Segmenting cervical epithelial nuclei from confocal images Gaussian Markov random fields

Luck, B.; Bovik, Alan C.; Richards‐Kortum, Rebecca

doi:10.1109/icip.2003.1246870

Cited by 5 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11 We used a segmentation algorithm to automatically segment cell nuclei within each image. 12 The segmentation algorithm correctly identifies 90% of nuclei present, with a false positive error rate of 14% compared to hand segmentation. The algorithm is described in detail in Ref.…”

Section: Image Processingmentioning

confidence: 99%

See 1 more Smart Citation

Real-time reflectance confocal microscopy: comparison of two-dimensional images and three-dimensional image stacks for detection of cervical precancer

et al. 2007

View full text Add to dashboard Cite

Confocal microscopy can provide real-time, 2-D and 3-D images of the cellular morphology and tissue architecture features that pathologists use to detect precancerous lesions without the need for tissue removal, sectioning, and staining. The utility of 3-D confocal image stacks of epithelial tissue for detecting dysplasia has not yet been explored. We aim to extract morphometry and tissue architecture information from 2-D confocal reflectance images and 3-D image stacks from fresh, unstained cervical biopsies and compare their potential for detecting dysplasia. Nine biopsies are obtained from eight patients; confocal images are acquired pre- and postacetic acid at multiple epithelial depths in 1.5 mum-intervals. Postacetic acid images are processed to segment cell nuclei; after segmentation, 2-D images taken at 50 mum below the tissue surface, and the entire 3-D image stacks are processed to extract morphological and architectural features. Data are analyzed to determine which features gave the best separation between normal and high-grade cervical precancer. Most significant differences are obtained from parameters extracted from the 3-D image stacks. However, in all cases where the 2-D features were multiplicatively scaled by the depth of acquisition divided by the epithelial thickness or scaled by the scattering coefficient, the significance level is equal to or greater than the comparable feature extracted from the 3-D image stacks. A linear discriminant function previously developed to separate 19 samples of normal tissue and high-grade cervical precancer based on the nuclear-to-cytoplasm (N/C) ratio and epithelial scattering coefficient is prospectively applied to the nine biopsies examined to determine the accuracy with which it could separate normal tissue from cervical intra epithelial neoplasia (CIN) 23. For the entire data set of 28 biopsies, a sensitivity and specificity of 100% is produced using this discriminant function; the scattering coefficient provides more discriminative capacity than the N/C ratio. The success of the scaled 2-D image features has important implications for using confocal microscopy to detect precancer in the clinic. Acquisition of the epithelial thickness or scattering coefficient requires less time than 3-D image sets and little additional effort is required to gain the added information compared to 2-D images alone.

show abstract

Section: Image Processingmentioning

confidence: 99%

“…The algorithm is described in detail in Ref. 12. First, a nonlinear edgepreserving image filtering technique-anisotropic median diffusion-was used to increase the signal-to-background ratio.…”

Section: Image Processingmentioning

confidence: 99%

Real-time reflectance confocal microscopy: comparison of two-dimensional images and three-dimensional image stacks for detection of cervical precancer

et al. 2007

View full text Add to dashboard Cite

show abstract

“…At each image depth, the mean gray-scale intensity was measured from each image. We used a segmentation algorithm to automatically segment cell nuclei within each image, 46 and we extracted the mean reflectance intensity from all segmented nuclei as a function of depth. The segmentation algorithm has a sensitivity of 90% with a false positive error rate of 14% compared with hand segmentation.…”

Section: Image Processingmentioning

confidence: 99%

“…The algorithm is described in detail in Ref. 46. Briefly, as a first processing step, we employed a powerful nonlinear edge-preserving image filtering techniqueanisotropic median diffusion-to increase the signalto-background ratio.…”

Section: Image Processingmentioning

confidence: 99%

Sources of scattering in cervical tissue: determination of the scattering coefficient by confocal microscopy

et al. 2005

View full text Add to dashboard Cite

Most models of light propagation through tissue assume that the scattering properties of various tissue layers are the same. We present evidence that the scattering coefficient of cervical epithelium varies by a factor of 3 within the epithelium owing to variations in nuclear density and to the presence of keratin. We estimated the scattering coefficient from regions of normal and precancerous cervical epithelium by fitting reflectance measurements from confocal images to an exponential function of depth based on Beer's law of attenuation. The results suggest that the normal cervix is characterized by highly variable scattering in the superficial epithelium, low scattering in the intermediate epithelium, and high scattering in the basal and stromal regions. In high-grade dysplasia, high scattering from high-density nuclei is observed throughout the entire epithelium.

show abstract

“…The filtering method that is used in this study is the median filter. A number of studies apply the median filter method in the pre-processing process to medical images [13,[27][28]. The median filter sorts the values (according to the brightness or intensity) of each neighbouring pixel in ascending order [1,13].…”

Section: Image Pre-processingmentioning

confidence: 99%

Computer aided decision support system for cervical cancer classification

et al. 2012

View full text Add to dashboard Cite

Conventional analysis of a cervical histology image, such a pap smear or a biopsy sample, is performed by an expert pathologist manually. This involves inspecting the sample for cellular level abnormalities and determining the spread of the abnormalities. Cancer is graded based on the spread of the abnormal cells. This is a tedious, subjective and timeconsuming process with considerable variations in diagnosis between the experts. This paper presents a computer aided decision support system (CADSS) tool to help the pathologists in their examination of the cervical cancer biopsies. The main aim of the proposed CADSS system is to identify abnormalities and quantify cancer grading in a systematic and repeatable manner. The paper proposes three different methods which presents and compares the results using 475 images of cervical biopsies which include normal, three stages of pre cancer, and malignant cases. This paper will explore various components of an effective CADSS; image acquisition, pre-processing, segmentation, feature extraction, classification, grading and disease identification. Cervical histological images are captured using a digital microscope. The images are captured in sufficient resolution to retain enough information for effective classification. Histology images of cervical biopsies consist of three major sections; background, stroma and squamous epithelium. Most diagnostic information are contained within the epithelium region. This paper will present two levels of segmentations; global (macro) and local (micro). At the global level the squamous epithelium is separated from the background and stroma. At the local or cellular level, the nuclei and cytoplasm are segmented for further analysis. Image features that influence the pathologists' decision during the analysis and classification of a cervical biopsy are the nuclei's shape and spread; the ratio of the areas of nuclei and cytoplasm as well as the texture and spread of the abnormalities. Similar features are extracted towards the automated classification process. This paper will present various feature extraction methods including colour, shape and texture using Gabor wavelet as well as various quantative metrics. Generated features are used to classify cells or regions into normal and abnormal categories. Following the classification process, the cancer is graded based on the spread of the abnormal cells. This paper will present the results of the grading process with five stages of the cancer spectrum. ABSTRACTConventional analysis of a cervical histology image, such a pap smear or a biopsy sample, is performed by an expert pathologist manually. This involves inspecting the sample for cellular level abnormalities and determining the spread of the abnormalities. Cancer is graded based on the spread of the abnormal cells. This is a tedious, subjective and timeconsuming process with considerable variations in diagnosis between the experts. This paper presents a computer aided decision support system (CADSS) tool to help the patholo...

show abstract

Segmenting cervical epithelial nuclei from confocal images Gaussian Markov random fields

Cited by 5 publications

References 7 publications

Real-time reflectance confocal microscopy: comparison of two-dimensional images and three-dimensional image stacks for detection of cervical precancer

Real-time reflectance confocal microscopy: comparison of two-dimensional images and three-dimensional image stacks for detection of cervical precancer

Sources of scattering in cervical tissue: determination of the scattering coefficient by confocal microscopy

Computer aided decision support system for cervical cancer classification

Contact Info

Product

Resources

About