No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Segmentation of blood cell image captured by single CCD color TV camera
Abstract
This paper discusses the classification of blood cell images. The image input method using the single CCD color TV camera and the special color compensation filter, as well as the method of region segmentation for the blood cell images, are described. The following elaborations are made in the image input stage to separate the red blood cell and the white blood cell images in a stable way using optical means.
(1) The bluish green light near 450 ∼ 500 nm is cut off from the white light.
(2) The accompanying light imbalance between the blue light and the green/red light is compensated by the special color compensation filter.
In the (region) segmentation of the blood cell images, a logical operation is developed in which the region of the red blood cell is extracted based on the binary images obtained by the threshold processing of the subtracted image. Using those methods, 59 blood cell images are processed and a satisfactory segmentation result is obtained.
... Segmentation of images of peripheral blood smears is straightforward because the leukocytes are sparsely distributed. Several algorithms have been developed that yield good results (2)(3)(4)(5)(6)(7)(8)(9)(10). These algorithms are based on thresholding operations and are well-suited for images of peripheral blood samples. ...
Morphologic examination of bone marrow and peripheral blood samples continues to be the cornerstone in diagnostic hematology. In recent years, interest in automatic leukocyte classification using image analysis has increased rapidly. Such systems collect a series of images in which each cell must be segmented accurately to be classified correctly. Although segmentation algorithms have been developed for sparse cells in peripheral blood, the problem of segmenting the complex cell clusters characterizing bone marrow images is harder and has not been addressed previously.
We present a novel algorithm for segmenting clusters of any number of densely packed cells. The algorithm first oversegments the image into cell subparts. These parts are then assembled into complete cells by solving a combinatorial optimization problem in an efficient way.
Our experimental results show that the algorithm succeeds in correctly segmenting densely clustered leukocytes in bone marrow images.
The presented algorithm enables image analysis-based analysis of bone marrow samples for the first time and may also be adopted for other digital cytometric applications where separation of complex cell clusters is required.
... Segmentation of solitary leukocytes is straightforward and fairly good results can be achieved using successive thresholding operations as shown in several papers [14,2,25,24,26,5,11,6,23]. In all of these, clusters are left out of consideration. ...
Human leukocytes (white blood cells) can be divided into about
twenty subclasses and the estimation of their distribution, called
differential counting, is an important diagnostic tool in various
clinical settings. Automatic differential counters based on digital
image analysis require good segmentation algorithms to locate each cell
and the accuracy of the subsequent classification depends on the correct
segmentation of solitary cells as well as cell clusters. Previously
published segmentation algorithms mainly use various thresholding
schemes to extract the nucleus and cytoplasm of solitary cells but, so
far, no successful cluster segmentation method has been developed. In
this paper we present a model-based segmentation algorithm that uses
interface propagation models to locate nuclear segments and their
adherent cytoplasms. These segments are then assembled using a
model-based combinatorial optimization scheme. The results are very
promising and, to our knowledge, this is the first successful attempt to
solve this problem
This paper presents a high throughput screening algorithm for leukemia cells that has been designed, implemented, and tested. It performs a recursive image segmentation technique, row-wise and column-wise, on edge detected cell image. The recursive image segmentation successfully eliminates background pixels from foreground pixels by only segmenting image sections that contain relevant pixels. Then, the algorithm generates a boundary box for all identified cells. The next step of the proposed algorithm, the cluster classification, uses signature plots to classify single cells from cell clusters, and determine total cell count, size, and position. The proposed algorithm was successfully tested on various leukemia cell images. Also, when compared to manual counting using hemocytometer, the algorithm result matched the hemocytometer result. In addition, the algorithm took less than three seconds to process each image. Hence, the proposed algorithm determines relevant cell population statistics with 95% accuracy and avoids unnecessary delays in the cell screening process
A technique for the localization of cytoplasmic and nucleic material in Wrights and Wrights-Giemsa strained blood cells is described. The microscopic field of view is first scanned with three different wavelengths of light and then digitized with the aid of a microscopic/vidicon/computer. Each of the three pictures is then converted to a binary color picture by comparison with three calculated clipping levels. The three binary color pictures are then logically combined to generate ``masks'' or sets of points which correspond to 1)nucleic points in the picture, 2) cytoplasmic points in the picture, and 3)red-cell points in the picture. The algorithms involved are easy to implement either in hardware or software, and execute very rapidly in either environment.
An automatic white blood cell analyzer has been developed that consists of a computerized microscope that automatically classifies segmented neutrophils, band neutrophils, lymphocytes, monocytes, eosinophils and basophils. In operation, it also flags and counts all abnormal cells. The classification is performed using similar cellular morphological features used by cytotechnologists, such as shape, optical density, nuclear area, cytoplasm area and color. After the blood slide has been placed in a special holder between the objective and the condenser of the microscope and is brought into approximate focus, the automatic focusing system takes over and provides consistently sharp focus by automatically moving the objective in 0. 1- mu m increments over a range of 0. 5 mm in z-direction during the entire differential count. Direction and displacement for the automatic focus is controlled by means of the acuity features of the cells and subsequent differentiation. The x-y stage moves at 500 steps per sec. in 5- mu m increments across a meander pattern 300 mu m wide in search of white cells. When a white cell is acquired, the x-y stage automatically moves the cell into the center of a 20 multiplied by 20- mu m TV camera window for image processing and cell classification. The cell image is scanned with 48 lines over 20- mu m square, resulting in resolution of about 0. 4 mu m. The output of the TV camera provides an analog electrical signal of the optical image. This is digitized by an analog-to-digital converter so the optical density of each image point is represented by a single computer word. From the ″electronic image″ stored in the core memory of a general purpose digital computer, certain cell features are extracted by analyzing the histogram. After the features of a cell have been extracted, they are compared with the standard values of those cells for which the machine has been trained.
The results of an automated classification of the peripheral blood leukocytes into eight categories are presented. The classification was achieved by means of digital image processing. The categories were: small lymphocytes, medium lymphocytes, large lymphocytes, band neutrophils, segmented neutrophils, eosinophils, basophils, and monocytes. An eight-dimensional multivariate Gaussian classifier was used. The features were extracted from a 50 Ã 50 point digital image. These features were measures of such visual concepts as nuclear size, nuclear shape, nuclear and cytoplasmic texture, cytoplasm color, and cytoplasm colored texture. The data set consisted of 1041 blood cell images and were divided into a training set of 523 cells and an independent testing set of 518 cells. These cells were digitized directly from the blood smear, which was stained with Wright's stain. Twenty different blood smears were used and were collected over a three-year period from 20 people. The "true" classification of the data set was obtained from four experienced hematology technicians. Their performance was compared to the automated classifier both in terms of an absolute classification of cells and in terms of estimating the percentage composition of the population (or the blood cell differential count). The measure of performance used was the percentage error for each class. The mean percentage error for the eight classes in terms of an absolute classification was 8 and 29 percent for the human observers and the automated classiffier, respectively.
A differential white blood cell classifier is described. The system, which is based upon a three-color flying spot-scanner approach, utilizes recognition parameters based on the principle of geometrical probability functions which are generated at high speed in a dedicated computer. The result is a pattern recognition system capable of performing a routine clinical differential cell count at the rate of 100 cells/40s on a traditionally prepared specimen. The Hematrak system was evaluated in a routine clinical laboratory which reported that reproducibility, normal cell recognition accuracy, and the detection of abnormality were at least comparable to the manual technique.
The simulation of a system to perform an automated leukocyte differential has been achieved through the measurement of certain features or parameters on the cell image. Using photomicrographs on Kodachrome II-A film of Wright's stained leukocytes, four features have successfully separated five normal cell types. Using a sequential procedure based on erythrocyte color to locate the leukocyte in the field of view, statistical analysis on a set of 74 training cells yields a partitioning of the four-dimensional feature space into five distinct regions. An unknown cell may then be classified by measuring its distance to each of the five regions (clusters) via a specified metric.
Fully automated blood cell differential system and its application. ANT'88
- A Hashizume
- J Motoike
- R Yabe
Cell image processing in cell analyzer MICROX
- Miyake T.
Automatic classification of blood cell image
- Shimomae T.
Development of automatic blood cell analyzer
- Yamamoto S.
Method and apparatus utilizing color algebra for analyzing scene region
- J E Green
An automated classification of blood cells by multistage classifier. IECON'84 pp
- R Suzuki A.Hashizume
- H Matsusitaandr
- Yabe
Computer recognition of microscopic images. EASCON '75 pp
- J W Bacus
- R K Aggarwal
- . G Belanger
Segmentation of blood cell image using color information. Trans. (D‐II)
- Suzuki R.