Dataset Information

Segmentation of White Blood Cell from Acute Lymphoblastic Leukemia Images Using Dual-Threshold Method.

ABSTRACT: We propose a dual-threshold method based on a strategic combination of RGB and HSV color space for white blood cell (WBC) segmentation. The proposed method consists of three main parts: preprocessing, threshold segmentation, and postprocessing. In the preprocessing part, we get two images for further processing: one contrast-stretched gray image and one H component image from transformed HSV color space. In the threshold segmentation part, a dual-threshold method is proposed for improving the conventional single-threshold approaches and a golden section search method is used for determining the optimal thresholds. For the postprocessing part, mathematical morphology and median filtering are utilized to denoise and remove incomplete WBCs. The proposed method was tested in segmenting the lymphoblasts on a public Acute Lymphoblastic Leukemia (ALL) image dataset. The results show that the performance of the proposed method is better than single-threshold approach independently performed in RGB and HSV color space and the overall single WBC segmentation accuracy reaches 97.85%, showing a good prospect in subsequent lymphoblast classification and ALL diagnosis.

SUBMITTER: Li Y

PROVIDER: S-EPMC4893444 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Segmentation of White Blood Cell from Acute Lymphoblastic Leukemia Images Using Dual-Threshold Method.

Li Yan Y Zhu Rui R Mi Lei L Cao Yihui Y Yao Di D

Computational and mathematical methods in medicine 20160522

We propose a dual-threshold method based on a strategic combination of RGB and HSV color space for white blood cell (WBC) segmentation. The proposed method consists of three main parts: preprocessing, threshold segmentation, and postprocessing. In the preprocessing part, we get two images for further processing: one contrast-stretched gray image and one H component image from transformed HSV color space. In the threshold segmentation part, a dual-threshold method is proposed for improving the co ...[more]

PMID: 27313659

Similar Datasets

Project description:BACKGROUND:Drug-resistant cell lines, established from drug-sensitive cell lines by drug exposure in vitro, are the most useful cancer models in studies on the mechanism of chemoresistance. However, the success rate of the traditional approaches to construct such cell lines is low because a long time is required for the addition of drugs. METHODS:A cell culture technique was used to establish the drug-resistant cell lines from their parental cells. Molecular and cellular biological techniques including flow cytometry, MTT assay, western blotting, and DNA fingerprinting analysis were used to characterize the drug-resistant cell lines. Nude mice were used for xenograft studies. RESULTS:We established novel glucocorticoid (GC)-resistant cell lines from 3 GC-sensitive acute lymphoblastic leukemia (ALL) cell lines. First, we established a novel GC-resistant T-ALL cell line, CEM-C7/HDR, by mimicking the microenvironment of the bone marrow and culturing GC-sensitive CEM-C7-14 cells under hypoxia for 5?weeks with a single dexamethasone (Dex) treatment. The CEM-C7/HDR cells had been cultured continuously in drug-free medium under normoxia for 1?year. The IC50 and resistance index (RI) to Dex were maintained at 60~70??M and 1500~1800, respectively, which is in consistent with the IC50 and RI of GC-resistant CEM-C1-15 cells. To clarify the reliability of the method, we subcloned CEM-C7-14 cells, and obtained Dex-resistant cell lines, CEM-C7-SC2/HDR and CEM-C7-SC14/HDR, from 2 monoclonal cells of CEM-C7-14 by the same method. Moreover, we obtained two additional Dex-resistant B-ALL cell lines, NALM-6/HDR and HXEX-ALL1/HDR, from NALM-6 and HXEX-ALL1 cells with the same approach. CONCLUSIONS:CEM-C7/HDR, NALM-6/HDR and HXEX-ALL1/HDR cell lines may serve as useful GC-resistant ALL models for both in vitro and in vivo studies. Culturing under hypoxic condition with a single Dex treatment is a novel and convenient approach for generating stable GC resistant cell lines.

Dataset Information

Segmentation of White Blood Cell from Acute Lymphoblastic Leukemia Images Using Dual-Threshold Method.

Publications

Segmentation of White Blood Cell from Acute Lymphoblastic Leukemia Images Using Dual-Threshold Method.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets