Fig 7 - uploaded by John Nguyen
Content may be subject to copyright.
Automated total RBC counting. The overlapping cells were segmented with proposed method, and their contours were labeled with blue ellipses. Those isolated RBCs, labeled with black plus symbols, were counted directly without segmentation procedures.
Source publication
- [...]
The Kleihauer-Betke (KB) test is the standard method for quantitating fetal-maternal hemorrhage (FMH) in maternal care. In hospitals, KB test is performed by a certified technologist to count a minimum of 2,000 fetal and maternal red blood cells (RBCs) on a blood smear. Manual counting suffers from inherent inconsistency and unreliability. This pap...
Context in source publication
Context 1
... other. Our proposed algorithm (spatial-color-based SC) generates a new feature vec- tor by adding spatial information into the original color matrix, which is proven effective in segmenting overlapping cells (see row 5 in Fig. 6). Furthermore, contour fitting on the overlapping cells generates clear ellipse-like contours for cell quantification. Fig. 7 shows the segmentation and counting results of one KB image. The overlapping cells were segmented, and their contours were labeled with blue ellipses. Those isolated cells, labeled with black plus symbols, were counted directly with- out segmentation procedures. To evaluate the accuracy of to- tal RBC counting, 12 KB images were ...
Citations
... Used the Hough transform technique for RBC counting and the morphological approach for segmentation [12]. Proposed an automated detection system to count the fetal and maternal RBC [13]. Proposed a method to automatically classify the RBC into overlap, normal and abnormal clusters [14]. ...
This book series aims to provide a forum for researchers from both academia and industry to share their latest research contributions in the area of computing technologies and Data Sciences and thus to exchange knowledge with the common goal of shaping the future. The best way to create memories is to gather and share ideas, creativity and innovations.
... El peso fetal fue evaluado antes del procedimiento mediante ecografía de rutina, utilizando la fórmula de Haddlock y Shepard. Los casos de hemorragia materno-fetal severa se definieron como hemorragia de 5 mL o más de volumen de eritrocitos fetales (14)(15)(16)(17) . ...
Objective
: To compare the frequency and amount of maternal-fetal hemorrhage following amniocentesis and cordocentesis.
Design
: Case-control study. Institución. Hospital Central "Dr. Urquinaona", Maracaibo, Venezuela.
Methods
: Pregnant women with singleton pregnancies without fetal anomalies undergoing amniocentesis for fetal karyotyping (16-20 weeks’ gestation) or cordocentesis (20- 30 weeks’ pregnancy) in the period January 2017-May 2022. Main study outcomes: General characteristics of the procedure, Kleihauer-Brown-Betke test results, and maternal serum alpha-fetoprotein concentrations.
Results
: The study sample was 305 patients. Amniocentesis was performed in 165 women and cordocentesis in 140 cases. De novo maternal-fetal hemorrhage was observed in 8 patients (4.8%) after amniocentesis and in 41 patients (29.3%) after cordocentesis, de novo maternalfetal hemorrhage was observed in 8 patients (4.8%). Serum alpha-fetoprotein concentrations increased in 24 cases (14.5%) after amniocentesis and in 55 cases (39.3%) after cordocentesis (p < 0.05). After cordocentesis, higher mean maternalfetal hemorrhage volume, elevation of individual volume values and significant increases in severe maternal-fetal hemorrhage (more than 5 mL of fetal erythrocytes) and total fetoplacental blood volume loss were observed (p < 0.05).
Conclusion
: These results show that both amniocentesis and cordocentesis increase the risk of maternal-fetal hemorrhage. However, ultrasound-guided amniocentesis has a lower risk of producing hemorrhage and resulting Rh isoimmunization compared to cordocentesis.
... At the event of fetal-maternal hemorrhage, the standard clinical method to quantify fetal and maternal red blood cells (RBCs) is the Kleihauer-Betke test, which is performed by a certified technologist. The automated system can count over 60 000 RBCs within 5 minutes, versus a technologist counting ∼2000 in about 15 minutes [118]. ...
Objective
Development of novel informatics methods focused on improving pregnancy outcomes remains an active area of research. The purpose of this study is to systematically review the ways that artificial intelligence (AI) and machine learning (ML), including deep learning (DL), methodologies can inform patient care during pregnancy and improve outcomes.
Materials and methods
We searched English articles on EMBASE, PubMed and SCOPUS. Search terms included ML, AI, pregnancy and informatics. We included research articles and book chapters, excluding conference papers, editorials and notes.
Results
We identified 127 distinct studies from our queries that were relevant to our topic and included in the review. We found that supervised learning methods were more popular (n = 69) than unsupervised methods (n = 9). Popular methods included support vector machines (n = 30), artificial neural networks (n = 22), regression analysis (n = 17) and random forests (n = 16). Methods such as DL are beginning to gain traction (n = 13). Common areas within the pregnancy domain where AI and ML methods were used the most include prenatal care (e.g. fetal anomalies, placental functioning) (n = 73); perinatal care, birth and delivery (n = 20); and preterm birth (n = 13). Efforts to translate AI into clinical care include clinical decision support systems (n = 24) and mobile health applications (n = 9).
Conclusions
Overall, we found that ML and AI methods are being employed to optimize pregnancy outcomes, including modern DL methods (n = 13). Future research should focus on less-studied pregnancy domain areas, including postnatal and postpartum care (n = 2). Also, more work on clinical adoption of AI methods and the ethical implications of such adoption is needed.
... One difficulty is also posed by the fact that cell are highly deformable. Counting can be defined also as a classification problem in cases when staining is used and as such simplifying the problem [10,11,12]. Other researchers have used multi stage procedures for the segmentation of breast tumour by using different classifiers and k-means based quantization [13]. ...
Medical field depends heavily on understanding and analyzing microscopy images of cells to better diagnose diseases, to evaluate the effectiveness of various medical treatments and to determine their health under stress. The amount of data that needs to be analyzed has increased and computer assisted analysis has become crucial as it would be very labor intensive for the medical practitioners otherwise. Many of the images are acquired using brightfield microscopy with no staining in order to avoid all the side effects. The unstained images have some associating challenges as they suffer from random nonuniform illumination, low contrast, relatively high transparency of the cytoplasm. The initial challenge of the large amount of data calls for the use of deep learning algorithms, whereas the other structural challenges call for the need to carefully train the convolutional neural networks in order to have a reliable system of evaluation. We have prepared a dataset of 20.000 images and we have tested the trained models on datasets with different number of images (N=300-8000). Here is this work we present classification of the cell health using convolutional neural networks and monitor the effect of the preprocessing steps on the overall accuracy.
... There are also many methods using artificial intelligence and machine learning to perform red blood cell counts. In [35], supervised learning and optimal clustering are employed along with spatial color classification to separate overlapping cells and count the number of fetal and maternal red blood cells. Classification of red blood cell images using spectral angle mapping (SAM) [36] is proposed; SAM leverages support vector machine (SVM) and establishes a standard red blood cell model for matching the red blood cells. ...
The isolation and observation of cardiomyocytes serve as the fundamental approach to cardiovascular research. The state-of-the-practice for the isolation and observation relies on manual operation of the entire culture process. Such a manual approach not only incurs high human errors, but also takes a long period of time. This paper proposes a new computer-aided paradigm to automatically, accurately, and efficiently perform the clustering and counting of cardiomyocytes, one of the key procedures for evaluating the success rate of cardiomyocytes isolation and the quality of culture medium. The key challenge of the proposed method lies in the unique, rod-like shape of cardiomyocytes, which has been hardly addressed in literature. Our proposed method employs a novel algorithm inspired by hesitant fuzzy sets and integrates an efficient implementation into the whole process of analyzing cardiomyocytes. The system, along with the data extracted from adult rats’ cardiomyocytes, has been experimentally evaluated with Matlab, showing promising results. The false accept rate (FAR) and the false reject rate (FRR) are as low as 1.46% and 1.97%, respectively. The accuracy rate is up to 98.7%—20% higher than the manual approach—and the processing time is reduced from tens of seconds to 3–5 s—an order of magnitude performance improvement.
... Chen et al. [30] have adopted a semi-automatic method to segment individual Pap smear cells and then train an SVM with cellular morphology and texture features for cell classification. Some other methods learning with cellular features for cell or nucleus classification are reported in [31]- [34], which provide promising performance in various microscopy images. However, all the approaches above use a multi-stage processing pipeline for nucleus/cell recognition, which typically consists of object detection and/or segmentation, feature representation computation, and classification, leading to image analysis inefficiency and great variability. ...
Objective:
Nucleus recognition is a critical yet challenging step in histopathology image analysis, for example in Ki67 immunohistochemistry stained images. Although many automated methods have been proposed, most use a multi-stage processing pipeline to categorize nuclei, leading to cumbersome, low-throughput and error-prone assessments. To address this issue, we propose a novel deep fully convolutional network for single-stage nucleus recognition.
Methods:
Instead of conducting direct pixel-wise classification, we formulate nucleus identification as a deep structured regression model. For each input image, it produces multiple proximity maps, each of which corresponds to one nucleus category and exhibits strong responses in central regions of nuclei. In addition, by taking into consideration the nucleus distribution in histopathology images, we further introduce an auxiliary task, region of interest (ROI) extraction, to assist and boost the nucleus quantification with weak ROI annotation. The proposed network can be learned in an end-to-end, pixel-to-pixel manner for simultaneous nucleus detection and classification.
Results:
We have evaluated this network on a pancreatic neuroendocrine tumor Ki67 image dataset, and the experiments demonstrate that our method outperforms recent state-of-the-art approaches.
Conclusion:
We present a new, pixel-to-pixel deep neural network with two sibling branches for effective nucleus recognition and observe that learning with another relevant task, ROI extraction, can further boost individual nucleus localization and classification.
Significance:
Our method provides a clean, single-stage nucleus recognition pipeline for histopathology image analysis, especially a new perspective for Ki67 image quantification, which would potentially benefit individual object quantification in whole-slide images.
... Another group employs concavity detection algorithms to find concave points on the mask and split the nuclei from these points (6,7). It has also been proposed to split the mask by identifying circular shapes by the Hough transform (8) and ellipse fitting techniques (9). The shape-based methods usually yield promising results when the degree of overlapping is relatively low so that there is no so much deviation in nucleus appearance from its assumed circular shape. ...
Cell nucleus segmentation remains an open and challenging problem especially to segment nuclei in cell clumps. Splitting a cell clump would be straightforward if the gradients of boundary pixels in‐between the nuclei were always higher than the others. However, imperfections may exist: inhomogeneities of pixel intensities in a nucleus may cause to define spurious boundaries whereas insufficient pixel intensity differences at the border of overlapping nuclei may cause to miss some true boundary pixels. In contrast, these imperfections are typically observed at the pixel‐level, causing local changes in pixel values without changing the semantics on a large scale. In response to these issues, this article introduces a new nucleus segmentation method that relies on using gradient information not at the pixel level but at the object level. To this end, it proposes to decompose an image into smaller homogeneous subregions, define edge‐objects at four different orientations to encode the gradient information at the object level, and devise a merging algorithm, in which the edge‐objects vote for subregion pairs along their orientations and the pairs are iteratively merged if they get sufficient votes from multiple orientations. Our experiments on fluorescence microscopy images reveal that this high‐level representation and the design of a merging algorithm using edge‐objects (gradients at the object level) improve the segmentation results.
... To solve this problem, marker-controlled watershed algorithms have been introduced [24][25][26], although marker-controlled watershed methods can address the oversegmentation problem successfully only if the extracted markers represent the actual objects. Hough transform [27][28][29][30], ellipse fitting [31], granulometry [8,32] and rule-based approaches [33,34] have been employed effectively in segmentation of overlapping regions; however, since these methods make restrictive shape assumptions, cell shape information may be distorted. The objective of this paper is to develop a new algorithm that can improve detection and segmentation of overlapping RBCs in microscopic images of thin blood smears. ...
... These statistical features were found to have highly significant differences between the normal and fatigue subjects, thereby providing useful features for fatigue status classification. These features can be used as input data for classifiers, such as clustering algorithm [37], neural networks (NNs), and SVMs, which can classify or detect muscular fatigue status. However, the design of practical and accurate automated recognition system remains a challenge. ...
... However, the design of practical and accurate automated recognition system remains a challenge. The challenge is to develop a robust and efficient classification technique that preserves important discriminatory information to provide better accuracy for classification [37], [38]. Consequently, for effective automated EMG signal classification, the systematic treatment of EMG signals must be conducted. ...
In this paper, a novel bacterial foraging algorithm (BFA)-Gaussian support vector classifier machine (GSVCM) model was proposed to improve the fatigue classification accuracy of electromyography (EMG) signals. This optimization mechanism involves the kernel parameter setting in the GSVCM training procedure, which significantly influences the classification accuracy. Experiments were conducted based on the EMG signal to differentiate the normal and fatigue status. In the proposed method, the EMG signals were decomposed into intrinsic mode functions by ensemble empirical mode decomposition (EEMD) before the mean instantaneous frequency could be obtained by Hilbert transform (HT). Finally, the fatigue statistical features can be extracted from fast Fourier transform and EEMD-HT. The application of this model to the fatigue status recognition of EMG signal indicated that further significant enhancement of the classification accuracy can be achieved by the proposed BFA-GSVCM classification system. The diagnostic method is effective and feasible.
... Blood cell classification helps doctors diagnose patients' diseases, such as leukemia, the presence of infections, some particular cancers, and acquired immunodeficiency syndrome, depending on the counts of different cell classes [9][10][11]. Traditionally, cells are observed by a specialist and the percent age of the occurrence of each type of cell is counted under a fluorescence microscope, which is very tedious, expensive, and time-consuming [12,13]. ...
With the advantage of fine spectral resolution, hyperspectral imagery provides great potential for cell classification. This paper provides a promising classification system including the following three stages: (1) band selection for a subset of spectral bands with distinctive and informative features, (2) spectral-spatial feature extraction, such as local binary patterns (LBP), and (3) followed by an effective classifier. Moreover, these three steps are further implemented on graphics processing units (GPU) respectively, which makes the system real-time and more practical. The GPU parallel implementation is compared with the serial implementation on central processing units (CPU). Experimental results based on real medical hyperspectral data demonstrate that the proposed system is able to offer high accuracy and fast speed, which are appealing for cell classification in medical hyperspectral imagery.
