Skip to content

Research at St Andrews

Automated detection and classification of desmoplastic reaction at the colorectal tumour front using deep learning

Research output: Contribution to journalArticlepeer-review

Author(s)

Ines P. Nearchou, Hideki Ueno, Yoshiki Kajiwara, Kate Lillard, Satsuki Mochizuki, Kengo Takeuchi, David J. Harrison, Peter D. Caie

School/Research organisations

Abstract

The categorisation of desmoplastic reaction (DR) present at the colorectal cancer (CRC) invasive front into mature, intermediate or immature type has been previously shown to have high prognostic significance. However, the lack of an objective and reproducible assessment methodology for the assessment of DR has been a major hurdle to its clinical translation. In this study, a deep learning algorithm was trained to automatically classify immature DR on haematoxylin and eosin digitised slides of stage II and III CRC cases (n = 41). When assessing the classifier’s performance on a test set of patient samples (n = 40), a Dice score of 0.87 for the segmentation of myxoid stroma was reported. The classifier was then applied to the full cohort of 528 stage II and III CRC cases, which was then divided into a training (n = 396) and a test set (n = 132). Automatically classed DR was shown to have superior prognostic significance over the manually classed DR in both the training and test cohorts. The findings demonstrated that deep learning algorithms could be applied to assist pathologists in the detection and classification of DR in CRC in an objective, standardised and reproducible manner.
Close

Details

Original languageEnglish
Article number1615
JournalCancers
Volume13
Issue number7
DOIs
Publication statusPublished - 31 Mar 2021

    Research areas

  • Deep learning, Image analysis, Desmoplastic reaction, Colorectal cancer, Digital pathology

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Assessment of immunological features in muscle-invasive bladder cancer prognosis using ensemble learning

    Gavriel, C., Dimitriou, N., Brieu, N., Nearchou, I. P., Arandelovic, O., Schmidt, G., Harrison, D. J. & Caie, P. D., 1 Apr 2021, In: Cancers. 13, 7, 1624.

    Research output: Contribution to journalArticlepeer-review

  2. Spatial immune profiling of the colorectal tumor microenvironment predicts good outcome in stage II patients

    Nearchou, I. P., Gwyther, B. M., Georgiakakis, E. C. T., Gavriel, C., Lillard, K., Kajiwara, Y., Ueno, H., Harrison, D. J. & Caie, P. D., 15 May 2020, In: npj Digital Medicine. 3, 10 p., 71.

    Research output: Contribution to journalArticlepeer-review

  3. Spatial Relationships Between Immune Infiltrate and Tumour Buds Improves Prognostic Accuracy in Stage II Colorectal Cancer

    Nearchou, I. P., Gavriel, C., Harrison, D. J. & Caie, P. D., Sep 2019, p. S1-S59.

    Research output: Contribution to conferencePaperpeer-review

Related by journal

  1. Cancers (Journal)

    Paul Andrew Reynolds (Member of editorial board)

    30 Sep 2020

    Activity: Publication peer-review and editorial work typesPeer review of manuscripts

Related by journal

  1. Assessment of immunological features in muscle-invasive bladder cancer prognosis using ensemble learning

    Gavriel, C., Dimitriou, N., Brieu, N., Nearchou, I. P., Arandelovic, O., Schmidt, G., Harrison, D. J. & Caie, P. D., 1 Apr 2021, In: Cancers. 13, 7, 1624.

    Research output: Contribution to journalArticlepeer-review

  2. Apoptosis and DNA methylation

    Meng, H. X., Hackett, J. A., Nestor, C., Dunican, D. S., Madej, M., Reddington, J. P., Pennings, S., Harrison, D. J. & Meehan, R. R., 1 Apr 2011, In: Cancers. 3, 2, p. 1798-1820 23 p.

    Research output: Contribution to journalArticlepeer-review

ID: 273498525

Top