University of Oulu

Kati Mäkelä, Mikko I. Mäyränpää, Hanna-Kaisa Sihvo, Paula Bergman, Eva Sutinen, Hely Ollila, Riitta Kaarteenaho, Marjukka Myllärniemi, Artificial intelligence identifies inflammation and confirms fibroblast foci as prognostic tissue biomarkers in idiopathic pulmonary fibrosis, Human Pathology, Volume 107, 2021, Pages 58-68, ISSN 0046-8177, https://doi.org/10.1016/j.humpath.2020.10.008

Artificial intelligence identifies inflammation and confirms fibroblast foci as prognostic tissue biomarkers in idiopathic pulmonary fibrosis

Saved in:
Author: Mäkelä, Kati1; Mäyränpää, Mikko I.2; Sihvo, Hanna-Kaisa3;
Organizations: 1Individualized Drug Therapy Research Program, Faculty of Medicine, University of Helsinki and Heart and Lung Center, Helsinki University Hospital, FI-00290, Helsinki, Finland
2Pathology, University of Helsinki and Helsinki University Hospital, FI-00290, Helsinki, Finland
3Aiforia Technologies, FI-00290, Helsinki, Finland
4Biostatistics Consulting, Department of Public Health, University of Helsinki and Helsinki University Hospital, FI-00290, Helsinki, Finland
5Research Unit of Internal Medicine, University of Oulu and Medical Research Center Oulu, Oulu University Hospital, FI-90014, Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 2 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021042211329
Language: English
Published: Elsevier, 2021
Publish Date: 2021-04-22
Description:

Summary

A large number of fibroblast foci (FF) predict mortality in idiopathic pulmonary fibrosis (IPF). Other prognostic histological markers have not been identified. Artificial intelligence (AI) offers a possibility to quantitate possible prognostic histological features in IPF. We aimed to test the use of AI in IPF lung tissue samples by quantitating FF, interstitial mononuclear inflammation, and intra-alveolar macrophages with a deep convolutional neural network (CNN). Lung tissue samples of 71 patients with IPF from the FinnishIPF registry were analyzed by an AI model developed in the Aiforia® platform. The model was trained to detect tissue, air spaces, FF, interstitial mononuclear inflammation, and intra-alveolar macrophages with 20 samples. For survival analysis, cut-point values for high and low values of histological parameters were determined with maximally selected rank statistics. Survival was analyzed using the Kaplan-Meier method. A large area of FF predicted poor prognosis in IPF (p = 0.01). High numbers of interstitial mononuclear inflammatory cells and intra-alveolar macrophages were associated with prolonged survival (p = 0.01 and p = 0.01, respectively). Of lung function values, low diffusing capacity for carbon monoxide was connected to a high density of FF (p = 0.03) and a high forced vital capacity of predicted was associated with a high intra-alveolar macrophage density (p = 0.03). The deep CNN detected histological features that are difficult to quantitate manually. Interstitial mononuclear inflammation and intra-alveolar macrophages were novel prognostic histological biomarkers in IPF. Evaluating histological features with AI provides novel information on the prognostic estimation of IPF.

see all

Series: Human pathology
ISSN: 0046-8177
ISSN-E: 1532-8392
ISSN-L: 0046-8177
Volume: 107
Pages: 58 - 68
DOI: 10.1016/j.humpath.2020.10.008
OADOI: https://oadoi.org/10.1016/j.humpath.2020.10.008
Type of Publication: A1 Journal article – refereed
Field of Science: 3121 General medicine, internal medicine and other clinical medicine
Subjects:
Copyright information: © 2020 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
  https://creativecommons.org/licenses/by-nc-nd/4.0/