Dataset Information

A large dataset of white blood cells containing cell locations and types, along with segmented nuclei and cytoplasm.

ABSTRACT: Accurate and early detection of anomalies in peripheral white blood cells plays a crucial role in the evaluation of well-being in individuals and the diagnosis and prognosis of hematologic diseases. For example, some blood disorders and immune system-related diseases are diagnosed by the differential count of white blood cells, which is one of the common laboratory tests. Data is one of the most important ingredients in the development and testing of many commercial and successful automatic or semi-automatic systems. To this end, this study introduces a free access dataset of normal peripheral white blood cells called Raabin-WBC containing about 40,000 images of white blood cells and color spots. For ensuring the validity of the data, a significant number of cells were labeled by two experts. Also, the ground truths of the nuclei and cytoplasm are extracted for 1145 selected cells. To provide the necessary diversity, various smears have been imaged, and two different cameras and two different microscopes were used. We did some preliminary deep learning experiments on Raabin-WBC to demonstrate how the generalization power of machine learning methods, especially deep neural networks, can be affected by the mentioned diversity. Raabin-WBC as a public data in the field of health can be used for the model development and testing in different machine learning tasks including classification, detection, segmentation, and localization.

SUBMITTER: Kouzehkanan ZM

PROVIDER: S-EPMC8782871 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A large dataset of white blood cells containing cell locations and types, along with segmented nuclei and cytoplasm.

Kouzehkanan Zahra Mousavi ZM Saghari Sepehr S Tavakoli Sajad S Rostami Peyman P Abaszadeh Mohammadjavad M Mirzadeh Farzaneh F Satlsar Esmaeil Shahabi ES Gheidishahran Maryam M Gorgi Fatemeh F Mohammadi Saeed S Hosseini Reshad R

Scientific reports 20220121 1

Accurate and early detection of anomalies in peripheral white blood cells plays a crucial role in the evaluation of well-being in individuals and the diagnosis and prognosis of hematologic diseases. For example, some blood disorders and immune system-related diseases are diagnosed by the differential count of white blood cells, which is one of the common laboratory tests. Data is one of the most important ingredients in the development and testing of many commercial and successful automatic or s ...[more]

PMID: 35064165

Similar Datasets

Project description:Coastal southeast Florida experiences a wide range of aerosol conditions, including African dust, biomass burning (BB) aerosols, as well as sea salt and other locally-emitted aerosols. These aerosols are important sources of cloud condensation nuclei (CCN), which play an essential role in governing cloud radiative properties. As marine environments dominate the surface of Earth, CCN characteristics in coastal southeast Florida have broad implications for other regions with the added feature that this site is perturbed by both natural and anthropogenic emissions. This study investigates the influence of different air mass types on CCN concentrations at 0.2% (CCN0.2%) and 1.0% (CCN1.0%) supersaturation (SS) based on ground site measurements during selected months in 2013, 2017, and 2018. Average CCN0.2% and CCN1.0% concentrations were 373 ± 200 cm-3 and 584 ± 323 cm-3, respectively, for four selected days with minimal presence of African dust and BB (i.e., background days). CCN concentrations were not elevated on the four days with highest influence of African dust (289 ± 104 cm-3 [0.2% SS] and 591 ± 302 cm-3 [1.0% SS]), consistent with high dust mass concentrations comprised of coarse particles that are few in number. In contrast, CCN concentrations were substantially enhanced on the five days with the greatest impact from BB (1408 ± 976 cm-3 [0.2% SS] and 3337 ± 1252 cm-3 [1.0% SS]). Ratios of CCN0.2%:CCN1.0% were used to compare the hygroscopicity of the aerosols associated with African dust, BB, and background days. Average ratios were similar for days impacted by African dust and BB (0.54 ± 0.17 and 0.55 ± 0.17, respectively). A 29% higher average ratio was observed on background days (0.71 ± 0.14), owing in part to a strong presence of sea salt and reduced presence of more hydrophobic species such as those of a carbonaceous or mineral-dust nature. Finally, periods of heavy rainfall were shown to effectively decrease both CCN0.2% and CCN1.0% concentrations. However, the rate varied at which such concentrations increased after the rain. This work contributes knowledge on the nucleating ability of African dust and BB in a marine environment after varying periods of atmospheric transport (days to weeks). The results can be used to understand the hygroscopicity of these air mass types, predict how they may influence cloud properties, and provide a valuable model constraint when predicting CCN concentrations in comparable situations.

Project description:BackgroundCorrect segmentation is critical to many applications within automated microscopy image analysis. Despite the availability of advanced segmentation algorithms, variations in cell morphology, sample preparation, and acquisition settings often lead to segmentation errors. This manuscript introduces a ranked-retrieval approach using logistic regression to automate selection of accurately segmented nuclei from a set of candidate segmentations. The methodology is validated on an application of spatial gene repositioning in breast cancer cell nuclei. Gene repositioning is analyzed in patient tissue sections by labeling sequences with fluorescence in situ hybridization (FISH), followed by measurement of the relative position of each gene from the nuclear center to the nuclear periphery. This technique requires hundreds of well-segmented nuclei per sample to achieve statistical significance. Although the tissue samples in this study contain a surplus of available nuclei, automatic identification of the well-segmented subset remains a challenging task.ResultsLogistic regression was applied to features extracted from candidate segmented nuclei, including nuclear shape, texture, context, and gene copy number, in order to rank objects according to the likelihood of being an accurately segmented nucleus. The method was demonstrated on a tissue microarray dataset of 43 breast cancer patients, comprising approximately 40,000 imaged nuclei in which the HES5 and FRA2 genes were labeled with FISH probes. Three trained reviewers independently classified nuclei into three classes of segmentation accuracy. In man vs. machine studies, the automated method outperformed the inter-observer agreement between reviewers, as measured by area under the receiver operating characteristic (ROC) curve. Robustness of gene position measurements to boundary inaccuracies was demonstrated by comparing 1086 manually and automatically segmented nuclei. Pearson correlation coefficients between the gene position measurements were above 0.9 (p < 0.05). A preliminary experiment was conducted to validate the ranked retrieval in a test to detect cancer. Independent manual measurement of gene positions agreed with automatic results in 21 out of 26 statistical comparisons against a pooled normal (benign) gene position distribution.ConclusionsAccurate segmentation is necessary to automate quantitative image analysis for applications such as gene repositioning. However, due to heterogeneity within images and across different applications, no segmentation algorithm provides a satisfactory solution. Automated assessment of segmentations by ranked retrieval is capable of reducing or even eliminating the need to select segmented objects by hand and represents a significant improvement over binary classification. The method can be extended to other high-throughput applications requiring accurate detection of cells or nuclei across a range of biomedical applications.

Project description:Roads are a major cause of habitat fragmentation that can negatively affect many mammal populations. Mitigation measures such as crossing structures are a proposed method to reduce the negative effects of roads on wildlife, but the best methods for determining where such structures should be implemented, and how their effects might differ between species in mammal communities is largely unknown. We investigated the effects of a major highway through south-eastern British Columbia, Canada on several mammal species to determine how the highway may act as a barrier to animal movement, and how species may differ in their crossing-area preferences. We collected track data of eight mammal species across two winters, along both the highway and pre-marked transects, and used a multi-scale modeling approach to determine the scale at which habitat characteristics best predicted preferred crossing sites for each species. We found evidence for a severe barrier effect on all investigated species. Freely-available remotely-sensed habitat landscape data were better than more costly, manually-digitized microhabitat maps in supporting models that identified preferred crossing sites; however, models using both types of data were better yet. Further, in 6 of 8 cases models which incorporated multiple spatial scales were better at predicting preferred crossing sites than models utilizing any single scale. While each species differed in terms of the landscape variables associated with preferred/avoided crossing sites, we used a multi-model inference approach to identify locations along the highway where crossing structures may benefit all of the species considered. By specifically incorporating both highway and off-highway data and predictions we were able to show that landscape context plays an important role for maximizing mitigation measurement efficiency. Our results further highlight the need for mitigation measures along major highways to improve connectivity between mammal populations, and illustrate how multi-scale data can be used to identify preferred crossing sites for different species within a mammal community.

Dataset Information

A large dataset of white blood cells containing cell locations and types, along with segmented nuclei and cytoplasm.

Publications

A large dataset of white blood cells containing cell locations and types, along with segmented nuclei and cytoplasm.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets