Automatic neutrophil nucleus lobe counting based on graph representation of region skeleton

Abnormal neutrophil nucleus lobation (like left shift and right shift) helps to diagnose for some clinical conditions. Currently, quantification of it depends on the manual microscopic inspection of blood smears by clinicians. The quality of the manual inspection is extremely limited by the efficiency of clinicians and their medical background. This article proposed an automatic lobe counting method based on the graph representation of the nucleus region skeletons. Skeletons of the segmented nucleus regions are computed by augmented Fast Marching Method and transformed into plane graphs. Then the nucleus lobes are split based on the extracted graph properties including width distribution along the skeleton and graph structure decomposition. Experiments show that the proposed method could efficiently approaches the real lobe numbers in blood smears and reliably distinguish the stabs from the segmented neutrophils, thus it should be helpful in automatic neutrophil lobe number quantification and abnormal lobation diagnosis. ? 2012 International Society for Advancement of Cytometry.     

Eff-UNet++: A novel architecture for plant leaf segmentation and counting

Leaf segmentation learns more about leaf-level traits such as leaf area, count, stress, and development phases. In plant phenotyping, segmentation and counting of plant organs like leaves are a major challenge due to considerable overlap between leaves and varying environmental conditions, including brightness variation and shadow, blur due to wind. Further, the plant's inherent challenges, such as the leaf texture, genotype, size, shape, and density variation of leaves, make the leaf segmentation task more complex. To meet these challenges, the present work proposes a novel method for leaf segmentation and counting employing Eff-Unet++, an encoder-decoder-based architecture. This architecture uses EfficientNet-B4 as an encoder for accurate feature extraction. The redesigned skip connections and residual block in the decoder utilize encoder output and help to address the information degradation problem. In addition, the redesigned skip connections reduce the computational complexity. The lateral output layer is introduced to aggregate the low-level to high-level features from the decoder, which improves segmentation performance. The proposed method validates its performance on three datasets: KOMATSUNA dataset, Multi-Modality Plant Imagery Dataset (MSU-PID), and Computer Vision for Plant Phenotyping dataset (CVPPP). The proposed approach outperforms the existing state-of-the-art methods UNet, UNet++, Residual-UNet, InceptionResv2-UNet, and DeeplabV3 leaf segmentation results achieve best dice (BestDice): 83.44, 71.17, 78.27 and Foreground-Background Dice (FgBgDice): 97.48, 91.35, 96.38 on KOMATSUNA, MSU-PID, and CVPPP dataset respectively. In addition, for leaf counting the results are difference in count (DiffFG): 0.11, 0.03, 0.12 and Absolute Difference in count (AbsDiffFG): 0.21, 0.38, 1.27 on KOMATSUNA, MSU-PID, and CVPPP dataset respectively.     

Leukocyte counting from a small amount of whole blood using a size-controlled microcavity array

Absolute counting of total leukocytes or specific subsets within small amounts of whole blood is difficult due to a lack of techniques that enable separation of all leukocytes from limited amounts of whole blood. In this study, a microfluidic device equipped with a size-controlled microcavity array for highly efficient separation of leukocytes from submicroliters of whole blood was developed. The microcavity array can separate leukocytes from whole blood based on differences in the size and deformability between leukocytes and other blood cells. Leukocytes recovered on aligned microcavities were continuously processed for image-based immunophenotypic analysis. Our device successfully recovered over 90% of leukocytes in 1 μL of whole blood without pretreatment such as density gradient centrifugation or erythrocyte lysis. In addition, the proposed system successfully performed absolute enumeration of human CD4(+) and CD8(+) leukocytes from 1 μL of whole blood, and the obtained data showed good correlation with conventional flow cytometric analysis. Our microfluidic device has great potential as a tool for a point-of-care leukocyte analysis system.     

基于目标颜色基及梯度方向匹配的菌落分割计数算法

【目的】通过菌落测试片提取菌落并计数,在农业、食品业、医疗卫生等领域中是一项常用且重要的工作。目前,菌落自动计数算法大都是以菌落培养皿为主要工作对象,对菌落测试片适用性较差。另外,目前相关技术在常规的粘连物体分割中有着较好的效果,但在菌落分割计数中,由于菌落本身的形态特征,对粘连菌落分割计数的效果尚不够精准。【方法】为解决此类问题,本文提出一种基于目标颜色基及梯度方向匹配的菌落分割计数算法。首先利用图像中菌落的颜色特征作为基,将图像转换到基空间内,以增强菌落与背景之间的差异,其次利用菌落图像的梯度幅值特征对梯度方向进行滤波,然后通过梯度方向进行匹配,进而将粘连的菌落分割,最后利用非极大值抑制的方法筛选出菌落并计数。【结果】经试验,本研究算法的计数精度可达98.00%,能够满足实际需求。【结论】在针对菌落的目标分割计数中,本研究算法不仅计数精度高,而且具有较好的鲁棒性,在对不同厂家的菌落总数测试片菌落分割计数中均有优异效果;然而在对大面积目标的检测分割中算法的准确率会有所下降,因此,该算法更适合于菌落等小目标的检测分割。     

Classification and lateralization of temporal lobe epilepsies with and without hippocampal atrophy based on whole-brain automatic MRI segmentation

Brain images contain information suitable for automatically sorting subjects into categories such as healthy controls and patients. We sought to identify morphometric criteria for distinguishing controls (n = 28) from patients with unilateral temporal lobe epilepsy (TLE), 60 with and 20 without hippocampal atrophy (TLE-HA and TLE-N, respectively), and for determining the presumed side of seizure onset. The framework employs multi-atlas segmentation to estimate the volumes of 83 brain structures. A kernel-based separability criterion was then used to identify structures whose volumes discriminate between the groups. Next, we applied support vector machines (SVM) to the selected set for classification on the basis of volumes. We also computed pairwise similarities between all subjects and used spectral analysis to convert these into per-subject features. SVM was again applied to these feature data. After training on a subgroup, all TLE-HA patients were correctly distinguished from controls, achieving an accuracy of 96 ± 2% in both classification schemes. For TLE-N patients, the accuracy was 86 ± 2% based on structural volumes and 91 ± 3% using spectral analysis. Structures discriminating between patients and controls were mainly localized ipsilaterally to the presumed seizure focus. For the TLE-HA group, they were mainly in the temporal lobe; for the TLE-N group they included orbitofrontal regions, as well as the ipsilateral substantia nigra. Correct lateralization of the presumed seizure onset zone was achieved using hippocampi and parahippocampal gyri in all TLE-HA patients using either classification scheme; in the TLE-N patients, lateralization was accurate based on structural volumes in 86 ± 4%, and in 94 ± 4% with the spectral analysis approach. Unilateral TLE has imaging features that can be identified automatically, even when they are invisible to human experts. Such morphometric image features may serve as classification and lateralization criteria. The technique also detects unsuspected distinguishing features like the substantia nigra, warranting further study.     

Leukocyte biophysics

The biophysical properties of leukocytes in the passive and active state are discussed. In the passive unstressed state, leukocytes are spherical with numerous membrane folds. Passive leukocytes exhibit viscoelastic properties, and the stress is carried largely by the cell cytoplasm and the nucleus. The membrane is highly deformable in shearing and bending, but resists area expansion. Membrane tension can usually be neglected but plays a role in cases of large deformation when the membrane becomes unfolded. The constant membrane area constraint is a determinant of phagocytic capacity, spreading of cells, and passage through narrow pores. In the active state, leukocytes undergo large internal cytoplasmic deformation, pseudopod projection, and granule redistribution. Several different measurements for assessment of biophysical properties and the internal cytoplasmic deformation in form of strain and strain rate tensors are presented. The current theoretical models for active cytoplasmic motion in leukocytes are discussed in terms of specific macromolecular reactions.     

Leukocyte adhesion and microvessel permeability

To investigate the direct effect of leukocyte adherence to microvessel walls on microvessel permeability, we developed a method to measure changes in hydraulic conductivity (L(p)) before and after leukocyte adhesion in individually perfused venular microvessels in frog mesentery. In 19 microvessels that were initially free of leukocyte sticking or rolling along the vessel wall, control L(p) was measured first with Ringer-albumin perfusate. Blood flow was then restored in each vessel with a reduced flow rate in the range of 30-116 microm/s to facilitate leukocyte adhesion. Each vessel was recannulated in 45 min. The mean number of leukocytes adhering to the vessel wall was 237 +/- 22 leukocytes/mm(2). At the same time, L(p) increased to 4.7 +/- 0.5 times the control value. Superfusion of isoproterenol (10 microM) after leukocyte adhesion brought the increased L(p) back to 1.1 +/- 0.2 times the control in 5-10 min (n = 9). Superfusing isoproterenol before leukocyte adhesion prevented the increase in L(p) (n = 6). However, the number of leukocytes adhering to the vessel wall was not significantly affected. These results demonstrated that leukocyte adhesion caused an increase in microvessel permeability that could be prevented or restored by increasing cAMP levels in endothelial cells using isoproterenol. Thus cAMP-dependent mechanisms that regulate inflammatory agent-induced increases in permeability also modulate leukocyte adhesion-induced increases in permeability but act independently of mechanisms that regulate leukocyte adhesion to the microvessel wall. Application of ketotifen, a mast cell stabilizer, and desferrioxamine mesylate, an iron-chelating reagent, attenuated the increase in L(p) induced by leukocyte adhesion, suggesting the involvement of oxidants and the activation of mast cells in leukocyte adhesion-induced permeability increase. Furthermore, with the use of an in vivo silver stain technique, the locations of the adherent leukocytes on the microvessel wall were identified quantitatively in intact microvessels.     

Aging and visual counting

Background

Much previous work on how normal aging affects visual enumeration has been focused on the response time required to enumerate, with unlimited stimulus duration. There is a fundamental question, not yet addressed, of how many visual items the aging visual system can enumerate in a “single glance”, without the confounding influence of eye movements.

Methodology/Principal Findings

We recruited 104 observers with normal vision across the age span (age 21–85). They were briefly (200 ms) presented with a number of well- separated black dots against a gray background on a monitor screen, and were asked to judge the number of dots. By limiting the stimulus presentation time, we can determine the maximum number of visual items an observer can correctly enumerate at a criterion level of performance (counting threshold, defined as the number of visual items at which ≈63% correct rate on a psychometric curve), without confounding by eye movements. Our findings reveal a 30% decrease in the mean counting threshold of the oldest group (age 61–85: ∼5 dots) when compared with the youngest groups (age 21–40: 7 dots). Surprisingly, despite decreased counting threshold, on average counting accuracy function (defined as the mean number of dots reported for each number tested) is largely unaffected by age, reflecting that the threshold loss can be primarily attributed to increased random errors. We further expanded this interesting finding to show that both young and old adults tend to over-count small numbers, but older observers over-count more.

Conclusion/Significance

Here we show that age reduces the ability to correctly enumerate in a glance, but the accuracy (veridicality), on average, remains unchanged with advancing age. Control experiments indicate that the degraded performance cannot be explained by optical, retinal or other perceptual factors, but is cortical in origin.     

Categorical counting

Pigeons pecked on three keys, responses to one of which could be reinforced after a few pecks, to a second key after a somewhat larger number of pecks, and to a third key after the maximum pecking requirement. The values of the pecking requirements and the proportion of trials ending with reinforcement were varied. Transits among the keys were an orderly function of peck number, and showed approximately proportional changes with changes in the pecking requirements, consistent with Weber's law. Standard deviations of the switch points between successive keys increased more slowly within a condition than across conditions. Changes in reinforcement probability produced changes in the location of the psychometric functions that were consistent with models of timing. Analyses of the number of pecks emitted and the duration of the pecking sequences demonstrated that peck number was the primary determinant of choice, but that passage of time also played some role. We capture the basic results with a standard model of counting, which we qualify to account for the secondary experiments.