Leukocytes Classification and Segmentation in Microscopic Blood Smear: A Resource-Aware Healthcare Service in Smart Cities

Sajjad, Muhammad; Khan, Saleem; Jan, Zahoor; Muhammad, Khan; Moon, Hyeonjoon; Kwak, Jin Tae; Rho, Seungmin; Mehmood, Irfan

doi:10.1109/access.2016.2636218

Cited by 97 publications

(58 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous work on blood cells like white blood cells (WBCs) and red blood cells (RBCs) [4][5][6][7] has used K-means, Zack algorithm, gradient magnitude, watershed transform, and SVM for segmentation along with some preprocessing for image enhancement [13]. ese works show outstanding performance for efficient detection and segmentation of blood cells.…”

Section: Related Workmentioning

confidence: 99%

“…Currently, several color space techniques are used for the partitioning of microscopic images like RGB, HIS, and LAB, but RGB is the most commonly used color space technique due to its close association with the human visual system [3]. Most of the previous works target the single cell segmentation [4][5][6][7]. e single cell technique targets only one type of cell (WBCs or RBCs) for segmentation at one time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Shahzad

Umar

Khan

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Previous works on segmentation of SEM (scanning electron microscope) blood cell image ignore the semantic segmentation approach of whole-slide blood cell segmentation. In the proposed work, we address the problem of whole-slide blood cell segmentation using the semantic segmentation approach. We design a novel convolutional encoder-decoder framework along with VGG-16 as the pixel-level feature extraction model. e proposed framework comprises 3 main steps: First, all the original images along with manually generated ground truth masks of each blood cell type are passed through the preprocessing stage. In the preprocessing stage, pixel-level labeling, RGB to grayscale conversion of masked image and pixel fusing, and unity mask generation are performed. After that, VGG16 is loaded into the system, which acts as a pretrained pixel-level feature extraction model. In the third step, the training process is initiated on the proposed model. We have evaluated our network performance on three evaluation metrics. We obtained outstanding results with respect to classwise, as well as global and mean accuracies. Our system achieved classwise accuracies of 97.45%, 93.34%, and 85.11% for RBCs, WBCs, and platelets, respectively, while global and mean accuracies remain 97.18% and 91.96%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Shahzad

Umar

Khan

et al. 2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…The features with their labels are used for matching different images by the classifier followed by designating those different images into corresponding classes [1].There are mainly three types of features such as color features, shape features and texture features can be extracted from an image. The most commonly used feature extraction techniques are as follows:…”

Section: Existing Feature Extraction Techniques For the Classificatiomentioning

confidence: 99%

“…The work by Muhammad Sajjad et.al [1] have concentrated in the estimation of classification of leukocytes or WBC which are supposed to be the basic building block of immune system of human body. This paper mainly deals with multi-class classification based on features extracted based on textural, wavelet transform and statistical properties.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Feature Extraction Techniques for Leukocyte Classification - A Review

Baby¹,

Devaraj²

2018

IJET

View full text Add to dashboard Cite

show abstract

White blood cell counting at point‐of‐care testing: A review

Luo

Chen

2020

Electrophoresis

View full text Add to dashboard Cite

White blood cells, which are also called leukocytes, are found in the immune system that are involved in protecting the body against infections and foreign invaders. Conventional methods of leukocyte analysis provide valuable and accurate information to medical specialists. Analyzing and diagnosing of a disease requires a combination of multiple biomarkers, in some cases, however, such as personal health care, this will occupy some medical resources and causes unnecessary consumption. Traditional method (such as flow cytometer) for WBC counting is time and labor consuming. Compared to gold standard (flow‐based fraction/micropore filtration) or improved filtration methods for WBC counting, this is still a lengthy and time consuming process and can lead to membrane fouling due to the rapid accumulation of biological materials. Therefore, the analysis of WBC counts requires more compact and efficient equipment. The microfluidic technologies, powered by different field (force, thermal, acoustic, optical, magnetic) and other methods for leukocyte counting and analysis, are much cost‐efficient and can be used in in‐home or in resource‐limited areas to achieve Point‐of‐Care (POC). In this review, we highlight the mainstream devices that have been commercialized and extensively employed for patients for WBC counting, Next, we present some recent development with regards to leucocyte counting (mainly microfluidic technologies) and comment on their relative merits. We aim to focus and discuss the possibility of achieving POC and help researchers to tackle individual challenges accordingly. Finally, we offer some technologies in addition to previous detection devices, such as image recognition technology and cloud computing, which we believe have great potential to further promote real‐time detection and improve medical diagnosis.

show abstract

Leukocytes Classification and Segmentation in Microscopic Blood Smear: A Resource-Aware Healthcare Service in Smart Cities

Cited by 97 publications

References 34 publications

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Robust Method for Semantic Segmentation of Whole-Slide Blood Cell Microscopic Images

Feature Extraction Techniques for Leukocyte Classification - A Review

White blood cell counting at point‐of‐care testing: A review

Contact Info

Product

Resources

About