Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimized Techniques Based on Dense Neural Networks

Salah A. Aly, Ali Bakhiet, Mazen Balat

TL;DR

This study presents a novel hybrid deep learning framework that combines DenseNet201 for feature extraction with a Dense Neural Network (DNN) for classification, optimized using the Harris Hawks Optimization (HHO) algorithm.

Abstract

Lymphoma diagnosis, particularly distinguishing between subtypes, is critical for effective treatment but remains challenging due to the subtle morphological differences in histopathological images. This study presents a novel hybrid deep learning framework that combines DenseNet201 for feature extraction with a Dense Neural Network (DNN) for classification, optimized using the Harris Hawks Optimization (HHO) algorithm. The model was trained on a dataset of 15,000 biopsy images, spanning three lymphoma subtypes: Chronic Lymphocytic Leukemia (CLL), Follicular Lymphoma (FL), and Mantle Cell Lymphoma (MCL). Our approach achieved a testing accuracy of 99.33\%, demonstrating significant improvements in both accuracy and model interpretability. Comprehensive evaluation using precision, recall, F1-score, and ROC-AUC underscores the model's robustness and potential for clinical adoption. This framework offers a scalable solution for improving diagnostic accuracy and efficiency in oncology.

Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimized Techniques Based on Dense Neural Networks

TL;DR

This study presents a novel hybrid deep learning framework that combines DenseNet201 for feature extraction with a Dense Neural Network (DNN) for classification, optimized using the Harris Hawks Optimization (HHO) algorithm.

Abstract

Lymphoma diagnosis, particularly distinguishing between subtypes, is critical for effective treatment but remains challenging due to the subtle morphological differences in histopathological images. This study presents a novel hybrid deep learning framework that combines DenseNet201 for feature extraction with a Dense Neural Network (DNN) for classification, optimized using the Harris Hawks Optimization (HHO) algorithm. The model was trained on a dataset of 15,000 biopsy images, spanning three lymphoma subtypes: Chronic Lymphocytic Leukemia (CLL), Follicular Lymphoma (FL), and Mantle Cell Lymphoma (MCL). Our approach achieved a testing accuracy of 99.33\%, demonstrating significant improvements in both accuracy and model interpretability. Comprehensive evaluation using precision, recall, F1-score, and ROC-AUC underscores the model's robustness and potential for clinical adoption. This framework offers a scalable solution for improving diagnostic accuracy and efficiency in oncology.

Paper Structure

This paper contains 23 sections, 7 equations, 4 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Materials and Methods Involved
  4. Dataset Description
  5. Data Preprocessing
  6. Feature Extraction
  7. Transfer Learning Using DenseNet201
  8. Freezing Strategies
  9. Feature Vector Concatenation
  10. Classification Models
  11. Model Architecture
  12. Model Compilation
  13. Optimized Dense Neural Network (ODNN) with Harris Hawks Optimization (HHO)
  14. Performance Evaluation Metrics
  15. Accuracy
  16. ...and 8 more sections

Figures (4)

  • Figure 1: Representative biopsy samples for each class of malignant lymphoma: CLL, FL, and MCL.
  • Figure 2: An overview of the methodology for lymphoma classification
  • Figure 3: Confusion Matrices Before and After Optimization
  • Figure 4: ROC Curve Before Optimization (DNN)