PESO: Prostate Epithelium Segmentation on H&amp;E-stained prostatectomy whole slide images

Bulten, Wouter; Bándi, Péter; Hoven, Jeffrey; Loo, Rob van de; Lotz, Johannes; Weiss, Nick; Laak, Jeroen van der; Ginneken, Bram van; Kaa, Christina Hulsbergen–van de; Litjens, Geert

doi:10.5281/zenodo.1485967

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although we do obtain the lowest score on this pattern (F1-score of 0.819), this score is still high especially given the poorly differentiated character of high Gleason grades, and the first benchmark on these grades. To allow others to compare their algorithms against ours we have decided to release our test data and H&E WSIs publicly, including both the test and training slides 23 . This dataset includes the 102 whole-slide H&E images used in this paper, all color deconvolution masks and the manually corrected regions.…”

Section: Discussionmentioning

confidence: 99%

Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard

Bulten

Bándi

Hoven

et al. 2019

Sci Rep

Self Cite

125

View full text Add to dashboard Cite

Given the importance of gland morphology in grading prostate cancer (PCa), automatically differentiating between epithelium and other tissues is an important prerequisite for the development of automated methods for detecting PCa. We propose a new deep learning method to segment epithelial tissue in digitised hematoxylin and eosin (H&E) stained prostatectomy slides using immunohistochemistry (IHC) as reference standard. We used IHC to create a precise and objective ground truth compared to manual outlining on H&E slides, especially in areas with high-grade PCa. 102 tissue sections were stained with H&E and subsequently restained with P63 and CK8/18 IHC markers to highlight epithelial structures. Afterwards each pair was co-registered. First, we trained a U-Net to segment epithelial structures in IHC using a subset of the IHC slides that were preprocessed with color deconvolution. Second, this network was applied to the remaining slides to create the reference standard used to train a second U-Net on H&E. Our system accurately segmented both intact glands and individual tumour epithelial cells. The generalisation capacity of our system is shown using an independent external dataset from a different centre. We envision this segmentation as the first part of a fully automated prostate cancer grading pipeline.

show abstract

Section: Discussionmentioning

confidence: 99%

Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard

Bulten

Bándi

Hoven

et al. 2019

Sci Rep

Self Cite

125

View full text Add to dashboard Cite

show abstract

A deep learning model to predict RNA-Seq expression of tumours from whole slide images

Schmauch¹,

Romagnoni²,

Pronier³

et al. 2020

Nat Commun

290

309

View full text Add to dashboard Cite

Deep learning methods for digital pathology analysis are an effective way to address multiple clinical questions, from diagnosis to prediction of treatment outcomes. These methods have also been used to predict gene mutations from pathology images, but no comprehensive evaluation of their potential for extracting molecular features from histology slides has yet been performed. We show that HE2RNA, a model based on the integration of multiple data modes, can be trained to systematically predict RNA-Seq profiles from whole-slide images alone, without expert annotation. Through its interpretable design, HE2RNA provides virtual spatialization of gene expression, as validated by CD3-and CD20-staining on an independent dataset. The transcriptomic representation learned by HE2RNA can also be transferred on other datasets, even of small size, to increase prediction performance for specific molecular phenotypes. We illustrate the use of this approach in clinical diagnosis purposes such as the identification of tumors with microsatellite instability.

show abstract

PESO: Prostate Epithelium Segmentation on H&E-stained prostatectomy whole slide images

Cited by 2 publications

References 0 publications

Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard

Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard

A deep learning model to predict RNA-Seq expression of tumours from whole slide images

Contact Info

Product

Resources

About