Project Title: Leukemia Prediction and Classification from Peripheral

Blood Smear $($PBS$)$ Images

Project Description:

Objective: The objective of this project is to develop a machine learning model that:

$1.$Predicts the presence of leukemia disease from Peripheral Blood Smear $($PBS$)$ images

Classifies the images into different types of leukemia:

Dataset: Utilize the provided dataset containing PBS images from suspected leukemia patients. The

dataset is divided into two classes: benign and malignant. The malignant class further includes subtypes

of leukemia: Early Pre$-$B$,$ Pre$-$B$,$ and Pro$-$B ALL.

The dataset is available in Kaggle website: Acute Lymphoblastic Leukemia $($ALL$)$ image dataset

$($

kaggle.com$)$

Tasks:

Leukemia Prediction $($Binary Classification$)$:

Data Preprocessing:

Preprocess the data given and show your prepared dataset.

Split the dataset into training and testing sets, considering the temporal aspect.

Train a binary classification model to predict the presence or absence of leukemia disease.

Choose an appropriate binary classification model $($e$.$g$.,$ logistic regression, support vector machine$).$

Evaluate the binary classification model using relevant metrics $($e$.$g$.,$ accuracy, precision, recall$).*$

Image Classification $($Multiclass Classification$)$:

Utilize the PBS images to train a classification model that distinguishes between different types

of leukemia $($benign$,$ Early Pre$-$B$,$ Pre$-$B$,$ Pro$-$B$).$

Choose and implement a suitable image classification model $($e$.$g$.,$ Convolutional Neural

Network $-$ CNN$).$

Evaluate the classification model using appropriate metrics $($e$.$g$.,$ accuracy, precision, recall$).$

Integration of Models:

Integrate the image classification and leukemia prediction models to provide a comprehensive

diagnosis.

Assess the overall performance of the combined model.

Deliverables:

Python script containing the code for data preprocessing, model training, image classification,

leukemia prediction and evaluation.

Written report explaining the methodology, model choices, and results.

Visualization of the prediction results and performance metrics.

Interpretation of the combined model's performance for leukemia prediction.

Justify your selection for the ML model and Upload your final data with your project.

You can compare between two or three models.

The performance of the model should be high $($don$\text{'}$t submit low performance model$).$

Write appropriate references that you used to complete your project.

If you want to use different tool $($ Exe. Matlab, etc.$)$ this will be accepted.