A Deep Evaluation of Digital Image based Bone Cancer Prediction using Modified Machine Learning Strategy

Every single person, regardless of their age or stage in life, is at risk of developing the fatal disease known as cancer. There is a greater likelihood that cancer will affect more than one-third of the population at some point throughout their lifespan. In particular, bone cancer is a significant cause for concern in terms of health since it frequently leads to the patient's passing away. By examining the pictures obtained from X-ray, MRI, or CT scans, it is possible to identify the presence of bone cancer. The manual process requires a significant amount of effort and time-consuming expertise, and it also requires specific knowledge. As a result, the development of an automated method to differentiate between healthy bone and bone that has advanced cancer is of the utmost importance. The texture of malignant bone in the affected region is distinct from that of healthy bone in that portion of the body. It is important to note that the sample contains a number of images that exhibit morphological characteristics that are characteristic of both malignant and healthy bone. The early identification of this malignancy, including bone cancer, may be accomplished with the highest possible degree of precision through the use of medical imaging correlation in conjunction with image processing and machine learning techniques. This study proposes a strategy for identifying bone cancer by utilizing data acquired from actual clinical trials. The method is comprised of a number of phases that have the potential to increase the accuracy of disease prediction. The proposed model is designed based on Modified Machine Learning Strategy, called Elevated Learning based Bone Cancer Prediction (ELBCP), in which it evaluates the input image and predicts the bone cancer with high precision as well as the model is cross-validated with the conventional learning based classification model called Support Vector Machine (SVM) to prove the efficiency and performance of the proposed scheme.