Next Article in Journal
Vibration Characteristics of Rolling Element Bearings with Different Radial Clearances for Condition Monitoring of Wind Turbine
Next Article in Special Issue
Neighborhood Singular Value Decomposition Filter and Application in Adaptive Beamforming for Coherent Plane-Wave Compounding
Previous Article in Journal
Ballasted Track Status Evaluation Based on Apparent Track Stiffness Index
Open AccessFeature PaperArticle

Weakly-Supervised Classification of HER2 Expression in Breast Cancer Haematoxylin and Eosin Stained Slides

1
INESC TEC, 4200-465 Porto, Portugal
2
Faculty of Engineering (FEUP), University of Porto, 4200-465 Porto, Portugal
3
Anatomic Pathology Service, Champalimaud Clinical Centre, Champalimaud Foundation, 1400-038 Lisbon, Portugal
4
Breast Unit, Champalimaud Clinical Centre, Champalimaud Foundation, 1400-038 Lisbon, Portugal
5
NOVA Medical School, 1169-056 Lisbon, Portugal
6
Faculty of Sciences (FCUP), University of Porto, 4169-007 Porto, Portugal
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(14), 4728; https://doi.org/10.3390/app10144728
Received: 3 June 2020 / Revised: 21 June 2020 / Accepted: 1 July 2020 / Published: 9 July 2020
(This article belongs to the Special Issue Medical Imaging and Analysis)
Human epidermal growth factor receptor 2 (HER2) evaluation commonly requires immunohistochemistry (IHC) tests on breast cancer tissue, in addition to the standard haematoxylin and eosin (H&E) staining tests. Additional costs and time spent on further testing might be avoided if HER2 overexpression could be effectively inferred from H&E stained slides, as a preliminary indication of the IHC result. In this paper, we propose the first method that aims to achieve this goal. The proposed method is based on multiple instance learning (MIL), using a convolutional neural network (CNN) that separately processes H&E stained slide tiles and outputs an IHC label. This CNN is pretrained on IHC stained slide tiles but does not use these data during inference/testing. H&E tiles are extracted from invasive tumour areas segmented with the HASHI algorithm. The individual tile labels are then combined to obtain a single label for the whole slide. The network was trained on slides from the HER2 Scoring Contest dataset (HER2SC) and tested on two disjoint subsets of slides from the HER2SC database and the TCGA-TCIA-BRCA (BRCA) collection. The proposed method attained 83.3 % classification accuracy on the HER2SC test set and 53.8 % on the BRCA test set. Although further efforts should be devoted to achieving improved performance, the obtained results are promising, suggesting that it is possible to perform HER2 overexpression classification on H&E stained tissue slides. View Full-Text
Keywords: weakly-supervised learning; HER2; breast cancer weakly-supervised learning; HER2; breast cancer
Show Figures

Figure 1

MDPI and ACS Style

Oliveira, S.P.; Ribeiro Pinto, J.; Gonçalves, T.; Canas-Marques, R.; Cardoso, M.-J.; Oliveira, H.P.; Cardoso, J.S. Weakly-Supervised Classification of HER2 Expression in Breast Cancer Haematoxylin and Eosin Stained Slides. Appl. Sci. 2020, 10, 4728.

AMA Style

Oliveira SP, Ribeiro Pinto J, Gonçalves T, Canas-Marques R, Cardoso M-J, Oliveira HP, Cardoso JS. Weakly-Supervised Classification of HER2 Expression in Breast Cancer Haematoxylin and Eosin Stained Slides. Applied Sciences. 2020; 10(14):4728.

Chicago/Turabian Style

Oliveira, Sara P.; Ribeiro Pinto, João; Gonçalves, Tiago; Canas-Marques, Rita; Cardoso, Maria-João; Oliveira, Hélder P.; Cardoso, Jaime S. 2020. "Weakly-Supervised Classification of HER2 Expression in Breast Cancer Haematoxylin and Eosin Stained Slides" Appl. Sci. 10, no. 14: 4728.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop