Anomoly Detection in Medical Imaging

EasyChair Preprint no. 12997

Abstract

The contemporary landscape of healthcare 
has been profoundly transformed by the infusion of 
machine learning techniques, which have heralded a new 
era of disease prediction and management. This research 
endeavors to address a critical gap in the existing 
healthcare paradigm by developing a unified system 
capable of predicting multiple diseases using a 
streamlined interface. Focusing primarily on Random 
Forest, a robust ensemble learning algorithm, and 
harnessing the power of deep learning, this study 
pioneers a comprehensive approach to disease 
forecasting. The study's core objective revolves around 
the accurate prediction of a spectrum of diseases, 
ranging from diabetes and heart disease to chronic 
kidney disease and cancer. Early detection of these 
ailments is pivotal, as it significantly impacts patient 
outcomes and healthcare costs. Leveraging Random 
Forest, a versatile and efficient machine learning 
algorithm, this research meticulously evaluates its 
predictive capabilities. By optimizing hyperparameters 
and fine-tuning the model, the study ensures the highest 
level of accuracy in disease prognosis. Additionally, the 
research delves into the realm of deep learning, a subset 
of machine learning that mimics the intricate neural 
networks of the human brain.

Keyphrases: disease detection, Medical Diagnosis, Medical Imaging, Pre-detection

@Booklet{EasyChair:12997,
  author = {Sai Viswas Basetti and Naveen Anmol and Raghava Chaithanya Alluri and Mahesh Babu Challa and Sai Ram Reddy},
  title = {Anomoly Detection in Medical Imaging},
  howpublished = {EasyChair Preprint no. 12997},

  year = {EasyChair, 2024}}