI) and edema (T2-FLAIR MRI). A baseline Cox proportional hazards model incorporating clinical variables was established for comparison. Three DeepSurv models were developed using different combinations of clinical, BM-derived, and edema-derived radiomic features. Model performance was evaluated using the concordance index (C-index). Kaplan–Meier analysis was performed for risk stratification, and Shapley Additive Explanations (SHAP) were used to identify the most influential prognostic features.

Results: The best predictive performance was achieved by the DeepSurv model integrating clinical, BM-derived, and edema-derived radiomic features, outperforming the clinical-only Cox model (C-index: 0.61 vs. 0.72). The model effectively stratified patients into distinct prognostic groups with significantly different local failure-free survival outcomes (P = 0.002). SHAP analysis identified edema Gray Level Co-occurrence Matrix (GLCM) Cluster Prominence as the most important predictor of local failure, followed by edema Large Area High Gray Level Emphasis (LAHGLE), tumor GLCM Cluster Prominence, and tumor LAHGLE. Patients with high edema GLCM Cluster Prominence exhibited significantly worse local failure-free survival than those with low values (P = 0.0155).

Conclusion: A combination of clinical, tumor-derived, and edema-derived radiomic features predicted Local Progression-Free Survival more accurately than clinical variables alone. Peritumoral edema features contributed more strongly to local failure prediction than tumor features, highlighting the prognostic importance of the tumor microenvironment. Patients received targeted therapy with low-risk radiomic profiles benefit from HSRT for local control.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability statement

The datasets analyzed for this study can be found in the https://github.com/snowflake-Zhao/BrM_HSRT.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 6 authors, 5 keywords, 20 references.

Cite

This paper

Jin, L., Zhao, Q., Xiao, Y., Hu, Y., Wu, J., & Zhang, G. (2026). Multimodal DeepSurv model with SHAP-based interpretation for predicting local failure in patients with brain metastases undergoing hypofractionated stereotactic radiotherapy. Frontiers in neuroscience, 20, 1908548. https://doi.org/10.3389/fnins.2026.1908548

BibTeX

@article{jin2026multimodal,
author = {Jin, Long and Zhao, Qifan and Xiao, Ying and Hu, Yuan and Wu, Jie and Zhang, Gaofei},
title = {{Multimodal DeepSurv model with SHAP-based interpretation for predicting local failure in patients with brain metastases undergoing hypofractionated stereotactic radiotherapy}},
journal = {Frontiers in neuroscience},
year = {2026},
month = aug,
volume = {20},
pages = {1908548},
publisher = {Frontiers Media SA},
issn = {1662-4548},
doi = {10.3389/fnins.2026.1908548},
url = {https://doi.org/10.3389/fnins.2026.1908548},
pmid = {42656372},
pmcid = {PMC13506756}
}

RIS

TY - JOUR
AU - Jin, Long
AU - Zhao, Qifan
AU - Xiao, Ying
AU - Hu, Yuan
AU - Wu, Jie
AU - Zhang, Gaofei
TI - Multimodal DeepSurv model with SHAP-based interpretation for predicting local failure in patients with brain metastases undergoing hypofractionated stereotactic radiotherapy
T2 - Frontiers in neuroscience
J2 - Front Neurosci
PY - 2026
DA - 2026/08/12
VL - 20
SP - 1908548
SN - 1662-4548
PB - Frontiers Media SA
DO - 10.3389/fnins.2026.1908548
UR - https://doi.org/10.3389/fnins.2026.1908548
LA - en
ER -

CSL-JSON

{
"id": "10.3389/fnins.2026.1908548",
"type": "article-journal",
"title": "Multimodal DeepSurv model with SHAP-based interpretation for predicting local failure in patients with brain metastases undergoing hypofractionated stereotactic radiotherapy",
"container-title": "Frontiers in neuroscience",
"author": [
{
"family": "Jin",
"given": "Long"
},
{
"family": "Zhao",
"given": "Qifan"
},
{
"family": "Xiao",
"given": "Ying"
},
{
"family": "Hu",
"given": "Yuan"
},
{
"family": "Wu",
"given": "Jie"
},
{
"family": "Zhang",
"given": "Gaofei"
}
],
"container-title-short": "Front Neurosci",
"volume": "20",
"page": "1908548",
"DOI": "10.3389/fnins.2026.1908548",
"PMID": "42656372",
"PMCID": "PMC13506756",
"ISSN": "1662-4548",
"publisher": "Frontiers Media SA",
"URL": "https://doi.org/10.3389/fnins.2026.1908548",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
12
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41598-024-60781-5 [code]
Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data.
Journal: Scientific reports
In common: structural MRI / diffusion, clinical / translational, other condition, 3 references
[2] doi:10.1109/jtehm.2022.3219625
A Self-Attention-Guided 3D Deep Residual Network With Big Transfer to Predict Local Failure in Brain Metastasis After Radiotherapy Using Multi-Channel MRI.
Journal: IEEE journal of translational engineering in health and medicine
In common: structural MRI / diffusion, clinical / translational, other condition, 3 references
[3] doi:10.3389/fonc.2025.1497195 [code]
Early characterization and prediction of glioblastoma and brain metastasis treatment efficacy using medical imaging-based radiomics and artificial intelligence algorithms.
Journal: Frontiers in oncology
In common: clinical / translational, other condition, 3 references
[4] doi:10.1038/s41598-023-47702-8 [code]
Predicting stereotactic radiosurgery outcomes with multi-observer qualitative appearance labelling versus MRI radiomics.
Journal: Scientific reports
In common: structural MRI / diffusion, clinical / translational, other condition, 2 references
[5] doi:10.1038/s41598-022-25389-7 [code]
Performance sensitivity analysis of brain metastasis stereotactic radiosurgery outcome prediction using MRI radiomics.
Journal: Scientific reports
In common: structural MRI / diffusion, clinical / translational, other condition, 2 references
[6] doi:10.1016/j.phro.2024.100602
Prediction of radiologic outcome-optimized dose plans and post-treatment magnetic resonance images: A proof-of-concept study in breast cancer brain metastases treated with stereotactic radiosurgery.
Journal: Physics and imaging in radiation oncology
In common: structural MRI / diffusion, clinical / translational, other condition, 2 references
[7] doi:10.1117/1.jmi.12.2.024504 [code]
Prediction of brain metastasis progression after stereotactic radiosurgery: sensitivity to changing the definition of progression.
Journal: Journal of medical imaging (Bellingham, Wash.)
In common: structural MRI / diffusion, clinical / translational, other condition, 2 references
[8] doi:10.1093/noajnl/vdad064 [code]
Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes.
Journal: Neuro-oncology advances
In common: structural MRI / diffusion, other condition, 2 references
[9] doi:10.1002/ijc.70250 [code]
Outcomes and risk factors of hemorrhage in patients with resected brain metastases.
Journal: International journal of cancer
In common: structural MRI / diffusion, clinical / translational, other condition, 1 reference
[10] doi:10.1186/s13014-026-02825-w [code]
Prediction of local failure after stereotactic radiotherapy in melanoma brain metastases using ensemble learning on clinical, dosimetric, and radiomic data.
Journal: Radiation oncology (London, England)
In common: structural MRI / diffusion, clinical / translational, other condition, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.