Segmentation of cytoplasm and nuclei of abnormal cells in cervical cytology using global and local graph cuts
Introduction
Screening by cytology is the commonest approach to prevent cervical cancer at a pre-cancerous stage [1]. However, it is known that screening of cervical cytology slides is labor intensive and mentally demanding on the cytotechnologist [2]. Automation-assisted reading (AAR) techniques have the potential to increase productivity and reduce screening errors. AAR uses automated microscopy to collect images of cervical cells, and then performs cell segmentation to quantitate cellular structures and morphology in order to extract candidate cells for targeted reading by pathologists. A large, prospective randomized trial found that although AAR increased the productivity by 60–80%, the sensitivity was reduced [3]. To improve the sensitivity, it is important to segment the abnormal cells reliably.
A variety of segmentation methods for cervical cytology have been proposed in recent years. The majority of cytoplasm segmentation used one or multiple of the following techniques: K-means [4], [5], edge detection [6], thresholding [7], [8] and active contours [5], [9]. Most of these works are designed for images of isolated cells, especially for those in the Herlev data set [11]. For segmentation in images containing multiple cells, thresholding [7], [8], [12] and level set [9], [10] techniques have been used. However, thresholding may lead to inaccuracy due to non-ideal imaging conditions, such as inconsistent staining and/or illumination and overlapping cells. The level set method is also suboptimal, due to computation cost and its tendency to locate some local extrema (e.g., inhomogeneous illumination).
For nucleus segmentation, related works can be divided into three groups: single-nucleus segmentation, multiple-nuclei segmentation, and touching-nuclei splitting. Existing single-nucleus segmentation approaches utilize contour, shape and color information by using active contour model [5], [13], parametric fitting [14] and difference maximization [4]. Nucleus segmentation for images containing multiple cells employ thresholding [9], [15], Hough transform [7], morphology (watershed) [8], [16], [17], and level set [10] techniques. Some of these methods [7], [8], [9] assume all nuclei located within the cytoplasm, as a result in that bare nuclei, which are strongly indicative of early cervical cancer, are missed. For splitting of touching-nuclei, morphological erosion [15] is a commonly used approach. An unsupervised method [18] for splitting touching nuclei is proposed by a combination of distance transform, expectation–maximization algorithm and ellipse fitting techniques. Through representing the nuclear shape by the vibrations of a spring-mass system, and learning the vibration models by active shape model, the nuclear boundary in the overlapping areas can be obtained accurately [19].
Generally, there are many cervical cells with mutual overlaps in a field-of-view (FOV) (see Fig. 1(a) as an example). Hence, a segmentation algorithm should capture the cytoplasm, multiple nuclei and touching-nuclei. Three of the aforementioned methods [7], [8], [10] can achieve all of these three tasks. However, these methods were developed to segment images, which only contain healthy cells rather than the mixture of healthy and abnormal cells. Since the size, shape and chromatin distributions of abnormal nuclei vary significantly (Fig. 1(b)), further development is needed to address typical variations encountered in a clinical setting. So far we have found only one previous study of automated segmentation of abnormal nuclei [20] and only very limited data was reported.
Segmentation of nuclei in histological images employ adaptive thresholding combined with active contour models [21]. Such automated methods are comparable with the manual delineation in segmentation accuracy. Similarly, graph cut (GC) approaches [22] are highly attractive in nucleus segmentation. The binarization of nuclei based on GC is addressed in [23] with results being more accurate than global thresholding. Prior knowledge like nucleus shape [24], manual annotation and local image features [25] can be incorporated in the GC framework to allow more robust segmentation.
In this paper, we propose to segment cervical cytoplasm globally and segment cervical nuclei locally based on GC approaches, respectively. The overall method, the outline of which is shown in Fig. 2, follows two tracks. The first track applies cytoplasm segmentation method to separate the cytoplasm from the background (upper part in Fig. 2). The second track applies nucleus binarization and touching-nuclei splitting methods to segment nuclei (lower part in Fig. 2). Specific contributions of the presented work consist of: (1) cytoplasm segmentation by using the multi-way GC [22] on the a* channel (CIE L*a*b* model in Ref. [26]) enhanced images (Section 2.1); (2) nucleus segmentation using a proposed “Local Adaptive GC” (LAGC) method which results in robust binarization of nuclei with a variety of morphologies, chromatin distributions and low contrasts (Section 2.2); (3) a splitting method for touching-nuclei by combining two concave points-based methods [27], [28] (Section 2.3).
Section snippets
Cytoplasm segmentation
Given a cervical cell image, the a* channel in CIE LAB color space is used for preprocessing. Initial segments are generated automatically by using Otsu's multiple thresholding algorithm [29] on the preprocessed image. The segmentation is refined by a multi-way GC method. In the rest of this section, we introduce the details of our cytoplasm segmentation.
Clinical data collection
All images used in this study were acquired using an Olympus BX41 microscope equipped with 20× objective (Olympus America, Inc., Central Valley, PA), Jenoptik ProgRes CF Color 1.4 Megapixel Camera (Jenoptik Optical Systems Inc., Jena, Germany), and MS300 motorized stage (NJRGB Inc., Nanjing, China). Image specifications were 24 bit RGB channels with resolution of 1360 × 1024 pixels.
The data set included 51 cervical cell images from 21 cervical slides, which were collected from the Department of
Parameters tuning
Our methods were implemented using C++ on a 64-bit Windows PC, which has a 2.66 GHz quad-core CPU and 4 GB of RAM. In our method, there are two major parameters that we tuned on training images. The cluster number in the global GC was tuned on 30 training images. We set it to 3, 4, 5, and 6, respectively, The resultant cytoplasm segmentation accuracy of DSC was 0.89, 0.93, 0.93, and 0.91, respectively. The sσ in the LAGC was tuned on 30 nuclei images. We varied the value of sσ (3, 5, 10, 15). The
Conclusion
To the best of our knowledge, this paper is the first attempt to achieve automated segmentation of both healthy and abnormal cervical cells in a FOV, given existing techniques more often designed for healthy cells and ideal imaging conditions. The proposed global GC method allows for cytoplasm delineation even when image histograms present non-bimodal distribution. The proposed LAGC approach and concave points-based method enable the nucleus segmentation in images with pathology and overlapping
Acknowledgements
The authors would like to thank Jingli Li, Shuangming Zheng, and Sheng Tang at the Shenzhen Microprofit Electronic Co. Ltd., for their participation in this work; Milan Sonka, Andreas Wahle, Li Zhang, and Junjie Bai from the University of Iowa, for their contributions to the manuscript revision and English writing. This work was supported by the Key Program of National Natural Science Foundation of China (Grant Number: 61031003), and the National Natural Science Foundation of China (Grant
References (46)
Automated screening of cervical cytology specimens
Hum Pathol
(1996)- et al.
Nucleus and cytoplast contour detector of cervical smear image
Pattern Recogn Lett
(2008) - et al.
Cytoplasm and nucleus segmentation in cervical smear images using Radiating GVF Snake
Pattern Recogn
(2012) - et al.
Segmentation of cervical cell nuclei in high-resolution microscopic images: a new algorithm and a web-based software framework
Comput Method Prog Biol
(2012) - et al.
Unsupervised segmentation and classification of cervical cell images
Pattern Recogn
(2012) - et al.
Unsupervised cell nucleus segmentation with active contours
Signal Process
(1998) - et al.
Combining shape, texture and intensity features for cell nuclei extraction in Pap smear images
Pattern Recogn Lett
(2011) - et al.
A survey of thresholding techniques
Comput Vis Graph Image Process
(1988) - et al.
Adaptive document binarization
Pattern Recogn
(2000) - et al.
Pap smear diagnosis using a hybrid intelligent scheme focusing on genetic algorithm based feature selection and nearest neighbour classification
Comput Biol Med
(2009)