Comparison of traditional image processing and deep learning approaches for classification of white blood cells in peripheral blood smear images

2019 ◽  
Vol 39 (2) ◽  
pp. 382-392 ◽  
Author(s):  
Roopa B. Hegde ◽  
Keerthana Prasad ◽  
Harishchandra Hebbar ◽  
Brij Mohan Kumar Singh
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Peripheral Blood ◽  
Blood Cells ◽  
Blood Smear ◽  
White Blood Cells ◽  
Peripheral Blood Smear ◽  
Learning Approaches ◽  
Traditional Image

scholarly journals Blood Cell Count Using Deep Learning Semantic Segmentation

2019 ◽  
Author(s):  
Thanh Tran ◽  
Lam Binh Minh ◽  
Suk-Hwan Lee ◽  
Ki-Ryong Kwon
Keyword(s):  
Deep Learning ◽  
Blood Cell ◽  
Cell Count ◽  
Blood Cells ◽  
Blood Smear ◽  
White Blood Cells ◽  
Semantic Segmentation ◽  
Peripheral Blood Smear ◽  
Cell Counting ◽  
Blood Cell Count

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.

Development of a robust algorithm for detection of nuclei of white blood cells in peripheral blood smear images

2019 ◽  
Vol 78 (13) ◽  
pp. 17879-17898 ◽  
Author(s):  
Roopa B. Hegde ◽  
Keerthana Prasad ◽  
Harishchandra Hebbar ◽  
Brij Mohan Kumar Singh
Keyword(s):  
Peripheral Blood ◽  
Blood Cells ◽  
Blood Smear ◽  
White Blood Cells ◽  
Peripheral Blood Smear ◽  
Robust Algorithm

scholarly journals Acquired Pelger-Huët anomaly in a patient treated with valganciclovir

2019 ◽  
Vol 12 (10) ◽  
pp. e230958 ◽  
Author(s):  
Elva Nieto-Borrajo ◽  
Alfredo Bermejo-Rodriguez
Keyword(s):  
Peripheral Blood ◽  
Blood Cells ◽  
Blood Count ◽  
Blood Smear ◽  
Complete Blood Count ◽  
White Blood Cells ◽  
Peripheral Blood Smear ◽  
Condensed Chromatin ◽  
Morphological Abnormalities

A follow-up blood count was performed on a 74-year-old woman diagnosed with colitis due to cytomegalovirus and under treatment with valganciclovir. The automated complete blood count revealed an abnormal white blood cells (WBC) scattergram together with WBC alert flags. The peripheral blood smear showed neutrophils with markedly hyposegmented nuclei or bilobed nuclei and very condensed chromatin or clumping chromatin all consistent with Pelger-Huët anomaly (PHA). We checked previous blood counts, ruling out an inherited PHA. We assessed the haematological, infectious and iatrogenic aetiologies for an acquired PHA. Once the valganciclovir treatment was completed and the drug was withdrawn, without changing the rest of the treatment, the morphological abnormalities of neutrophils were completely resolved. We conclude therefore that the acquired PHA presented by our patient is probably related to valganciclovir treatment.

PENENTUAN KRITERIA PENILAIAN KESAN JUMLAH LEUKOSIT PADA PEMERIKSAAN APUSAN DARAH TEPI

2018 ◽  
Vol 3 (2) ◽  
pp. 52-61
Author(s):  
Dzikra Arwie ◽  
Islawati
Keyword(s):  
Data Analysis ◽  
Statistical Analysis ◽  
Blood Cells ◽  
Blood Smear ◽  
White Blood Cells ◽  
Peripheral Blood Smear ◽  
Field Of View ◽  
Laboratory Observation ◽  
Number Of Cells

Leukocytes or white blood cells have a characteristic characteristic of different cells. Determination of the impression of the number of leukocytes is determined in the number of cells in the field of view. While the number of viewable field cells expressed is still quite varied. The purpose of this study was to determine the number of leukocytes in the field of view and expressed the impression of a sufficient amount. This research was conducted at the Laboratory of Health Analyst Department Panrita Husada Bulukumba on 9 April 2017 to 14 July 2017. This type of research is a laboratory observation that aims to determine the criteria for assessing the impression of the number of leukocytes on a peripheral blood smear. Data analysis using statistical analysis is the average and standard deviations to determine the impression of the number of leukocytes and use 3 inspection zones. The results of this study obtained results in zone IV the number of leukocyte impressions said to be sufficient was 7-10, in zone V the number of leukocyte impressions said to be sufficient was 4-9, and in zone VI the number of leukocyte impressions said to be sufficient was 3-8.  

scholarly journals Fashion Product Classification through Deep Learning and Computer Vision

2019 ◽  
Vol 9 (7) ◽  
pp. 1385 ◽  
Author(s):  
Luca Donati ◽  
Eleonora Iotti ◽  
Giulio Mordonini ◽  
Andrea Prati
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Feature Extraction ◽  
Deep Learning ◽  
Template Matching ◽  
Learning Approaches ◽  
Visual Classification ◽  
Product Classification ◽  
Processing Techniques

Visual classification of commercial products is a branch of the wider fields of object detection and feature extraction in computer vision, and, in particular, it is an important step in the creative workflow in fashion industries. Automatically classifying garment features makes both designers and data experts aware of their overall production, which is fundamental in order to organize marketing campaigns, avoid duplicates, categorize apparel products for e-commerce purposes, and so on. There are many different techniques for visual classification, ranging from standard image processing to machine learning approaches: this work, made by using and testing the aforementioned approaches in collaboration with Adidas AG™, describes a real-world study aimed at automatically recognizing and classifying logos, stripes, colors, and other features of clothing, solely from final rendering images of their products. Specifically, both deep learning and image processing techniques, such as template matching, were used. The result is a novel system for image recognition and feature extraction that has a high classification accuracy and which is reliable and robust enough to be used by a company like Adidas. This paper shows the main problems and proposed solutions in the development of this system, and the experimental results on the Adidas AG™ dataset.

Sign in / Sign up

Export Citation Format

Share Document