Image

Blood Cell Classification Using Deep Learning

Blood cell classification plays a vital role in diagnosing various medical conditions and diseases. This project focuses on developing a robust and efficient deep learning model to automate the classification of blood cells into distinct categories. Using a comprehensive dataset of blood cell images, we preprocess these images to ensure they are suitable for training. We then construct a convolutional neural network (CNN) using the powerful Keras and TensorFlow libraries. The primary goal of this project is to assist medical professionals by automating the blood cell classification process, thereby reducing the time and effort required for manual classification and increasing diagnostic accuracy. This project demonstrates the potential of AI in enhancing medical diagnostics, making the process more efficient and reliable.

Explanation All Code

STEP 1:

You can mount your Google Drive in a Google Colab notebook with this piece of code. This creates it simple to see files saved in Google Drive in the Colab setting so that data can be changed, analyzed, and models can be trained.


Importing Libraries

We import essential libraries for data processing, model building, evaluation, and visualization.

Data collection and preparation:


We utilized the Blood Cell Dataset for Deep Learning Classification. We collected a blood cell dataset consisting of 1800 images. After augmenting the images, the total dataset increased to 3000 images. Next, divide the dataset into 80% for training and 20% for validation.



Load Datasets

We set the paths for training and validation datasets stored in Google Drive.


Listing Categories

We list the categories (labels) in the training dataset directory.

Step 2:

Data Processing

Processing Training Data

Plotting Class Distributions

Processing Validation Data

Plotting Validation Data Distribution

Step 3:

Preparing Data for Model

Visualizing Random Training Images

Step 4:


Blood Cell Classification Using CNN, EfficientNetB4 and Vgg16 Model

  • CNN (Convolutional Neural Network): This model is designed to recognize patterns in images, making it a strong choice for image classification tasks like detecting skin cancer.
  • EfficientNetB4: This advanced model is known for its efficiency and accuracy. It balances performance and resource usage, making it ideal for complex image classification tasks.
  • VGG16: This model is renowned for its simplicity and depth. It uses 16 layers to extract features from images, making it highly effective for detailed image analysis needed in skin cancer detection.


By using these models, my project aims to accurately detect skin cancer from medical images, leveraging the strengths of each model to improve overall performance.


Building a Basic CNN Model

Training the Basic CNN Model

Plotting Training History

Evaluating Model Performance

Evaluating the Model

Plotting Confusion Matrix and Classification Report

Step 5:

Efficientnet_b4

Training the EfficientNetB4

Plotting Training History

Evaluating Model Performance

Evaluating the Model

We load the best model and evaluate it on the test data. There is the EfficientNetB4 Accuracy of 99.83%.


Saving the EfficientNet Model

Plotting Confusion Matrix and Classification Report

Step 6:

Building a Vgg16 model


We define and compile a vgg16 model.


Training the vgg16

Plotting Training History

We plot the accuracy and loss curves of the model.


Evaluating the Model

We load the best model and evaluate it on the test data. There is the vgg16 Accuracy of 93.17%.


Plotting Confusion Matrix and Classification Report

Step 6:

Prediction

Load the Model efficientnet_b4

Conclusion

The Blood Cell Classification project successfully demonstrates the application of advanced deep learning techniques to accurately classify different types of blood cells. By leveraging a well-structured convolutional neural network and a detailed dataset, our model achieved significant performance improvements. The use of data augmentation and model fine-tuning further enhanced the model's robustness and generalization capabilities, ensuring it performs well on new, unseen data. Throughout the project, we observed the transformative potential of AI in the field of medical diagnostics. The automated blood cell classification system we developed offers a scalable and efficient solution, reducing the workload of medical professionals and increasing diagnostic precision. This project's success highlights the broader implications of AI in healthcare, suggesting that similar approaches can be applied to other areas of medical image analysis, ultimately improving patient outcomes and advancing the field of medical research.
Code Editor