All-IDB: The acute lymphoblastic leukemia image database for image processing

Abstract

The visual analysis of pheripheral blood samples is an important test in the procedures for the diagnosis of leukemia. Automated systems based on artificial vision methods can speed up this operation and they can increase the accuracy of the response also in telemedicine applications. Unfortunately, there are not available public image datasets to test and compare such algorithms. In this paper we propose a new public dataset of blood samples, specifically designed for the evaluation and the comparison of algorithms for segmentation and classification. For each image in the dataset, the classification of cell is given, and it is provided a specific set of figures of merits to be processed in order to fairly compare different algorithms when working with the proposed dataset. We hope that this initiative could give a new test tool to the image processing and pattern matching communities, aiming at stimulate new studies in this important field of research.

Acute Leukemia Classification Using Convolution Neural Network in Clinical Decision Support System

“…In this experiment, the original ALL-IDB1 image database which consists of 108 cell image [3] (59 normal cell images and 49 abnormal cell images) was used. The number of labelled training data and unlabelled testing data are shown in Table 1.…”

Automatic Segmentation of Acute Leukemia Cells

“…It is a public dataset of microscopic images of blood samples designed for the evaluation and the comparison of algorithms for segmentation and image classification. It was the same material that has been used by Kekre H [24] and the used database is available [23].…”

“… 115 digital images of size 256x256 captured with a simple light microscope with three ocular lenses and an analog video CCD which is coupled to a Pinnacle to digitize the captured images [23,24]. It is a public dataset of microscopic images of blood samples designed for the evaluation and the comparison of algorithms for segmentation and image classification.…”

“…They showed that automated cells splitting by watershed technique is better for cell counting. Labati RD et al [23,24], used morphological operators encoded in the structuring element that depend on object shape and characteristics. Median filters and morphological operations applied for noise removal as suggested by researchers [25].…”

Fingerprint Authentication in Digital Watermarking Using YCbCr Colour Space & 2D Walsh Code

“…For the experiments, we have used the acute lymphoblastic leukemia image database ALLIDB, proposed by Donida Labati in [10]. It is public dataset which contains blood sample image of normal patient and patient having leukemia.…”