•  
  •  
 

Abstract

The study of medical image-based disease detection has witnessed a notable surge in interest and success with computational methods. This work proposes a novel framework to detect diseases at earlier stages from medical images, using mathematical model and Machine Learning. Introduce two new quantitative measures for COVID-19 and Tumor disease detection: image uncertainty based on Shannon entropy and image complexity based on fractal dimension. Our result demonstrated that in COVID-19 positive images exhibited skewed pixel distribution due to the hazy regions resulting in lower entropy values for diseased cases compared to healthy ones. The second quantity, fractal dimension was measured by box counting method determines the image's complexity. The outcomes of both techniques were applied to the classification of images using the Machine Learning (ML) model k-NN (k-nearest neighbor). This complete framework provides a new and unique approach to identify and classify diverse types of images with a classification accuracy of 90% for Covid and 70% for Tumor achieved. Our work shows that Entropy and fractal dimensions can distinguish between COVID-19 and healthy patients, making them promise for early diagnosis. This manuscript presents a novel, computationally efficient and explainable methodology for disease classification that provides early-stage disease detection.

Keywords

CT scan, Fractal dimension, K-nearest neighbors, Machine learning, Magnetic resonance imaging, Medical image analysis, Shannon entropy, Statistical analysis

Subject Area

Computer Science

Article Type

Article

First Page

1354

Last Page

1365

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download

Share

COinS