Biology subjects

Tavakoli, E.

Publications and source records attributed to Tavakoli, E..

3 recordsLinked to original sources

bioRxiv2021

Generalizability in White Blood Cells' Classification Problem

Counting and classifying white blood cells (WBCs) in blood samples helps the early diagnosis of the disease. Many works have been done to develop machine learning-based methods to count WBCs. However, most of these works have low generalizability, and their accuracy decreases sharply as the dataset changes. In this paper, a new method is presented that helps to increase the generalization power. In this method, first, the WBCs nucleus is segmented, and then its convex hull is obtained. By subtracting the nucleus from the convex hull, a new image is created called the representative of the convex hull (ROC). Then, by Training a convolutional neural network (CNN) with the cells RGB image as well as the binary images of the nucleus and ROC, the generalization power is increased. The proposed method was first trained on the Raabin-WBC dataset, then its performance was evaluated on the LISC dataset without retraining. The proposed methods accuracy on the Raabin-WBC and LISC datasets is 93.97% and 51.57 %, respectively. Besides, the generalization power of four well-known CNNs named VGG16, ResNext50, MobileNet-V2, and MnasNet1 was investigated. It was found that VGG16 has more generalization power among these models.

bioengineering↗

bioRxiv2021

Raabin-WBC: a large free access dataset of white blood cells from normal peripheral blood

Accurate and early detection of peripheral white blood cell anomalies plays a crucial role in the evaluation of an individuals well-being. The emergence of new technologies such as artificial intelligence can be very effective in achieving this. In this regard, most of the state-of-the-art methods use deep neural networks. Data can significantly influence the performance and generalization power of machine learning approaches, especially deep neural networks. To that end, we collected a large free available dataset of white blood cells from normal peripheral blood samples called Raabin-WBC. Our dataset contains about 40000 white blood cells and artifacts (color spots). To reassure correct data, a significant number of cells were labeled by two experts, and the ground truth of nucleus and cytoplasm were extracted by experts for some cells (about 1145), as well. To provide the necessary diversity, various smears have been imaged. Hence, two different cameras and two different microscopes were used. The Raabin-WBC dataset can be used for different machine learning tasks such as classification, detection, segmentation, and localization. We also did some primary deep learning experiments on Raabin-WBC, and we showed how the generalization power of machine learning methods, especially deep neural networks, was affected by the mentioned diversity.

bioengineering↗

bioRxiv2021

New Segmentation and Feature Extraction Algorithm for the Classification of White Blood Cells in Peripheral Smear Images

This article addresses a new method for the classification of white blood cells (WBCs) using image processing techniques and machine learning methods. The proposed method consists of three steps: detecting the nucleus and cytoplasm, extracting features, and classification. At first, a new algorithm is designed to segment the nucleus. For the cytoplasm to be detected, only a part of it located inside the convex hull of the nucleus is involved in the process. This attitude helps us overcome the difficulties of segmenting the cytoplasm. In the second phase, three shapes and four novel color features are devised and extracted. Finally, by using an SVM model, the WBCs are classified. The segmentation algorithm can detect the nucleus with a dice similarity coefficient of 0.9675. The proposed method can categorize WBCs in Raabin-WBC, LISC, and BCCD datasets with accuracies of 94.65 %, 92.21 %, and 94.20 %, respectively. It is worth mentioning that the hyperparameters of the classifier are fixed only with the Raabin-WBC dataset, and these parameters are not readjusted for LISC and BCCD datasets. The obtained results demonstrate that the proposed method is robust, fast, and accurate.

bioengineering↗