Patrik Malm

Screening for Cervical Cancer Using Automated Analysis of PAP-Smears

Cervical cancer is one of the most deadly and common forms of cancer among women if no action is taken to prevent it, yet it is preventable through a simple screening test, the so-called PAP-smear. This is the most effective cancer prevention measure developed so far. But the visual examination of the smears is time consuming and expensive and there have been numerous attempts at automating the analysis ever since the test was introduced more than 60 years ago. The first commercial systems for automated analysis of the cell samples appeared around the turn of the millennium but they have had limited impact on the screening costs. In this paper we examine the key issues that need to be addressed when an automated analysis system is developed and discuss how these challenges have been met over the years. The lessons learned may be useful in the efforts to create a cost-effective screening system that could make affordable screening for cervical cancer available for all women globally, thus preventing most of the quarter million annual unnecessary deaths still caused by this disease.

Automated segmentation of free-lying cell nuclei in Pap smears for malignancy-associated change analysis

This paper presents an automated algorithm for robustly detecting and segmenting free-lying cell nuclei in bright-field microscope images of Pap smears. This is an essential initial step in the development of an automated screening system for cervical cancer based on malignancy associated change (MAC) analysis. The proposed segmentation algorithm makes use of gray-scale annular closings to identify free-lying nuclei-like objects together with marker-based watershed segmentation to accurately delineate the nuclear boundaries. The algorithm also employs artifact rejection based on size, shape, and granularity to ensure only the nuclei of intermediate squamous epithelial cells are retained. An evaluation of the performance of the algorithm relative to expert manual segmentation of 33 fields-of-view from 11 Pap smear slides is also presented. The results show that the sensitivity and specificity of nucleus detection is 94.71% and 85.30% respectively, and that the accuracy of segmentation, measured using the Dice coefficient, of the detected nuclei is 97.30±1.3%.

Papsynth: simulated bright-field images of cervical smears

In this paper, we present a simulator for bright-field microscope images of “Pap-smears”, which is the most common technique used today for cervical cancer screening. Lacking a ground truth for real images, these realistic synthetic images may be used to tune and validate image analysis and processing algorithms. We demonstrate this for two tasks: uncorrelated noise removal and nucleus segmentation. The simulator is a part of a larger project, aiming at automatic, cost efficient screening for cervical cancer in developing countries.

Closing Curves with Riemannian Dilation: Application to Segmentation in Automated Cervical Cancer Screening

In this paper, we describe a nuclei segmentation algorithm for Pap smears that uses anisotropic dilation for curve closing. Edge detection methods often return broken edges that need to be closed to achieve a proper segmentation. Our method performs dilation using Riemannian distance maps that are derived from the local structure tensor field in the image. We show that our curve closing improve the segmentation along weak edges and significantly increases the overall performance of segmentation. This is validated in a thorough study on realistic synthetic cell images from our Pap smear simulator. The algorithm is also demonstrated on bright-field microscope images of real Pap smears from cervical cancer screening.

Debris removal in Pap-smear images

Since its introduction in the 1940s the Pap-smear test has helped reduce the incidence of cervical cancer dramatically in countries where regular screening is standard. The automation of this procedure is an open problem that has been ongoing for over fifty years without reaching satisfactory results. Existing systems are discouragingly expensive and yet they are only able to make a correct distinction between normal and abnormal samples in a fraction of cases. Therefore, they are limited to acting as support for the cytotechnicians as they perform their manual screening. The main reason for the current limitations is that the automated systems struggle to overcome the complexity of the cell structures. Samples are covered in artefacts such as blood cells, overlapping and folded cells, and bacteria, that hamper the segmentation processes and generate large number of suspicious objects. The classifiers designed to differentiate between normal cells and pre-cancerous cells produce unpredictable results when classifying artefacts. In this paper, we propose a sequential classification scheme focused on removing unwanted objects, debris, from an initial segmentation result, intended to be run before the actual normal/abnormal classifier. The method has been evaluated using three separate datasets obtained from cervical samples prepared using both the standard Pap-smear approach as well as the more recent liquid based cytology sample preparation technique. We show success in removing more than 99% of the debris without loosing more than around one percent of the epithelial cells detected by the segmentation process.

Acrosome integrity assessment of boar spermatozoa images using an early fusion of texture and contour descriptors

The assessment of the state of the acrosome is a priority in artificial insemination centres since it is one of the main causes of function loss. In this work, boar spermatozoa present in gray scale images acquired with a phase-contrast microscope have been classified as acrosome-intact or acrosome-damaged, after using fluorescent images for creating the ground truth. Based on shape prior criteria combined with Otsus thresholding, regional minima and watershed transform, the spermatozoa heads were segmented and registered. One of the main novelties of this proposal is that, unlike what previous works stated, the obtained results show that the contour information of the spermatozoon head is important for improving description and classification. Other of this work novelties is that it confirms that combining different texture descriptors and contour descriptors yield the best classification rates for this problem up to date. The classification was performed with a Support Vector Machine backed by a Least Squares training algorithm and a linear kernel. Using the biggest acrosome intact-damaged dataset ever created, the early fusion approach followed provides a 0.9913 F-Score, outperforming all previous related works.

Novel chromatin texture features for the classification of pap smears

This paper presents a set of novel structural texture features for quantifying nuclear chromatin patterns in cells on a conventional Pap smear. The features are derived from an initial segmentation of the chromatin into bloblike texture primitives. The results of a comprehensive feature selection experiment, including the set of proposed structural texture features and a range of different cytology features drawn from the literature, show that two of the four top ranking features are structural texture features. They also show that a combination of structural and conventional features yields a classification performance of 0.954±0.019 (AUC±SE) for the discrimination of normal (NILM) and abnormal (LSIL and HSIL) slides. The results of a second classification experiment, using only normal-appearing cells from both normal and abnormal slides, demonstrates that a single structural texture feature measuring chromatin margination yields a classification performance of 0.815±0.019. Overall the results demonstrate the efficacy of the proposed structural approach and that it is possible to detect malignancy associated changes (MACs) in Papanicoloau stain.

Simulation of bright-field microscopy images depicting pap-smear specimen

As digital imaging is becoming a fundamental part of medical and biomedical research, the demand for computer‐based evaluation using advanced image analysis is becoming an integral part of many research projects. A common problem when developing new image analysis algorithms is the need of large datasets with ground truth on which the algorithms can be tested and optimized. Generating such datasets is often tedious and introduces subjectivity and interindividual and intraindividual variations. An alternative to manually created ground‐truth data is to generate synthetic images where the ground truth is known. The challenge then is to make the images sufficiently similar to the real ones to be useful in algorithm development. One of the first and most widely studied medical image analysis tasks is to automate screening for cervical cancer through Pap‐smear analysis. As part of an effort to develop a new generation cervical cancer screening system, we have developed a framework for the creation of realistic synthetic bright‐field microscopy images that can be used for algorithm development and benchmarking. The resulting framework has been assessed through a visual evaluation by experts with extensive experience of Pap‐smear images. The results show that images produced using our described methods are realistic enough to be mistaken for real microscopy images. The developed simulation framework is very flexible and can be modified to mimic many other types of bright‐field microscopy images.

A Structural Texture Approach for Characterising Malignancy Associated Changes in Pap Smears Based on Mean-Shift and the Watershed Transform

This paper presents a novel structural approach to quantitatively characterising nuclear chromatin texture in light microscope images of Pap smears. The approach is based on segmenting the chromatin into blob-like primitives and characterising their properties and arrangement. The segmentation approach makes use of multiple focal planes. It comprises two basic steps: (i) mean-shift filtering in the feature space formed by concatenating pixel spatial coordinates and intensity values centred around the best all-in-focus plane, and (ii) hierarchical marker-based watershed segmentation. The paper also presents an empirical evaluation of the approach based on the classification of 43 routine clinical Pap smears. Two variants of the approach were compared to a reference approach (employing extended depth-of-field rather than mean-shift) in a feature selection/classification experiment, involving 138 segmentation-based features, for discriminating normal and abnormal slides. The results demonstrate improved performance over the reference approach. The results of a second feature selection/classification experiment, including additional classes of features from the literature, show that a combination of the proposed structural and conventional features yields a classification performance of 0.919 ± 0.015 (AUC ± Std. Dev.). Overall the results demonstrate the efficacy of the proposed structural approach and confirm that it is indeed possible to detect malignancy associated changes (MACs) in conventional Papanicolaou stain.

Interrogating health-related public databases from a food toxicology perspective : Computational analysis of scoring data

Over the last 15 years, an expanding number of databases with information on noxious effects of substances on mammalian organisms and the environment have been made available on the Internet. This set of databases is a key source of information for risk assessment within several areas of toxicology. Here we present features and relationships across a relatively wide set of publicly accessible databases broadly within toxicology, in part by clustering multi-score representations of such repositories, to support risk assessment within food toxicology. For this purpose 36 databases were each scrutinized, using 18 test substances from six different categories as probes. Results have been analyzed by means of various uni- and multi-variate statistical operations. The former included a special index devised to afford context-specific rating of databases across a highly heterogeneous data matrix, whereas the latter involved cluster analysis, enabling the identification of database assemblies with overall shared characteristics. One database - HSDB - was outstanding due to rich and qualified information for most test substances, but an appreciable fraction of the interrogated repositories showed good to decent scoring. Among the six chosen substance groups, Food contact materials had the most comprehensive toxicological information, followed by the Pesticides category.