Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Artificial intelligence classification of spatial CD8 + T-cell distribution on computed tomography in oropharyngeal cancer

Haraldsson, André LU ; Askmyr, David LU ; Altunbulakli, Can LU orcid ; Nilsson, Mikael LU orcid ; Pignol, Jean Philippe ; Gustafsson Jamtheim, Christian LU ; Linnér, Anton ; Lindstedt, Malin LU orcid ; Greiff, Lennart LU and Gebre-Medhin, Maria LU (2026) In Radiotherapy and Oncology 221.
Abstract

CD8 + T-cell presence and distribution in oropharyngeal cancer (OPC) reflects specific immune phenotypes and are linked to prognosis. Image processing methods such as convolutional neural networks (CNN) may enhance treatment decisions. From standard computed tomography (CT) images, this study evaluates radiomics in combination with machine learning models and CNN for prediction of spatially resolved CD8 + T-cell immune profiles and survival outcomes. Pre-treatment CT images were analysed using and comparing radiomics and CNNs to predict stroma-to-cancer cell islet CD8 + T-cell infiltration ratios (SIR) and immune phenotypes as determined from spatially resolved tissue-array. Open data with genomic and image information were used for... (More)

CD8 + T-cell presence and distribution in oropharyngeal cancer (OPC) reflects specific immune phenotypes and are linked to prognosis. Image processing methods such as convolutional neural networks (CNN) may enhance treatment decisions. From standard computed tomography (CT) images, this study evaluates radiomics in combination with machine learning models and CNN for prediction of spatially resolved CD8 + T-cell immune profiles and survival outcomes. Pre-treatment CT images were analysed using and comparing radiomics and CNNs to predict stroma-to-cancer cell islet CD8 + T-cell infiltration ratios (SIR) and immune phenotypes as determined from spatially resolved tissue-array. Open data with genomic and image information were used for external validation. Further, we predicted survival outcomes stratified with our model in OPC patients recruited to the ARTSCAN III randomised clinical trial, which compared cetuximab with cisplatin concurrent with radiotherapy. Our CNN model achieved an area under the curve (AUC) of 0.75 (range 0.71–0.81) in predicting high versus low SIR, performing better than radiomics. When stratifying the ARTSCAN III patients according to the CNN-derived immune scores, patients with an inflamed phenotype had improved local control (HR 0.03, 95% CI 0–0.23, p < 0.0001), progression-free survival (PFS) (HR 0.36, 95%CI 0.18–0.71, p = 0.003), and overall survival (HR 0.35, 95%CI 0.14–0.85, p = 0.02) in univariable and multivariable analyses. When stratifying the ARTSCAN III patients by type of chemotherapy, high immune score classification corresponded to better PFS in cetuximab-treated patients. Our findings indicate the potential of CNNs to predict CD8 + T-cell infiltration in OPC, offering a promising non-invasive tool for treatment stratification and personalised therapy.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Radiotherapy and Oncology
volume
221
article number
111607
publisher
Elsevier
external identifiers
  • pmid:42162743
  • scopus:105039453904
ISSN
0167-8140
DOI
10.1016/j.radonc.2026.111607
language
English
LU publication?
yes
id
c97c900f-042f-4ff0-8d85-30ddd2e4f0e4
date added to LUP
2026-08-25 13:54:58
date last changed
2026-09-08 14:42:34
@article{c97c900f-042f-4ff0-8d85-30ddd2e4f0e4,
  abstract     = {{<p>CD8 + T-cell presence and distribution in oropharyngeal cancer (OPC) reflects specific immune phenotypes and are linked to prognosis. Image processing methods such as convolutional neural networks (CNN) may enhance treatment decisions. From standard computed tomography (CT) images, this study evaluates radiomics in combination with machine learning models and CNN for prediction of spatially resolved CD8 + T-cell immune profiles and survival outcomes. Pre-treatment CT images were analysed using and comparing radiomics and CNNs to predict stroma-to-cancer cell islet CD8 + T-cell infiltration ratios (SIR) and immune phenotypes as determined from spatially resolved tissue-array. Open data with genomic and image information were used for external validation. Further, we predicted survival outcomes stratified with our model in OPC patients recruited to the ARTSCAN III randomised clinical trial, which compared cetuximab with cisplatin concurrent with radiotherapy. Our CNN model achieved an area under the curve (AUC) of 0.75 (range 0.71–0.81) in predicting high versus low SIR, performing better than radiomics. When stratifying the ARTSCAN III patients according to the CNN-derived immune scores, patients with an inflamed phenotype had improved local control (HR 0.03, 95% CI 0–0.23, p &lt; 0.0001), progression-free survival (PFS) (HR 0.36, 95%CI 0.18–0.71, p = 0.003), and overall survival (HR 0.35, 95%CI 0.14–0.85, p = 0.02) in univariable and multivariable analyses. When stratifying the ARTSCAN III patients by type of chemotherapy, high immune score classification corresponded to better PFS in cetuximab-treated patients. Our findings indicate the potential of CNNs to predict CD8 + T-cell infiltration in OPC, offering a promising non-invasive tool for treatment stratification and personalised therapy.</p>}},
  author       = {{Haraldsson, André and Askmyr, David and Altunbulakli, Can and Nilsson, Mikael and Pignol, Jean Philippe and Gustafsson Jamtheim, Christian and Linnér, Anton and Lindstedt, Malin and Greiff, Lennart and Gebre-Medhin, Maria}},
  issn         = {{0167-8140}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{Radiotherapy and Oncology}},
  title        = {{Artificial intelligence classification of spatial CD8 + T-cell distribution on computed tomography in oropharyngeal cancer}},
  url          = {{http://dx.doi.org/10.1016/j.radonc.2026.111607}},
  doi          = {{10.1016/j.radonc.2026.111607}},
  volume       = {{221}},
  year         = {{2026}},
}