H&E image analysis pipeline for quantifying morphological features

Valeria Ariotta; Oskari Lehtonen; Shams Salloum; Giulia Micoli; Kari Lavikka; Ville Rantanen; Johanna Hynninen; Anni Virtanen; Sampsa Hautaniemi

doi:10.1016/j.jpi.2023.100339

H&E image analysis pipeline for quantifying morphological features

J Pathol Inform. 2023 Oct 5:14:100339. doi: 10.1016/j.jpi.2023.100339. eCollection 2023.

Authors

Valeria Ariotta¹, Oskari Lehtonen¹, Shams Salloum^{1

2}, Giulia Micoli¹, Kari Lavikka¹, Ville Rantanen¹, Johanna Hynninen³, Anni Virtanen², Sampsa Hautaniemi¹

Affiliations

¹ Research Program in Systems Oncology, Research Programs Unit, Faculty of Medicine, University of Helsinki, 00014 Helsinki, Finland.
² Department of Pathology, University of Helsinki and HUS Diagnostic Center, Helsinki University Hospital, 00029 Helsinki, Finland.
³ Department of Obstetrics and Gynaecology, University of Turku and Turku University Hospital, 200521 Turku, Finland.

Abstract

Detecting cell types from histopathological images is essential for various digital pathology applications. However, large number of cells in whole-slide images (WSIs) necessitates automated analysis pipelines for efficient cell type detection. Herein, we present hematoxylin and eosin (H&E) Image Processing pipeline (HEIP) for automatied analysis of scanned H&E-stained slides. HEIP is a flexible and modular open-source software that performs preprocessing, instance segmentation, and nuclei feature extraction. To evaluate the performance of HEIP, we applied it to extract cell types from ovarian high-grade serous carcinoma (HGSC) patient WSIs. HEIP showed high precision in instance segmentation, particularly for neoplastic and epithelial cells. We also show that there is a significant correlation between genomic ploidy values and morphological features, such as major axis of the nucleus.

Keywords: Digital pathology; Feature extraction; Instance segmentation; Ovarian high-grade serous carcinoma; Ploidy; Whole-slide images.