Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer

Frederik Wessels, Max Schmitt, Eva Krieghoff-Henning, Tanja Jutzi, Thomas S. Worst, Frank Waldbillig, Manuel Neuberger, Roman C. Maron, Matthias Steeg, Timo Gaiser, Achim Hekler, Jochen S. Utikal, Christof von Kalle, Stefan Fröhling, Maurice S. Michel, Philipp Nuhn, Titus J. Brinker*

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

51 Citations (Scopus)

Abstract

Objective: To develop a new digital biomarker based on the analysis of primary tumour tissue by a convolutional neural network (CNN) to predict lymph node metastasis (LNM) in a cohort matched for already established risk factors. Patients and Methods: Haematoxylin and eosin (H&E) stained primary tumour slides from 218 patients (102 N+; 116 N0), matched for Gleason score, tumour size, venous invasion, perineural invasion and age, who underwent radical prostatectomy were selected to train a CNN and evaluate its ability to predict LN status. Results: With 10 models trained with the same data, a mean area under the receiver operating characteristic curve (AUROC) of 0.68 (95% confidence interval [CI] 0.678–0.682) and a mean balanced accuracy of 61.37% (95% CI 60.05–62.69%) was achieved. The mean sensitivity and specificity was 53.09% (95% CI 49.77–56.41%) and 69.65% (95% CI 68.21–71.1%), respectively. These results were confirmed via cross-validation. The probability score for LNM prediction was significantly higher on image sections from N+ samples (mean [SD] N+ probability score 0.58 [0.17] vs 0.47 [0.15] N0 probability score, P = 0.002). In multivariable analysis, the probability score of the CNN (odds ratio [OR] 1.04 per percentage probability, 95% CI 1.02–1.08; P = 0.04) and lymphovascular invasion (OR 11.73, 95% CI 3.96–35.7; P < 0.001) proved to be independent predictors for LNM. Conclusion: In our present study, CNN-based image analyses showed promising results as a potential novel low-cost method to extract relevant prognostic information directly from H&E histology to predict the LN status of patients with prostate cancer. Our ubiquitously available technique might contribute to an improved LN status prediction.

Original languageEnglish
Pages (from-to)352-360
Number of pages9
JournalBJU International
Volume128
Issue number3
DOIs
Publication statusPublished - Sept 2021
Externally publishedYes

Keywords

  • #PCSM
  • #ProstateCancer
  • #uroonc
  • artificial intelligence
  • convolutional neural network
  • deep learning
  • machine learning
  • neoplasm metastasis
  • prostatic neoplasms

Fingerprint

Dive into the research topics of 'Deep learning approach to predict lymph node metastasis directly from primary tumour histology in prostate cancer'. Together they form a unique fingerprint.

Cite this