Dataset Information

Alam2019 - Machine learning approach of automatic identification and counting of blood cells

ABSTRACT: This model is used for automatic identification and counting of three types of blood cells: Red Blood Cells (RBC), White Blood Cells (WBC) and Platelet (Platelets) using the ‘you only look once’ (YOLO) object detection and classification algorithm with some additions to remove overannotation. The YOLO framework has been trained with a modified configuration BCCD Dataset of blood smear images to automatically identify and count red blood cells, white blood cells, and platelets. Postprocessing with k-nearest neighbor (KNN) and intersection over union (IOU) approach reduces issues with multiple annotation of platelets. The original code was extended to save the trained YoloV2 network state into the protobuf format. This is then used to generate the ONNX model, containing the weigths. Additional code was added to implement the inference step for image annotation based on the ONNX model, as well as the post-processing logic as used on the original model output. Dependencies have been documented explicitly using a conda environment.yml file to simplify reproducibility. Original GitHub repository: https://github.com/MahmudulAlam/Automatic-Identification-and-Counting-of-Blood-Cells GitHub repository: https://github.com/nilshoffmann/Automatic-Identification-and-Counting-of-Blood-Cells

SUBMITTER: Nils Hoffmann

PROVIDER: BIOMD0000001069 | BioModels | 2023-05-25

REPOSITORIES: BioModels

ACCESS DATA

Dataset's files

Source:

			Action	DRS
	BIOMD0000001069?filename=Dockerfile.onnx	Other
	BIOMD0000001069?filename=Dockerfile.train	Other
	BIOMD0000001069?filename=biomodels-ontology-terms.docx	Other
	BIOMD0000001069?filename=ground_truth.csv	Csv
	BIOMD0000001069?filename=image_001.jpg	Other

Items per page:

1 - 5 of 13

Similar Datasets

Project description:Background: Earlobe color is a typical external trait in chicken. There are some previous studies showing that the chicken white/red earlobe color is a polygenic and sex-linked trait in some breeds, but its molecular genetic and histological mechanisms still remain unclear. Methods: We herein utilized histological section, genome-wide association study (GWAS) and RNA-seq, further to investigate the potential histological and molecular genetic mechanisms of white/red earlobe formation in Qiangyuan Partridge chicken (QYP). Results: through histological section analysis, we found the dermal papillary layer of red earlobes had many more blood vessels than that of white earlobes. And we identified a total of 44 SNPs from Chromosome 1, 2, 3, 4, 9, 10, 11, 13, 19, 20, 23 and Z, that was significantly associated with the chicken white/red earlobe color from GWAS, along with 73 significantly associated genes obtained (e.g., PIK3CB, B4GALT1 and TP63), supporting the fact that the white/red earlobe color was also polygenic and sex-linked in QYP. Importantly, PIK3CB and B4GALT1 are both involved in the biological process of angiogenesis, which may directly give rise to the chicken white earlobe formation through regulating blood vessel density in chicken earlobe. Additionally, through contrast of RNA-seq profiles between white earlobe skins and red earlobe skins, we further identified TP63 and CDH1 differentially expressed. Combined with the existing knowledge of TP63 in epithelial development and tumor angiogenesis, we propose that down-regulated TP63 in white earlobes may play roles in thickening the skin and decreasing the vessel numbers in dermal papillary layer, thereby contributing to the white earlobe formation via paling the redness of the skin in QYP, but the specific mechanism remains further clarified. Conclusion: our findings advance the existing understanding of the white earlobe formation, as well as provide new clues to understand the molecular mechanism of chicken white/red earlobe color formation.

Dataset Information

Alam2019 - Machine learning approach of automatic identification and counting of blood cells

Dataset's files

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets