A Resilient Deep Learning Approach for Detecting Fungus Images

EasyChair Preprint no. 11836

Abstract

This research paper introduces a robust deep learning model designed for the early and accurate detection of black fungus (mucormycosis) in medical imaging. The proposed model integrates the powerful features of Gabor filters with the transfer learning technique, aiming to enhance the model's robustness and effectiveness in identifying fungal infections. Gabor filters are employed to extract texture features from medical images, capturing subtle patterns indicative of black fungus presence. Transfer learning is then applied using a pre-trained convolutional neural network (CNN) architecture, leveraging knowledge from large datasets to improve the model's performance on the specific task of mucormycosis detection. The synergy of Gabor filters and transfer learning provides the model with the capability to discern intricate fungal patterns in diverse medical imaging scenarios, ensuring its adaptability to varying conditions. The paper presents extensive experimental results, demonstrating the model's superior performance compared to existing approaches. The proposed deep learning model not only showcases promising results in black fungus detection but also sets the stage for future advancements in leveraging hybrid techniques for improved disease diagnosis in medical imaging.

Keyphrases: A Resilient Deep Learning, detecting, Fungus Images

@Booklet{EasyChair:11836,
  author = {Karem Mohammed},
  title = {A Resilient Deep Learning Approach for Detecting Fungus Images},
  howpublished = {EasyChair Preprint no. 11836},

  year = {EasyChair, 2024}}