CNN-Based Approach for Overlapping Erythrocyte Counting and Cell Type Classification in Peripheral Blood Images

Abstract

Automatic analysis of cell numbers and types from blood smear images is essential for diagnosing and treating many diseases. Peripheral smear has been used for many years and is a gold standard method. However, the overlap in cells during the peripheral smear process may cause incorrectly predicted results in counting blood cells and classifying cell types. This problem can occur both in automated systems and in manual inspections by experts. Convolutional neural networks provide reliable results for segmentation and classification problems in the medical field. However, creating ground truth labels in the data during the segmentation process is a time-consuming and error-prone process. This study proposes a new CNN-based strategy to eliminate the overlap-induced counting problem in peripheral smear blood samples and to determine the blood cell type with high accuracy. In the proposed method, images of the entire slide were divided into sub-images, block by block, using adaptive image processing techniques to identify the overlapping cells and cell types. CNN was used to classify the number of cells separated from the original images into sub-images by blocks. The proposed method both counts overlapping red blood cells and distinguishes RBC-WBC with an accuracy rate of 99.73%. The results show that the proposed method can be adapted to areas where high-resolution images are found and reliable results.

Digital assessment of peripheral blood and bone marrow aspirate smears

“…[35][36][37] used CNN models to successfully identify and account for overlapping RBCs in cell type classification. 41…”

“…Other CNN models have focused on improved quantification of RBCs and RBC precursors within PB smears for the diagnosis of benign hematologic disorders and infectious diseases. To eliminate the issue of RBC overlap in PB smear analyzers, Pala et al used CNN models to successfully identify and account for overlapping RBCs in cell type classification 41 . Wang et al developed a Faster R‐CNN model to identify reticulocytes with higher recall and precision compared to flow cytometric methods 42 .…”

Self Adaptive Methods for Learning Rate Parameter of Q-Learning Algorithm

“…Machine learning methods can produce the most appropriate results in the face of new situations by analysing the sensors on the system or the data sources given to it before (Grefenstette n.d.). Especially in recent years, the development of computer, software and information systems along with technology has enabled artificial intelligence and machine learning to be widely used in fields such as economy (Jogunola et al 2020;Meng and Journal of Intelligent Systems: Theory and Applications 6(2) (2023) 191-198 192 Khushi 2019; Sarızeybek and Sevli 2022), medicine (Bayraj et al 2022;Cimen et al 2021;Pala et al 2019Pala et al , 2021Pala et al , 2022, biology, chemistry, informatics (Ekinci 2022;Omurca et al 2022;Toğaçar, Eşidir, and Ergen 2021) and engineering (Akyurek and Bucak 2012;Bucak and Zohdy 1999;Chen et al 2022;Çimen et al 2019;Singh, Kumar, and Singh 2022). Machine learning methods can generally be grouped as Supervised Learning, Unsupervised Learning and reinforcement learning.…”