Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
20 views

B-ALL Prediction Using Computer Vision (TensorFlow)

The document describes a minor project to develop a machine learning model for early detection of acute lymphoblastic leukemia (ALL) using image classification. ALL is a common type of blood cancer in children. The purpose is to classify medical images of blood samples to detect ALL at early stages for improved treatment outcomes. The project will use a dataset of peripheral blood smear images labeled as benign or malignant ALL subtypes to train a convolutional neural network model for automated diagnosis and subtype classification of ALL.

Uploaded by

bipra.patra24
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
20 views

B-ALL Prediction Using Computer Vision (TensorFlow)

The document describes a minor project to develop a machine learning model for early detection of acute lymphoblastic leukemia (ALL) using image classification. ALL is a common type of blood cancer in children. The purpose is to classify medical images of blood samples to detect ALL at early stages for improved treatment outcomes. The project will use a dataset of peripheral blood smear images labeled as benign or malignant ALL subtypes to train a convolutional neural network model for automated diagnosis and subtype classification of ALL.

Uploaded by

bipra.patra24
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 18

MINOR PROJECT- I

EARLY STAGE DETECTION OF

B-ACUTE LYMPHOBLASTIC LEUKEMIA


USING IMAGE CLASSIFICATION

Guided by: Dr. Pradeep Kumar Tiwari


Project by: Purushottam Malbishoye and Bipra Patra
Introduction
Description and Purpose
Acute Lymphoblastic Leukemia (ALL) is a type of blood cancer that
affects the white blood cells called lymphocytes. It is the most common
type of cancer in children, but can also affect adults. Early detection of
ALL is crucial for successful treatment and improved survival rates.

The purpose of this project is to develop a machine learning model that


can detect ALL in its early stages, based on patient data and medical
imaging.

MINOR PROJECT | APR. 2023


Symptoms & Diagnosis
Common symptoms include
fatigue
fever
bruising
bone pain.

Diagnosis typically involves


blood tests
bone marrow biopsy
imaging.

MINOR PROJECT | APR. 2023


Why Computer vision ?
As a highly prevalent cancer, the definitive diagnosis of
acute lymphoblastic leukemia (ALL) requires
invasive,
expensive, and
time-consuming diagnostic tests.
ALL diagnosis using peripheral blood smear (PBS) images
plays a vital role in the initial cancer screening 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.
Consequently, data scientists are presented with an opportunity
to analyze the image data with the aim of predicting the ALL
stage.

MINOR PROJECT | APR. 2023


Dataset used
The images of this dataset were prepared in the bone marrow laboratory of Taleqani Hospital (Tehran, Iran). This
dataset consisted of 3256 PBS images from 89 suspected of ALL patients whose blood samples were prepared and
stained by skillful laboratory staff. This dataset is divided into two classes benign and malignant. The former
comprises hematogones; 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 using a Zeiss camera in a microscope with 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. After color thresholding-based segmentation in the HSV color space, we also provide segmented images.

dataset url: https://www.kaggle.com/datasets/mehradaria/leukemia

DATA CITATION:
MEHRAD ARIA, MUSTAFA GHADERZADEH, DAVOOD BASHASH, HASSAN ABOLGHASEMI, FARKHONDEH ASADI, AND AZAMOSSADAT HOSSEINI, “ACUTE LYMPHOBLASTIC LEUKEMIA
(ALL) IMAGE DATASET.” KAGGLE, (2021). DOI: 10.34740/KAGGLE/DSV/2175623.

PUBLICATION CITATION:
GHADERZADEH, M, ARIA, M, HOSSEINI, A, ASADI, F, BASHASH, D, ABOLGHASEMI, H. A FAST AND EFFICIENT CNN MODEL FOR B-ALL DIAGNOSIS AND ITS SUBTYPES CLASSIFICATION
USING PERIPHERAL BLOOD SMEAR IMAGES. INT J INTELL SYST. 2022; 37: 5113- 5133. DOI:10.1002/INT.22753

MINOR PROJECT | APR. 2023


System
Architecture

You might also like