If you use this dataset in your research, please credit the authors. Publication Citation: Azamossadat Hosseini, Mohammad Amir (Robin) Eshraghi, Tania Taami, Hamidreza Sadeghsalehi, Zahra Hoseinzadeh, Mustafa Ghaderzadeh, Mohammad Rafiee, A mobile application based on efficient lightweight CNN model for classification of B-ALL cancer from non-cancerous cells: A design and implementation study, Informatics in Medicine Unlocked, Volume 39, 2023, 101244, ISSN 2352-9148, Paper: https://doi.org/10.1016/j.imu.2023.101244. Source code: https://github.com/MAmirEshraghi/Lightweight-Deep-CNN-Based-Mobile-App-in-the-Screening-of-ALL

The definitive diagnosis of Acute Lymphoblastic Leukemia (ALL), as a highly prevalent cancer, requires invasive, expensive, and time-consuming diagnostic tests. ALL diagnosis using peripheral blood smear (PBS) images plays a vital role in the initial screening of cancer from non-cancer cases. The examination of these PBS images by laboratory users is riddled with problems such as diagnostic error because the non-specific nature of ALL signs and symptoms often leads to misdiagnosis.

The images of this dataset were prepared in the bone marrow laboratory of Taleqani Hospital (Tehran, Iran). This dataset consisted of 3242 PBS images from 89 patients suspected of ALL, whose blood samples were prepared and stained by skilled laboratory staff. This dataset is divided into two classes benign and malignant. The former comprises hematogenous, and the latter is the ALL group with three subtypes of malignant lymphoblasts: Early Pre-B, Pre-B, and Pro-B ALL. All the images were taken by using a Zeiss camera in a microscope with a 100x magnification and saved as JPG files. A specialist using the flow cytometry tool made the definitive determination of the types and subtypes of these cells.

Dataset

This dataset was created by heewonpark

Released under Database: Open Database, Contents: Database Contents

Contents

Dataset

This dataset was created by Ashiq

Contents

Dataset

This dataset was created by Hamzairfan503

Released under CC0: Public Domain

Contents

Dataset

This dataset was created by Johar M. Ashfaque

Contents

Dataset

This dataset was created by Hari Schuth

Contents

Dataset

This dataset was created by Johar M. Ashfaque

Contents

It contains the following files:

ALL_IDB_1-2 The ALL_IDB1 version 1.0 can be used both for testing segmentation capability of algorithms, as well as the classification systems and image preprocessing methods. This dataset is composed of 108 images collected during September, 2005. It contains about 150 blood images each class 50 images, where the lymphocytes has been labeled by expert oncologists. The images are taken with different magnifications of the microscope ranging from 300 to 500.

Dataset

This dataset was created by Shahariar 13

Released under MIT

Contents

Dataset

This dataset was created by zahir4

Contents

Dataset

This dataset was created by Wahidul Hasan Abir

Contents

The microscopic blood cell dataset for leukemia detection consists of high-resolution images essential for automated diagnostic systems. Each image captures detailed cellular morphology under standardized conditions, focusing on both normal and abnormal blood cells.

Key Components: - Myeloblasts (AML indicators): 12-20 micrometers, round/oval, high nuclear-cytoplasm ratio, visible nucleoli - Lymphoblasts (ALL indicators): 10-14 micrometers, homogeneous chromatin, minimal cytoplasm - Normal cells: Mature lymphocytes, neutrophils, monocytes, eosinophils, basophils

Technical Specifications: Resolution: 1024x1024 pixels minimum Staining: Wright-Giemsa Magnification: 100x oil immersion (1000x total) Color: 24-bit RGB Multiple focal planes per sample

Quality Measures: Expert hematopathologist validation Standardized imaging conditions Multiple samples per cell type Detailed preparation documentation Complete technical metadata

Clinical Applications: Normal vs. abnormal cell differentiation Leukemia subtype identification Disease progression monitoring Early detection screening Treatment response assessment

Image Annotations Include: Nuclear patterns and contours Cytoplasmic features Nucleoli presence Cell measurements Abnormal inclusions/Auer rods

Machine Learning Capabilities: Automated cell classification Quantitative feature analysis Differential counting Morphological abnormality detection The dataset's structured organization and comprehensive documentation support both research initiatives and clinical applications in blood cancer diagnostics. Its standardized format enables reliable machine learning model development for automated leukemia detection systems.

This dataset consists of 5000 images (.jpg) where the distribution is 1000 per class

About This Data

Malignant lymphoma is a cancer affecting lymph nodes. Three types of malignant lymphoma are represented in the set: - CLL (chronic lymphocytic leukemia); - FL (follicular lymphoma); - MCL (mantle cell lymphoma).

The ability to distinguish classes of lymphoma from biopsies sectioned and stained with Hematoxylin/Eosin (H+E) would allow for more consistent and less demanding diagnosis of this disease. Only the most expert pathologists specializing in these types of lymphomas are able to consistently and accurately classify these three lymphoma types from H+E-stained biopsies. The standard practice is to use class-specific probes in order to distinguish these classes reliably.

This dataset is a collection of samples prepared by different pathologists at different sites. There is a large degree of staining variation that one would normally expect from such samples.

How To Cite this Dataset

If you find this dataset useful, please credit the authors

Original Article

Orlov, Nikita & Chen, Wayne & Eckley, David & Macura, Tomasz & Shamir, Lior & Jaffe, Elaine & Goldberg, Ilya. (2010). Automatic Classification of Lymphoma Images With Transform-Based Global Features. IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society. 14. 1003-13. 10.1109/TITB.2010.2050695.

BibTeX

@article{article, author = {Orlov, Nikita and Chen, Wayne and Eckley, David and Macura, Tomasz and Shamir, Lior and Jaffe, Elaine and Goldberg, Ilya}, year = {2010}, month = {07}, pages = {1003-13}, title = {Automatic Classification of Lymphoma Images With Transform-Based Global Features}, volume = {14}, journal = {IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society}, doi = {10.1109/TITB.2010.2050695} }

License

License was not specified at the source

Splash Image

Photo by Yassine Khalfalli on Unsplash

Image Preview

Chronic Lymphocytic Leukemia (CLL)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F793761%2F895ec7920df6e19fa16b8831b44d8abc%2FCLL.jpg?generation=1587359355893368&alt=media" alt="CLL">

Follicular Lymphoma (FL)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F793761%2Fe57c6dfe8e5d68750fd6834449292d0c%2FFL.jpg?generation=1587359386411233&alt=media" alt="FL">

Mantle Cell Lymphoma (MCL)

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F793761%2Fab2edfb97c04e39d22ca9d1b467a4063%2FMCL.jpg?generation=1587359404910944&alt=media" alt="MCL">