Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images
Graphical abstract
Introduction
Current manual assessment of Haematoxylin and Eosin (H&E) stained histology slides suffers from low throughput and is naturally prone to intra- and inter-observer variability (Elmore et al., 2015). To overcome the difficulty in visual assessment of tissue slides, there is a growing interest in digital pathology (DP), where digitised whole-slide images (WSIs) are acquired from glass histology slides using a scanning device. This permits efficient processing, analysis and management of the tissue specimens (Madabhushi and Lee, 2016). Each WSI contains tens of thousands of nuclei of various types, which can be further analysed in a systematic manner and used for predicting clinical outcome. Here, the type of nucleus refers to the cell type in which it is located. For example, nuclear features can be used to predict survival (Alsubaie et al., 2018) and also for diagnosing the grade and type of disease (Lu et al., 2018). Also, efficient and accurate detection and segmentation of nuclei can facilitate good quality tissue segmentation (Sirinukunwattana, Snead, Epstein, Aftab, Mujeeb, Tsang, Cree, Rajpoot, 2018, Javed, Fraz, Epstein, Snead, Rajpoot, 2018), which can in turn not only facilitate the quantification of WSIs but may also serve as an important step in understanding how each tissue component contributes to disease. In order to use nuclear features for downstream analysis within computational pathology, nuclear segmentation must be carried out as an initial step. However, this remains a challenge because nuclei display a high level of heterogeneity and there is significant inter- and intra-instance variability in the shape, size and chromatin pattern between and within different cell types, disease types or even from one region to another within a single tissue sample. Tumour nuclei, in particular, tend to be present in clusters, which gives rise to many overlapping instances, providing a further challenge for automated segmentation, due to the difficulty of separating neighbouring instances.
As well as extracting each individual nucleus, determining the type of each nucleus can increase the diagnostic potential of current DP pipelines. For example, accurately classifying each nucleus to be from tumour or lymphocyte enables downstream analysis of tumour infiltrating lymphocytes (TILs), which have been shown to be predictive of cancer recurrence (Corredor et al., 2019). Yet, similar to nuclear segmentation, classifying the type of each nucleus is difficult, due to the high variance of nuclear appearance within each WSI. Typically, nuclei are classified using two disjoint models: one for detecting each nucleus and then another for performing nuclear classification (Sharma, Zerbe, Heim, Wienert, Behrens, Hellwich, Hufnagl, 2015, Wang, Hu, Li, Liu, Zhu, 2016). However, it would be preferable to utilise a single unified model for nuclear instance segmentation and classification.
In this paper, we present a deep learning approach3 for simultaneous segmentation and classification of nuclear instances in histology images. The network is based on the prediction of horizontal and vertical distances (and hence the name HoVer-Net) of nuclear pixels to their centres of mass, which are subsequently leveraged to separate clustered nuclei. For each segmented instance, the nuclear type is subsequently determined via a dedicated up-sampling branch. To the best of our knowledge, this is the first approach that achieves instance segmentation and classification within the same network. We present comparative results on six independent multi-tissue histology image datasets and demonstrate state-of-the-art performance compared to other recently proposed methods. The main contributions of this work are listed as follows:
- •
A novel network, targeted at simultaneous segmentation and classification of nuclei, where horizontal and vertical distance map predictions separate clustered nuclei.
- •
We show that the proposed HoVer-Net achieves state-of-the-art performance on multiple H&E histology image datasets, as compared to over a dozen recently published methods.
- •
An interpretable and reliable evaluation framework that effectively quantifies nuclear segmentation performance and overcomes the limitations of existing performance measures.
- •
A new dataset4 of 24,319 exhaustively annotated nuclei within 41 colorectal adenocarcinoma image tiles.
Section snippets
Nuclear instance segmentation
Within the current literature, energy-based methods, in particular the watershed algorithm, have been widely utilised to segment nuclear instances. For example, Yang et al. (2006) used thresholding to obtain the markers and the energy landscape as input for watershed to extract the nuclear instances. Nonetheless, thresholding relies on a consistent difference in intensity between the nuclei and background, which does not hold for more complex images and hence often produces unreliable results.
Methods
Our overall framework for automatic nuclear instance segmentation and classification can be observed in Fig. 1 and the proposed network in Fig. 2. Here, nuclear pixels are first detected and then, a tailored post-processing pipeline is used to simultaneously segment nuclear instances and obtain the corresponding nuclear types. The framework is based upon the horizontal and vertical distance maps, which can be seen in Fig. 3. In the figure, each nuclear pixel denotes either the horizontal or
Nuclear instance segmentation evaluation
Assessment and comparison of different methods is usually given by an overall score that indicates which method is superior. However, to further investigate the method, it is preferable to break the problem into sub-tasks and measure the performance of the method on each sub-task. This enables an in depth analysis, thus facilitating a comprehensive understanding of the approach, which can help drive forward model development. For nuclear instance segmentation, the problem can be divided into
Datasets
As part of this work, we introduce a new dataset that we term as the colorectal nuclear segmentation and phenotypes (CoNSeP) dataset,6 consisting of 41 H&E stained image tiles, each of size 1000 × 1000 pixels at 40 × objective magnification. Images were extracted from 16 colorectal adenocarcinoma (CRA) WSIs, each belonging to an individual patient, and scanned with an Omnyx VL120 scanner within the department
Discussion and conclusions
Analysis of nuclei in large-scale histopathology images is an important step towards automated downstream analysis for diagnosis and prognosis of cancer. Nuclear features have been often used to assess the degree of malignancy (Gurcan et al., 2009). However, visual analysis of nuclei is a very time consuming task because there are often tens of thousands of nuclei within a given whole-slide image (WSI). Performing simultaneous nuclear instance segmentation and classification enables subsequent
Declaration of Competing Interest
The authors confirm that there are no conflicts of interest.
Acknowledgements
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. 2016R1C1B2012433) and by the Ministry of Science and ICT (MSIT) (No. 2018K1A3A1A74065728). We also acknowledge the financial support from EPSRC and MRC, provided as part of the Mathematics for Real-World Systems CDT. We thank Peter Naylor for his assistance in the implementation of the DIST network.
References (45)
- et al.
Segmentation of neuronal nuclei based on clump splitting and a two-step binarization of images
Expert Syst. Appl.
(2013) - et al.
A survey on deep learning in medical image analysis
Med. Image Anal.
(2017) - et al.
Nuclear shape and orientation features from h&e images predict survival in early-stage estrogen receptor-positive breast cancers
Lab. Investig.
(2018) - et al.
Segmentation of nuclei in histopathology images by deep regression of the distance map
IEEE Trans. Med. Imaging
(2018) - et al.
Prostate cancer detection: fusion of cytological and textural features
J. Pathol. Inform.
(2011) - et al.
Quantitative image analysis of cellular heterogeneity in breast tumors complements genomic profiling
Sci. Transl. Med.
(2012) - et al.
Tensorflow: a system for large-scale machine learning.
OSDI
(2016) - et al.
An integrated region-, boundary-, shape-based active contour for multiple object overlap resolution in histological imagery
IEEE Trans. Med. Imaging
(2012) - et al.
A bottom-up approach for tumour differentiation in whole slide images of lung adenocarcinoma
Medical Imaging 2018: Digital Pathology
(2018) - et al.
On the robustness of semantic segmentation models to adversarial attacks
CoRR
(2017)
Segnet: a deep convolutional encoder-decoder architecture for image segmentation
IEEE Trans. Pattern Anal. Mach. Intell.
Qupath: open source software for digital pathology image analysis
Sci. Rep.
Cellprofiler: image analysis software for identifying and quantifying cell phenotypes
Genome Biol.
Dcan: deep contour-aware networks for accurate gland segmentation
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Segmentation of clustered nuclei with shape markers and marking function
IEEE Trans. Biomed. Eng.
Spatial architecture and arrangement of tumor-infiltrating lymphocytes for predicting likelihood of recurrence in early-stage non–small cell lung cancer
Clin. Cancer Res.
ImageNet: a large-scale hierarchical image database
CVPR09
Diagnostic concordance among pathologists interpreting breast biopsy specimens
JAMA
Sams-net: stain-aware multi-scale network for instance-based nuclei segmentation in histology images
Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on
Histopathological image analysis: a review
IEEE reviews in biomedical engineering
Cited by (738)
Computational pathology: A survey review and the way forward
2024, Journal of Pathology InformaticsPublicly available datasets of breast histopathology H&E whole-slide images: A scoping review
2024, Journal of Pathology InformaticsImproving generalization capability of deep learning-based nuclei instance segmentation by non-deterministic train time and deterministic test time stain normalization
2024, Computational and Structural Biotechnology JournalBUA-Net: Boundary and uncertainty-aware attention network for lumbar multi-region magnetic resonance imaging segmentation
2024, Biomedical Signal Processing and ControlSimultaneously segmenting and classifying cell nuclei by using multi-task learning in multiplex immunohistochemical tissue microarray sections
2024, Biomedical Signal Processing and ControlMulti-task global optimization-based method for vascular landmark detection
2024, Computerized Medical Imaging and Graphics