Automated recognition of white blood cells using deep learning
- PDF / 1,405,760 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 0 Downloads / 236 Views
ORIGINAL ARTICLE
Automated recognition of white blood cells using deep learning Amin Khouani1 · Mostafa El Habib Daho1 · Sidi Ahmed Mahmoudi2 · Mohammed Amine Chikh1 · Brahim Benzineb3 Received: 4 March 2020 / Revised: 17 July 2020 / Accepted: 24 July 2020 © Korean Society of Medical and Biological Engineering 2020
Abstract The detection, counting, and precise segmentation of white blood cells in cytological images are vital steps in the effective diagnosis of several cancers. This paper introduces an efficient method for automatic recognition of white blood cells in peripheral blood and bone marrow images based on deep learning to alleviate tedious tasks for hematologists in clinical practice. First, input image pre-processing was proposed before applying a deep neural network model adapted to cells localization and segmentation. Then, model outputs were improved by using combined predictions and corrections. Finally, a new algorithm that uses the cooperation between model results and spatial information was implemented to improve the segmentation quality. To implement our model, python language, Tensorflow, and Keras libraries were used. The calculations were executed using NVIDIA GPU 1080, while the datasets used in our experiments came from patients in the Hemobiology service of Tlemcen Hospital (Algeria). The results were promising and showed the efficiency, power, and speed of the proposed method compared to the state-of-the-art methods. In addition to its accuracy of 95.73%, the proposed approach provided fast predictions (less than 1 s). Keywords Deep learning · White blood cells · Image segmentation · Classification · Mask RCNN · Object detection
1 Introduction In cytopathology analysis, the morphology of white blood cells and the counting of instances in cell slides can have medical significance for the diagnosis of several cancer diseases[1, 2]. However, the manual detection and segmentation of these structures can be costly, tedious and timeconsuming tasks, especially with the variability of structures
* Amin Khouani amin.khouani@univ‑tlemcen.dz Mostafa El Habib Daho mostafa.elhabibdaho@univ‑tlemcen.dz Sidi Ahmed Mahmoudi [email protected] Mohammed Amine Chikh mohammedamine.chikh@univ‑tlemcen.dz Brahim Benzineb [email protected] 1
University of Tlemcen, Tlemcen, Algeria
2
University of Mons, 20 Parc Sq., 7000 Mons, Belgium
3
CHU of Tlemcen, Tlemcen, Algeria
and the overlap between objects in images. Therefore, automatic search and segmentation techniques can help hematologists in clinical practice expedite treatment and improve efficiency and reliability. Previously automatic detection and segmentation for cytological images had difficulties, mainly due to high variation between the cell features. While some methods as [3] have used an optimized pixel-based classification approach, they have divided their work into two steps. The first one consists of using a classifier (Decision Tree or Random Forest) to perform the classification of each pixel in the image accordin
Data Loading...
