Assessment of UK practice for management of acute childhood idiopathic thrombocytopenic purpura against published guidelines

BACKGROUND

Guidelines for management of acute immune thrombocytopenic purpura (ITP) in childhood were published in 1992. Regional audit in 1995 showed substantial variation in clinical practice not related to clinical differences in patient groups, which indicated a need for national audit.

METHODS

Individuals aged from birth to their 16th birthday newly presenting with ITP were identified over 14 months by regular mailing of paediatricians and haematologists for case notification. Information was obtained from follow-up by a detailed questionnaire.

FINDINGS

ITP was clinically mild and benign in 323 (76%) of 427 cases, including 181 (70%) of 260 cases with platelet counts below 10 x 10(9)/L. There were no deaths or intracranial haemorrhages. There was a substantial discrepancy between clinical practice and published guidelines: many children were admitted to hospital and received treatment unnecessarily; there was overuse of intravenous immunoglobulin (IVIg) as first-line therapy (94 children); children received steroids without marrow examination; and there was inappropriate use of platelet transfusions (41 with mild or moderate disease).

INTERPRETATION

Our results indicate a need for change in practice.

Three-dimensional identification of stem cells by computational holographic imaging

We present an optical imaging system and mathematical algorithms for three-dimensional sensing and identification of stem cells. Data acquisition of stem cells is based on holographic microscopy in the Fresnel domain by illuminating the cells with a laser. In this technique, the holograms of stem cells are optically recorded with an image sensor array interfaced with a computer and three-dimensional images of the stem cells are reconstructed from the Gabor-filtered digital holograms. The Gabor wavelet transformation for feature extraction of the digital hologram is performed to improve the process of identification. The inverse Fresnel transformation of the Gabor-filtered digital hologram is performed to reconstruct the multi-scale three-dimensional images of the stem cells at different depths along the longitudinal direction. For recognition and classification of stem cells, a statistical approach using an empirical cumulative density function is introduced. The experiments indicate that the proposed system can be potentially useful for recognizing and classifying stem cells. To the best of our knowledge, this is the first report on using three-dimensional holographic microscopy for automated identification of stem cells.

Non-association of estrogen receptor genotypes with bone mineral density and bone turnover in Korean pre-, peri-, and postmenopausal women

Estrogen is known to play a critical role in both skeletal maturity and the rate of bone loss. This suggests the possibility that the estrogen receptor (ER) gene is one of the candidate genes that determines peak bone density and/or bone turnover rate. We investigated two established restriction fragment length polymorphisms (RFLPs) in intron 1 at the ER gene, represented as PvuII and XbaI. In 598 healthy Korean women aged 20-74 years, we examined the association of these ER genotypes with bone mineral density (BMD) and bone turnover status. The distribution of the PvuII and XbaI RFLPs was as follows: pp 205 (34.3%), Pp 308 (51.5%), PP 85 (14.2%) and xx 384 (64.2%), Xx 180 (30.1%), XX 34 (5.7%), respectively (where capital letters signify the absence of, and lower-case letters signify the presence of, the restriction site of each RFLP). No significant genotypic differences were found in BMD and bone markers. We grouped the subjects into three categories according to their menstrual status: 104 premenopausal women with regular menstruation, 182 perimenopausal women who had amenorrhea of not less than 3 months and not more than 12 months' duration, and 312 postmenopausal women whose last menstruation was at least 12 months previously. No significant genotypic difference in either BMD or bone markers was found in any of these three groups. Furthermore we categorized women in peri- and postmenopause into a high loser group and a normal loser group according to the level of bone resorption markers. There was no difference in genotypic proportions between the high and normal loser groups. Our data suggest that these ER polymorphisms are not associated with BMD or bone turnover in Korean women.

Three-dimensional imaging and recognition of microorganism using single-exposure on-line (SEOL) digital holography

We address three-dimensional (3D) visualization and recognition of microorganisms using single-exposure on-line (SEOL) digital holography. A coherent 3D microscope-based Mach-Zehnder interferometer records a single on-line Fresnel digital hologram of microorganisms. Three-dimensional microscopic images are reconstructed numerically at different depths by an inverse Fresnel transformation. For recognition, microbiological objects are segmented by processing the background diffraction field. Gabor-based wavelets extract feature vectors with multi-oriented and multi-scaled Gabor kernels. We apply a rigid graph matching (RGM) algorithm to localize predefined shape features of biological samples. Preliminary experimental and simulation results using sphacelaria alga and tribonema aequale alga microorganisms are presented. To the best of our knowledge, this is the first report on 3D visualization and recognition of microorganisms using on-line digital holography with single-exposure.

Automated statistical quantification of three-dimensional morphology and mean corpuscular hemoglobin of multiple red blood cells

In this paper, we present an automated approach to quantify information about three-dimensional (3D) morphology, hemoglobin content and density of mature red blood cells (RBCs) using off-axis digital holographic microscopy (DHM) and statistical algorithms. The digital hologram of RBCs is recorded by a CCD camera using an off-axis interferometry setup and quantitative phase images of RBCs are obtained by a numerical reconstruction algorithm. In order to remove unnecessary parts and obtain clear targets in the reconstructed phase image with many RBCs, the marker-controlled watershed segmentation algorithm is applied to the phase image. Each RBC in the segmented phase image is three-dimensionally investigated. Characteristic properties such as projected cell surface, average phase, sphericity coefficient, mean corpuscular hemoglobin (MCH) and MCH surface density of each RBC is quantitatively measured. We experimentally demonstrate that joint statistical distributions of the characteristic parameters of RBCs can be obtained by our algorithm and efficiently used as a feature pattern to discriminate between RBC populations that differ in shape and hemoglobin content. Our study opens the possibility of automated RBC quantitative analysis suitable for the rapid classification of a large number of RBCs from an individual blood specimen, which is a fundamental step to develop a diagnostic approach based on DHM.

Cell morphology-based classification of red blood cells using holographic imaging informatics

We present methods that automatically select a linear or nonlinear classifier for red blood cell (RBC) classification by analyzing the equality of the covariance matrices in Gabor-filtered holographic images. First, the phase images of the RBCs are numerically reconstructed from their holograms, which are recorded using off-axis digital holographic microscopy (DHM). Second, each RBC is segmented using a marker-controlled watershed transform algorithm and the inner part of the RBC is identified and analyzed. Third, the Gabor wavelet transform is applied to the segmented cells to extract a series of features, which then undergo a multivariate statistical test to evaluate the equality of the covariance matrices of the different shapes of the RBCs using selected features. When these covariance matrices are not equal, a nonlinear classification scheme based on quadratic functions is applied; otherwise, a linear classification is applied. We used the stomatocyte, discocyte, and echinocyte RBC for classifier training and testing. Simulation results demonstrated that 10 of the 14 RBC features are useful in RBC classification. Experimental results also revealed that the covariance matrices of the three main RBC groups are not equal and that a nonlinear classification method has a much lower misclassification rate. The proposed automated RBC classification method has the potential for use in drug testing and the diagnosis of RBC-related diseases.

Automated segmentation of multiple red blood cells with digital holographic microscopy

We present a method to automatically segment red blood cells (RBCs) visualized by digital holographic microscopy (DHM), which is based on the marker-controlled watershed algorithm. Quantitative phase images of RBCs can be obtained by using off-axis DHM along to provide some important information about each RBC, including size, shape, volume, hemoglobin content, etc. The most important process of segmentation based on marker-controlled watershed is to perform an accurate localization of internal and external markers. Here, we first obtain the binary image via Otsu algorithm. Then, we apply morphological operations to the binary image to get the internal markers. We then apply the distance transform algorithm combined with the watershed algorithm to generate external markers based on internal markers. Finally, combining the internal and external markers, we modify the original gradient image and apply the watershed algorithm. By appropriately identifying the internal and external markers, the problems of oversegmentation and undersegmentation are avoided. Furthermore, the internal and external parts of the RBCs phase image can also be segmented by using the marker-controlled watershed combined with our method, which can identify the internal and external markers appropriately. Our experimental results show that the proposed method achieves good performance in terms of segmenting RBCs and could thus be helpful when combined with an automated classification of RBCs.

Automated quantitative analysis of 3D morphology and mean corpuscular hemoglobin in human red blood cells stored in different periods

Quantitative phase (QP) images of red blood cells (RBCs), which are obtained by off-axis digital holographic microscopy, can provide quantitative information about three-dimensional (3D) morphology of human RBCs and the characteristic properties such as mean corpuscular hemoglobin (MCH) and MCH surface density (MCHSD). In this paper, we investigate modifications of the 3D morphology and MCH in RBCs induced by the period of storage time for the purpose of classification of RBCs with different periods of storage by using off-axis digital holographic microscopy. The classification of RBCs based on the duration of storage is highly relevant because a long storage of blood before transfusion may alter the functionality of RBCs and, therefore, cause complications in patients. To analyze any changes in the 3D morphology and MCH of RBCs due to storage, we use data sets from RBC samples stored for 8, 13, 16, 23, 27, 30, 34, 37, 40, 47, and 57 days, respectively. The data sets consist of more than 3,300 blood cells in eleven classes, with more than 300 blood cells per class. The classes indicate the storage period of RBCs and are listed in chronological order. Using the RBCs donated by healthy persons, the off-axis digital holographic microscopy reconstructs several quantitative phase images of RBC samples stored for eleven different periods. We employ marker-controlled watershed transform to remove the background in the RBC quantitative phase images obtained by the off-axis digital holographic microscopy. More than 300 single RBCs are extracted from the segmented quantitative phase images for each class. Such a large number of RBC samples enable us to obtain statistical distributions of the characteristic properties of RBCs after a specific period of storage. Experimental results show that the 3D morphology of the RBCs, in contrast to MCH, is essentially related to the aging of the RBCs.

Pharmacogenetics of the mycophenolic acid targets inosine monophosphate dehydrogenases IMPDH1 and IMPDH2: gene sequence variation and functional genomics

BACKGROUND AND PURPOSE

Inosine monophosphate dehydrogenases, encoded by IMPDH1 and IMPDH2, are targets for the important immunosuppressive drug, mycophenolic acid (MPA). Variation in MPA response may result, in part, from genetic variation in IMPDH1 and IMPDH2.

EXPERIMENTAL APPROACH

We resequenced IMPDH1 and IMPDH2 using DNA from 288 individuals from three ethnic groups and performed functional genomic studies of the sequence variants observed.

KEY RESULTS

We identified 73 single nucleotide polymorphisms (SNPs) in IMPDH1, 59 novel, and 25 SNPs, 24 novel, in IMPDH2. One novel IMPDH1 allozyme (Leu275) had 10.2% of the wild-type activity as a result of accelerated protein degradation. Decreased activity of the previously reported IMPDH2 Phe263 allozyme was primarily due to decreased protein quantity, also with accelerated degradation. These observations with regard to the functional implications of variant allozymes were supported by the IMPDH1 and IMPDH2 X-ray crystal structures. A novel IMPDH2 intron 1 SNP, G > C IVS1(93), was associated with decreased mRNA quantity, possibly because of altered transcription.

CONCLUSIONS AND IMPLICATIONS

These results provide insight into the nature and extent of sequence variation in the IMPDH1 and IMPDH2 genes. They also describe the influence of gene sequence variation that alters the encoded amino acids on IMPDH function and provide a foundation for future translational studies designed to correlate sequence variation in these genes with outcomes in patients treated with MPA.

Quantitative investigation of red blood cell three-dimensional geometric and chemical changes in the storage lesion using digital holographic microscopy

Quantitative phase information obtained by digital holographic microscopy (DHM) can provide new insight into the functions and morphology of single red blood cells (RBCs). Since the functionality of a RBC is related to its three-dimensional (3-D) shape, quantitative 3-D geometric changes induced by storage time can help hematologists realize its optimal functionality period. We quantitatively investigate RBC 3-D geometric changes in the storage lesion using DHM. Our experimental results show that the substantial geometric transformation of the biconcave-shaped RBCs to the spherocyte occurs due to RBC storage lesion. This transformation leads to progressive loss of cell surface area, surface-to-volume ratio, and functionality of RBCs. Furthermore, our quantitative analysis shows that there are significant correlations between chemical and morphological properties of RBCs.

Three-dimensional visualization of objects in scattering medium by use of computational integral imaging

In this paper, we propose a method to three-dimensionally visualize objects in a scattering medium using integral imaging. Our approach is based on a particular use of the interference phenomenon between the ballistic photons getting through the scattering medium and the scattered photons being scattered by the medium. For three-dimensional (3D) sensing of the scattered objects, the synthetic aperture integral imaging system under coherent illumination records the scattered elemental images of the objects. Then, the computational geometrical ray propagation algorithm is applied to the scattered elemental images in order to eliminate the interference patterns between scattered and object beams. The original 3D information of the scattered objects is recovered by multiple imaging channels, each with a unique perspective of the object. We present both simulation and experimental results with virtual and real objects to demonstrate the proposed concepts.

3-D visualization and identification of biological microorganisms using partially temporal incoherent light in-line computational holographic imaging

We present a new method for three-dimensional (3-D) visualization and identification of biological microorganisms using partially temporal incoherent light in-line (PTILI) computational holographic imaging and multivariate statistical methods. For 3-D data acquisition of biological microorganisms, the band-pass filtered white light is used to illuminate a biological sample. The transversely and longitudinally diffracted pattern of the biological sample is magnified by microscope objective (MO) and is optically recorded with an image sensor array interfaced with a computer. Three-dimensional reconstruction of the biological sample from the diffraction pattern is accomplished by using computational Fresnel propagation method. Principal components analysis and nonparametric inference algorithms are applied to the 3-D complex amplitude biological sample for identification purposes. Experiments indicate that the proposed system can be useful for identifying biological microorganisms. To the best of our knowledge, this is the first report on using PTILI computational holographic microscopy for identification of biological microorganisms.

Real-time automated 3D sensing, detection, and recognition of dynamic biological micro-organic events

In this paper, we present an overview of three-dimensional (3D) optical imaging techniques for real-time automated sensing, visualization, and recognition of dynamic biological microorganisms. Real time sensing and 3D reconstruction of the dynamic biological microscopic objects can be performed by single-exposure on-line (SEOL) digital holographic microscopy. A coherent 3D microscope-based interferometer is constructed to record digital holograms of dynamic micro biological events. Complex amplitude 3D images of the biological microorganisms are computationally reconstructed at different depths by digital signal processing. Bayesian segmentation algorithms are applied to identify regions of interest for further processing. A number of pattern recognition approaches are addressed to identify and recognize the microorganisms. One uses 3D morphology of the microorganisms by analyzing 3D geometrical shapes which is composed of magnitude and phase. Segmentation, feature extraction, graph matching, feature selection, and training and decision rules are used to recognize the biological microorganisms. In a different approach, 3D technique is used that are tolerant to the varying shapes of the non-rigid biological microorganisms. After segmentation, a number of sampling patches are arbitrarily extracted from the complex amplitudes of the reconstructed 3D biological microorganism. These patches are processed using a number of cost functions and statistical inference theory for the equality of means and equality of variances between the sampling segments. Also, we discuss the possibility of employing computational integral imaging for 3D sensing, visualization, and recognition of biological microorganisms illuminated under incoherent light. Experimental results with several biological microorganisms are presented to illustrate detection, segmentation, and identification of micro biological events.

No-search focus prediction at the single cell level in digital holographic imaging with deep convolutional neural network

Digital propagation of an off-axis hologram can provide the quantitative phase-contrast image if the exact distance between the sensor plane (such as CCD) and the reconstruction plane is correctly provided. In this paper, we present a deep-learning convolutional neural network with a regression layer as the top layer to estimate the best reconstruction distance. The experimental results obtained using microsphere beads and red blood cells show that the proposed method can accurately predict the propagation distance from a filtered hologram. The result is compared with the conventional automatic focus-evaluation function. Additionally, our approach can be utilized at the single-cell level, which is useful for cell-to-cell depth measurement and cell adherent studies.

Noise-free quantitative phase imaging in Gabor holography with conditional generative adversarial network

This paper shows that deep learning can eliminate the superimposed twin-image noise in phase images of Gabor holographic setup. This is achieved by the conditional generative adversarial model (C-GAN), trained by input-output pairs of noisy phase images obtained from synthetic Gabor holography and the corresponding quantitative noise-free contrast-phase image obtained by the off-axis digital holography. To train the model, Gabor holograms are generated from digital off-axis holograms with spatial shifting of the real image and twin image in the frequency domain and then adding them with the DC term in the spatial domain. Finally, the digital propagation of the Gabor hologram with Fresnel approximation generates a super-imposed phase image for the C-GAN model input. Two models were trained: a human red blood cell model and an elliptical cancer cell model. Following the training, several quantitative analyses were conducted on the bio-chemical properties and similarity between actual noise-free phase images and the model output. Surprisingly, it is discovered that our model can recover other elliptical cell lines that were not observed during the training. Additionally, some misalignments can also be compensated with the trained model. Particularly, if the reconstruction distance is somewhat incorrect, this model can still retrieve in-focus images.

Automated red blood cells extraction from holographic images using fully convolutional neural networks

In this paper, we present two models for automatically extracting red blood cells (RBCs) from RBCs holographic images based on a deep learning fully convolutional neural network (FCN) algorithm. The first model, called FCN-1, only uses the FCN algorithm to carry out RBCs prediction, whereas the second model, called FCN-2, combines the FCN approach with the marker-controlled watershed transform segmentation scheme to achieve RBCs extraction. Both models achieve good segmentation accuracy. In addition, the second model has much better performance in terms of cell separation than traditional segmentation methods. In the proposed methods, the RBCs phase images are first numerically reconstructed from RBCs holograms recorded with off-axis digital holographic microscopy. Then, some RBCs phase images are manually segmented and used as training data to fine-tune the FCN. Finally, each pixel in new input RBCs phase images is predicted into either foreground or background using the trained FCN models. The RBCs prediction result from the first model is the final segmentation result, whereas the result from the second model is used as the internal markers of the marker-controlled transform algorithm for further segmentation. Experimental results show that the given schemes can automatically extract RBCs from RBCs phase images and much better RBCs separation results are obtained when the FCN technique is combined with the marker-controlled watershed segmentation algorithm.

Automated three-dimensional microbial sensing and recognition using digital holography and statistical sampling

We overview an approach to providing automated three-dimensional (3D) sensing and recognition of biological micro/nanoorganisms integrating Gabor digital holographic microscopy and statistical sampling methods. For 3D data acquisition of biological specimens, a coherent beam propagates through the specimen and its transversely and longitudinally magnified diffraction pattern observed by the microscope objective is optically recorded with an image sensor array interfaced with a computer. 3D visualization of the biological specimen from the magnified diffraction pattern is accomplished by using the computational Fresnel propagation algorithm. For 3D recognition of the biological specimen, a watershed image segmentation algorithm is applied to automatically remove the unnecessary background parts in the reconstructed holographic image. Statistical estimation and inference algorithms are developed to the automatically segmented holographic image. Overviews of preliminary experimental results illustrate how the holographic image reconstructed from the Gabor digital hologram of biological specimen contains important information for microbial recognition.

Three-dimensional counting of morphologically normal human red blood cells via digital holographic microscopy

Counting morphologically normal cells in human red blood cells (RBCs) is extremely beneficial in the health care field. We propose a three-dimensional (3-D) classification method of automatically determining the morphologically normal RBCs in the phase image of multiple human RBCs that are obtained by off-axis digital holographic microscopy (DHM). The RBC holograms are first recorded by DHM, and then the phase images of multiple RBCs are reconstructed by a computational numerical algorithm. To design the classifier, the three typical RBC shapes, which are stomatocyte, discocyte, and echinocyte, are used for training and testing. Nonmain or abnormal RBC shapes different from the three normal shapes are defined as the fourth category. Ten features, including projected surface area, average phase value, mean corpuscular hemoglobin, perimeter, mean corpuscular hemoglobin surface density, circularity, mean phase of center part, sphericity coefficient, elongation, and pallor, are extracted from each RBC after segmenting the reconstructed phase images by using a watershed transform algorithm. Moreover, four additional properties, such as projected surface area, perimeter, average phase value, and elongation, are measured from the inner part of each cell, which can give significant information beyond the previous 10 features for the separation of the RBC groups; these are verified in the experiment by the statistical method of Hotelling's T-quare test. We also apply the principal component analysis algorithm to reduce the dimension number of variables and establish the Gaussian mixture densities using the projected data with the first eight principal components. Consequently, the Gaussian mixtures are used to design the discriminant functions based on Bayesian decision theory. To improve the performance of the Bayes classifier and the accuracy of estimation of its error rate, the leaving-one-out technique is applied. Experimental results show that the proposed method can yield good results for calculating the percentage of each typical normal RBC shape in a reconstructed phase image of multiple RBCs that will be favorable to the analysis of RBC-related diseases. In addition, we show that the discrimination performance for the counting of normal shapes of RBCs can be improved by using 3-D features of an RBC.

Automated multi-parameter measurement of cardiomyocytes dynamics with digital holographic microscopy

Compounds tested during drug development may have adverse effects on the heart; therefore all new chemical entities have to undergo extensive preclinical assessment for cardiac liability. Conventional intensity-based imaging techniques are not robust enough to provide detailed information for cell structure and the captured images result in low-contrast, especially to cell with semi-transparent or transparent feature, which would affect the cell analysis. In this paper we show, for the first time, that digital holographic microscopy (DHM) integrated with information processing algorithms automatically provide dynamic quantitative phase profiles of beating cardiomyocytes. We experimentally demonstrate that relevant parameters of cardiomyocytes can be obtained by our automated algorithm based on DHM phase signal analysis and used to characterize the physiological state of resting cardiomyocytes. Our study opens the possibility of automated quantitative analysis of cardiomyocyte dynamics suitable for further drug safety testing and compounds selection as a new paradigm in drug toxicity screens.

Three-dimensional identification of biological microorganism using integral imaging

In this paper, we address the identification of biological microorganisms using microscopic integral imaging (II). II senses multi-view directional information of 3D objects illuminated by incoherent light. A micro-lenslet array generates a set of elemental images by projecting a 3D scene onto a detector array. In computational reconstruction of II, 3D volumetric scenes are numerically reconstructed by means of a geometrical ray projection method. The identification of the biological samples is performed using the 3D volume of the reconstructed object. In one approach, the multivariate statistical distribution of the reference sample is measured in 3D space and compared with an unknown input sample by means of statistical discriminant functions. The multivariate empirical cumulative density of the 3D volume image is determined for classification. On the other approach, the graph matching technique is applied to 3D volumetric images with Gabor feature extraction. The reference morphology is identified in unknown input samples using 3D grids. Experimental results are presented for the identification of sphacelaria alga and tribonema aequale alga. We present experimental results for both 3D and 2D imaging. To the best of our knowledge, this is the first report on 3D identification of microorganisms using II.

Shape tolerant three-dimensional recognition of biological microorganisms using digital holography

We present a system for shape tolerant three-dimensional (3D) recognition of biological microorganisms using holographic microscopy. The system recognizes 3D microorganisms by analyzing complex images of the 3D microorganism restored from single-exposure on-line (SEOL) digital hologram. In this technique the SEOL hologram is recorded by a Mach-Zehnder interferometer, and then the original complex images are reconstructed numerically at different depths by inverse Fresnel transformation. For recognition, a number of sampling segment features are arbitrarily extracted from the restored 3D image. These samples are processed using a number of cost functions and the sampling distributions for the difference of the parameters (location, dispersion) between the sample segment features of the reference and input 3D image are calculated using a statistical sampling method. Then, a hypothesis testing for the equality of the parameters between reference and input 3D image is performed for a statistical decision about populations on the basis of sampling distribution information. Student's t distribution and Fisher's F distribution are used to statistically analyze the difference of means and the ratio of variances of two populations, respectively. The proposed system is designed to be tolerant to recognizing various, plain microorganisms with analogous shape such as bacteria and algae. Preliminary experimental results are presented to illustrate the robustness of the proposed recognition system using statistical inference.

Human red blood cell recognition enhancement with three-dimensional morphological features obtained by digital holographic imaging

The classification of erythrocytes plays an important role in the field of hematological diagnosis, specifically blood disorders. Since the biconcave shape of red blood cell (RBC) is altered during the different stages of hematological disorders, we believe that the three-dimensional (3-D) morphological features of erythrocyte provide better classification results than conventional two-dimensional (2-D) features. Therefore, we introduce a set of 3-D features related to the morphological and chemical properties of RBC profile and try to evaluate the discrimination power of these features against 2-D features with a neural network classifier. The 3-D features include erythrocyte surface area, volume, average cell thickness, sphericity index, sphericity coefficient and functionality factor, MCH and MCHSD, and two newly introduced features extracted from the ring section of RBC at the single-cell level. In contrast, the 2-D features are RBC projected surface area, perimeter, radius, elongation, and projected surface area to perimeter ratio. All features are obtained from images visualized by off-axis digital holographic microscopy with a numerical reconstruction algorithm, and four categories of biconcave (doughnut shape), flat-disc, stomatocyte, and echinospherocyte RBCs are interested. Our experimental results demonstrate that the 3-D features can be more useful in RBC classification than the 2-D features. Finally, we choose the best feature set of the 2-D and 3-D features by sequential forward feature selection technique, which yields better discrimination results. We believe that the final feature set evaluated with a neural network classification strategy can improve the RBC classification accuracy.