Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information

Wang, Yinxi ; Ali, Maya Alsheh ; Vallon-Christersson, Johan LU orcid ; Humphreys, Keith ; Hartman, Johan and Rantalainen, Mattias (2023) In European Journal of Cancer 191.
Abstract

Background: Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer. Methods: Deep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic... (More)

Background: Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer. Methods: Deep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic score to dichotomise patients into Deep-ITH low- and high-risk groups was established using an elastic-net regularised Cox proportional hazards model (recurrence-free survival). Prognostic performance was evaluated in two independent data sets: SöS-BC-1 (N = 1358) and SCAN-B-Lund (N = 1262). Results: We observed an increase in risk of recurrence in the high-risk group with hazard ratio (HR) 2.11 (95%CI:1.22–3.60; p = 0.007) using nested cross-validation. Subgroup analyses confirmed the prognostic performance in oestrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, grade 3, and large tumour subgroups. The prognostic value was confirmed in the independent SöS-BC-1 cohort (HR = 1.84; 95%CI:1.03–3.3; p = 3.99 × 10−2). In the other external cohort, significant HR was observed in the subgroup of histological grade 2 patients, as well as in the subgroup of patients with small tumours (<20 mm). Conclusion: We developed a novel method for an automated, scalable, and cost-efficient measure of ITH from WSIs that provides independent prognostic value for breast cancer. Significance: Transcriptional ITH predicted by deep learning models enables prediction of patient survival from routine histopathology WSIs in breast cancer.

(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
keywords
Breast cancer, Deep learning, Histopathology, Intra-tumour heterogeneity, Prognosis
in
European Journal of Cancer
volume
191
article number
112953
publisher
Elsevier
external identifiers
  • pmid:37494846
  • scopus:85165516272
ISSN
0959-8049
DOI
10.1016/j.ejca.2023.112953
language
English
LU publication?
yes
id
8e86e561-f538-457a-90cf-caf64baded06
date added to LUP
2023-08-30 14:37:28
date last changed
2024-04-20 03:16:37
@article{8e86e561-f538-457a-90cf-caf64baded06,
  abstract     = {{<p>Background: Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer. Methods: Deep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic score to dichotomise patients into Deep-ITH low- and high-risk groups was established using an elastic-net regularised Cox proportional hazards model (recurrence-free survival). Prognostic performance was evaluated in two independent data sets: SöS-BC-1 (N = 1358) and SCAN-B-Lund (N = 1262). Results: We observed an increase in risk of recurrence in the high-risk group with hazard ratio (HR) 2.11 (95%CI:1.22–3.60; p = 0.007) using nested cross-validation. Subgroup analyses confirmed the prognostic performance in oestrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, grade 3, and large tumour subgroups. The prognostic value was confirmed in the independent SöS-BC-1 cohort (HR = 1.84; 95%CI:1.03–3.3; p = 3.99 × 10<sup>−2</sup>). In the other external cohort, significant HR was observed in the subgroup of histological grade 2 patients, as well as in the subgroup of patients with small tumours (&lt;20 mm). Conclusion: We developed a novel method for an automated, scalable, and cost-efficient measure of ITH from WSIs that provides independent prognostic value for breast cancer. Significance: Transcriptional ITH predicted by deep learning models enables prediction of patient survival from routine histopathology WSIs in breast cancer.</p>}},
  author       = {{Wang, Yinxi and Ali, Maya Alsheh and Vallon-Christersson, Johan and Humphreys, Keith and Hartman, Johan and Rantalainen, Mattias}},
  issn         = {{0959-8049}},
  keywords     = {{Breast cancer; Deep learning; Histopathology; Intra-tumour heterogeneity; Prognosis}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{European Journal of Cancer}},
  title        = {{Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information}},
  url          = {{http://dx.doi.org/10.1016/j.ejca.2023.112953}},
  doi          = {{10.1016/j.ejca.2023.112953}},
  volume       = {{191}},
  year         = {{2023}},
}