Markovian analysis of cervical cell images.

Markovian analysis is a method to measure optical texture based on gray-level transition probabilities in digitized images. Experiments are described that investigate that classification performance of parameters generated by Markovian analysis. Results using Markov texture parameters show that the selection of a Markov step size strongly affects classification error rates and the number of parameters required to achieve the maximum correct classification rates. Markov texture parameters are shown to achieve high rates of correct classification in discriminating images of normal from abnormal cervical cell nuclei.     

Automation of cell line development

An automated platform for development of high producing cell lines for biopharmaceutical production has been established in order to increase throughput and reduce development costs. The concept is based on the Cello robotic system (The Automation Partnership) and covers screening for colonies and expansion of static cultures. In this study, the glutamine synthetase expression system (Lonza Biologics) for production of therapeutic monoclonal antibodies in Chinese hamster ovary cells was used for evaluation of the automation approach. It is shown that the automated procedure is capable of producing cell lines of equal quality to the traditionally generated cell lines in terms of colony detection following transfection and distribution of IgG titer in the screening steps. In a generic fed-batch evaluation in stirred tank bioreactors, IgG titers of 4.7 and 5.0 g/L were obtained for best expressing cell lines. We have estimated that the number of completed cell line development projects can be increased up to three times using the automated process without increasing manual workload, compared to the manual process. Correlation between IgG titers obtained in early screens and titers achieved in fed-batch cultures in shake flasks was found to be poor. This further implies the benefits of utilizing a high throughput system capable of screening and expanding a high number of transfectants. Two concentrations, 56 and 75 μM, of selection agent, methionine sulphoximine (MSX), were applied to evaluate the impact on the number of colonies obtained post transfection. When applying selection medium containing 75 μM MSX, fewer low producing transfectants were obtained, compared to cell lines selected with 56 μM MSX, but an equal number of high producing cell lines were found. By using the higher MSX concentration, the number of cell line development projects run in parallel could be increased and thereby increasing the overall capacity of the automated platform process. A. Salmén and K. Lindgren contributed equally to the work.     

A selective mapping algorithm for computer analysis of voided urine cell images

One of the fundamental targets of the automated image analysis of cytologic preparations is the reduction of computer classification errors due to cells or other objects that do not lend themselves to image segmentation or that have morphologic features that may mislead the cell classification schemes. In prior work from this laboratory, the achievement of this goal was attempted by hierarchical analysis of sequential microscopic objects at high resolution. This paper reports on the successful development and implementation of an automated "selective mapping algorithm" that selects cells at low power for further analysis and eliminates a large proportion of unwanted "objects." The algorithm classifies the objects and extracts appropriate features from a 256 X 240 digital image obtained via a 10 X planachromatic objective. The five-node binary tree classifier used in this triage is described. The algorithm was trained and tested initially on 501 visually classified microscopic "objects," resulting in a correct acceptance rate of 61.3% and correct rejection rate of 81.3%. The selective mapping algorithm was subsequently integrated into the video-based image analysis system constructed at the Montefiore Medical Center for the diagnostic evaluation of sediments of voided urine. The algorithm was then tested on ten cytocentrifuge preparations for a preliminary evaluation of its performance. Up to 100 "objects" per case were selected by the algorithm for further classification by the computer at high power. Of the 810 "objects" selected by the selective mapping algorithm, 344 (42.5%) were classified by the computer at high resolution as cells of diagnostic value ("WELL" cells) and 466 were rejected.(ABSTRACT TRUNCATED AT 250 WORDS)     

Prediction of cervical neoplasia diagnosis groups. Discriminant analysis on digitized cell images

The purpose of this study was to develop discriminant analysis models for predicting cervical dysplasia/neoplasia case diagnoses using cytometric features derived from the digital image analysis of cell monolayers. The data base consisted of 925 cells from 27 cases diagnosed either as moderate dysplasia (n = 10), severe dysplasia (n = 5), carcinoma in situ (n = 8) or invasive carcinoma (n = 4) on both tissue biopsy and monolayer preparations. Cell features examined were cell diameter, nuclear diameter, nuclear mean optical density (OD), nuclear integrated OD (IOD), nuclear OD standard deviation, normalized IOD, nuclear texture and nuclear-cytoplasmic ratio. Features derived from cells visually classified as moderate dysplasia correctly predicted the case diagnosis of moderate dysplasia versus more severe disease for 85% of the cells. Prediction models using summary measures (mean and variance) derived from all visually classified abnormal cells within each case correctly separated all cases into their respective diagnostic categories. These findings suggest that dysplastic cells in a cytologic sample have features that collectively reflect the tissue diagnosis, regardless of the visual differences among the cells. Such information has potential use for diagnosis and possibly for prognosis.     

Segmentation of cervical cell images.

A major problem in the automation of cervical cytology screening is the segmentation of cell images. This paper describes various standard segmentation methods plus one which determines a segmentation threshold based on the stability of the perimeter of the cell as the threshold is varied. As well as contour, certain structural information is used to decide upon the threshold which separates cytoplasm from the background. Once the cytoplasm threshold is found, cytoplasm and nucleus are separated by simple clustering into three groups, cytoplasm, folded cytoplasm and nucleus. These techniques have been tested on 1500 cervical cells that belong to one of eight normal classes and five abnormal classes. A minimum Mahalanobis distance classifier was used to compare results. Manually thresholded cells were classified correctly 66.0% of the time for the 13 class problem and 95.2% of the time on the two (normal-abnormal) class problem. The contour tracing technique was 52.9% and 90.0% correct, respectively.     

Automated analysis of muscle fibre images

A technique for studying the distribution and size of different fibre types in muscles is proposed for automated analysis of individual fibres in optical density images from ATPase-stained muscle sections. After delineation, fibres may be classified into different histological types (1, 2A, 2B and 2C) using the measurement of their mean optical density (mOD). The densitometric measurements were obtained from three serial histological slides stained under different conditions. The delineation procedure is performed on one of the images: the resulting mask is fitted to the other images using a linear coordinate transform. Along with densitometric measurements, the lesser diameter of the fibres is computed. Both in processing and in analysis, extensive use was made of mathematical morphology tools. All software was implemented on a VICOM digital image processor, extended with a VISIOMORPH morphoprocessor board.     

Fractal and nonfractal analysis of cell images: comparison and application to neuronal dendritic arborization

 Neurons of the rat spinal cord were stained using the Golgi impregnation method. Successfully impregnated neurons from laminae II, III, and VI were subjected to fractal and nonfractal analyses. Fractal analysis was performed using length-related techniques. Since an application of fractal methods to the analysis of dendrite arbor structures requires caution, we adopted as appropriate a nonfractal method proposing a generalized power-law model with two main nonfractal parameters: (i) the anfractuosity, characterizing the degree of dendritic deviation from straight lines; and (ii) an estimate of the total length of arbor dendrites. The anfractuosity can distinguish between two sets of drawings where the fractal methods failed. We also redefine some basic concepts of fractal geometry, present the ruler-counting method, and propose a new definition of fractal dimension. Received: 5 February 2002 / Accepted: 25 June 2002 Acknowledgement. We thank Ing. Dejan Ristanović for preparing the computer program used in this study. Correspondence to: D. Ristanović (e-mail: dusan@ristanovic.com, Tel.: +381-11-3615767)     

Automatic analysis of agarose gel images.

MOTIVATION: Automatic tools to speed up routine biological processes are very much sought after in bio-medical research. Much repetitive work in molecular biology, such as allele calling in genetic analysis, can be made semi-automatic or task specific automatic by using existing techniques from computer science and signal processing. Computerized analysis is reproducible and avoids various forms of human error. Semi-automatic techniques with an interactive check on the results speed up the analysis and reduce the error. RESULTS: We have successfully implemented an image processing software package to automatically analyze agarose gel images of polymorphic DNA markers. We have obtained up to 90% accuracy for the classification of alleles in good quality images and up to 70% accuracy in average quality images. These results are obtained within a few seconds. Even after subsequent interactive checking to increase the accuracy of allele classification to 100%, the overall speed with which the data can be processed is greatly increased, compared to manual allele classification. AVAILABILITY: The IDL source code of the software is available on request from jonathan.flint@well.ox.ac.uk     

Automation of peak-tracking analysis of stepwise perturbed NMR spectra

We describe a new algorithmic approach able to automatically pick and track the NMR resonances of a large number of 2D NMR spectra acquired during a stepwise variation of a physical parameter. The method has been named Trace in Track (TinT), referring to the idea that a gaussian decomposition traces peaks within the tracks recognised through 3D mathematical morphology. It is capable of determining the evolution of the chemical shifts, intensity and linewidths of each tracked peak.The performances obtained in term of track reconstruction and correct assignment on realistic synthetic spectra were high above 90% when a noise level similar to that of experimental data were considered. TinT was applied successfully to several protein systems during a temperature ramp in isotope exchange experiments. A comparison with a state-of-the-art algorithm showed promising results for great numbers of spectra and low signal to noise ratios, when the graduality of the perturbation is appropriate. TinT can be applied to different kinds of high throughput chemical shift mapping experiments, with quasi-continuous variations, in which a quantitative automated recognition is crucial.     

A scene-segmentation method for multispectral cell images

A scene-segmentation method for two-color digitized images acquired from a Papanicolaou-stained cervical smear is proposed. The method first segments a scene into background, red cytoplasm, blue cytoplasm and nuclear regions by a pixel-wise classification and then merges the segmented regions for both types of cytoplasm into a single region. To create the minimum-distance classifier used for the pixel classification, class median vectors are selected from a two-dimensional histogram formed from the optical densities in the red and green images (scanned at 610 nm and 535 nm, respectively). Reference points defined from knowledge about the two-color images played an important role in selecting the vectors for the red and blue cytoplasm. This method was applied to 33 sets of the two-color images. The resulting segmented regions corresponded well with regions apparent to the the human observer. Three different investigations related to the method were carried out; these studies confirmed the suitability of the proposed method.     

Scintigraphic analysis, with the help of functional images]

Functional images are a new technique for analysis and visualization biological values. Each point of the organ is substitute by a functional value, representative of local uptake. This type of processing is interesting as the dynamic information gained is stored in a concentrated form, which can be easily reproduced and filed.