Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Early Detection and Classification of Breast Cancer Using Deep Learning Techniques

Mst. Mumtahina Labonno, D. M. Asadujjaman, Md. Mahfujur Rahman, Abdullah Tamim, Mst. Jannatul Ferdous, Rafi Muttaki Mahi

TL;DR

This study tackles automated early detection and multiclass classification of breast cancer using ultrasound imagery. It benchmarks three pretrained CNNs (ResNet50, MobileNet, VGG16) plus a custom CNN on Kaggle's Breast Cancer Image Classification dataset (9,248 images across Benign, Malignant, Normal), reporting highest overall accuracy for ResNet50 at 98.41% and near-perfect AUC for VGG16. The methodology combines deep transfer learning with a bespoke CNN, using 224×224 input images and a 70/15/15 train/validation/test split, and evaluates via standard metrics including Accuracy, F1, Precision, Recall, and AUC-ROC. The results underscore the potential of deep learning as a clinical decision-support tool for rapid, automated breast cancer screening, enhancing early detection while complementing physician expertise.

Abstract

Breast cancer is one of the deadliest cancers causing about massive number of patients to die annually all over the world according to the WHO. It is a kind of cancer that develops when the tissues of the breast grow rapidly and unboundly. This fatality rate can be prevented if the cancer is detected before it gets malignant. Using automation for early-age detection of breast cancer, Artificial Intelligence and Machine Learning technologies can be implemented for the best outcome. In this study, we are using the Breast Cancer Image Classification dataset collected from the Kaggle depository, which comprises 9248 Breast Ultrasound Images and is classified into three categories: Benign, Malignant, and Normal which refers to non-cancerous, cancerous, and normal images.This research introduces three pretrained model featuring custom classifiers that includes ResNet50, MobileNet, and VGG16, along with a custom CNN model utilizing the ReLU activation function.The models ResNet50, MobileNet, VGG16, and a custom CNN recorded accuracies of 98.41%, 97.91%, 98.19%, and 92.94% on the dataset, correspondingly, with ResNet50 achieving the highest accuracy of 98.41%.This model, with its deep and powerful architecture, is particularly successful in detecting aberrant cells as well as cancerous or non-cancerous tumors. These accuracies show that the Machine Learning methods are more compatible for the classification and early detection of breast cancer.

Early Detection and Classification of Breast Cancer Using Deep Learning Techniques

TL;DR

This study tackles automated early detection and multiclass classification of breast cancer using ultrasound imagery. It benchmarks three pretrained CNNs (ResNet50, MobileNet, VGG16) plus a custom CNN on Kaggle's Breast Cancer Image Classification dataset (9,248 images across Benign, Malignant, Normal), reporting highest overall accuracy for ResNet50 at 98.41% and near-perfect AUC for VGG16. The methodology combines deep transfer learning with a bespoke CNN, using 224×224 input images and a 70/15/15 train/validation/test split, and evaluates via standard metrics including Accuracy, F1, Precision, Recall, and AUC-ROC. The results underscore the potential of deep learning as a clinical decision-support tool for rapid, automated breast cancer screening, enhancing early detection while complementing physician expertise.

Abstract

Breast cancer is one of the deadliest cancers causing about massive number of patients to die annually all over the world according to the WHO. It is a kind of cancer that develops when the tissues of the breast grow rapidly and unboundly. This fatality rate can be prevented if the cancer is detected before it gets malignant. Using automation for early-age detection of breast cancer, Artificial Intelligence and Machine Learning technologies can be implemented for the best outcome. In this study, we are using the Breast Cancer Image Classification dataset collected from the Kaggle depository, which comprises 9248 Breast Ultrasound Images and is classified into three categories: Benign, Malignant, and Normal which refers to non-cancerous, cancerous, and normal images.This research introduces three pretrained model featuring custom classifiers that includes ResNet50, MobileNet, and VGG16, along with a custom CNN model utilizing the ReLU activation function.The models ResNet50, MobileNet, VGG16, and a custom CNN recorded accuracies of 98.41%, 97.91%, 98.19%, and 92.94% on the dataset, correspondingly, with ResNet50 achieving the highest accuracy of 98.41%.This model, with its deep and powerful architecture, is particularly successful in detecting aberrant cells as well as cancerous or non-cancerous tumors. These accuracies show that the Machine Learning methods are more compatible for the classification and early detection of breast cancer.
Paper Structure (12 sections, 4 equations, 4 figures, 4 tables)

This paper contains 12 sections, 4 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Dataset and Experiment
  5. Data Pre-Processing
  6. Training Models
  7. Deep Transfer Learning Model
  8. Custom CNN
  9. Hyperparameters
  10. Evaluation Criteria
  11. Result And Discussion
  12. Conclusion

Figures (4)

  • Figure 1: Block diagram of the multi-class classification of proposed framework
  • Figure 2: Custom CNN Architecture
  • Figure 3: Confusion Matrix Visualization for (a)ResNet50, (b)MobileNet, (c)VGG16, and (d) custom CNN model
  • Figure 4: ROC curve of ROC curves for (a)ResNet50, (b)MobileNet, (c)VGG16, and (d) custom CNN model