Blood Cells Cancer analyzed via CNN

Explore the Web App on Hugging Face

• Step 1: Download Data
• Step 2: Put the images in the APP
• Step 3: Click it Predict

Table of Contents

• Blood Cells Cancer analyzed via CNN
• 1. Problem Statement
• 2. Data Description
  • Attribute Information
    • Inputs
    • Output
• 3. EDA
• 4. Modelling Evaluation
• 5. Results

Blood Cells Cancer analyzed via CNN

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.  Thus , our aim is to use two different deep learning architectures, CNN, in order to classiify correctly all stages of cancer.

1. Problem Statement

Classify correctly the 4 classes of stages of cancer, where one of them is benign and the others three are Malignant

2. Data Description

Data is obtained from kaggle.

• Number of instances - 3242
• Number of classes - 4

  Attribute Information

  Inputs

  • filepath: filepath of images

  Output

  • label : classification of 4 types of cells cancer

3. EDA

4. Modelling Evaluation

• Algorithms used
  • AlexNet
  • VGG16
• Metrics used: Accuracy, Precision, Recall, F1-Score

5. Results