Artificial Intelligence in Biomedical Images Analysis

Introduction

Biomedical imaging or “diagnostic by imaging” (RX, MRI, CT) refers to the process of observing an area of the body not visible from the outside, providing a set of images that reveal the presence of diseases and, if possible, provide a diagnosis. In recent years, several studies have been conducted to exploit artificial intelligence (AI) in biomedical images analysis and propose solutions for automatic diagnosis support systems. AI application in biomedical field deals with several tasks that differ in terms of purpose (classification, detection segmentation) and data involved (MRI, TC, PET). More in details, the research activities mostly focus on image registration, image detection and segmentation, image classification and image generation, proposing solutions that exploit the physiological characteristics of medical images.  In other words, “medical images are more than pictures” in which diagnostic-related information is not only associated with image texture.  

Collaborations

  • Rome Biomedical Campus University Foundation
  • Department of Advanced Biomedical Sciences, Università degli Studi di Napoli Federico II
  • Istituto Nazionale Tumori Fondazione Pascale
  • Division of Neonatology, Università degli Studi di Napoli Federico II 

Projects

  • Synergy-Net: Research and Digital Solutions in the Fight Against Oncological Diseases
  • QLUS project : Neonatal respiratory diseases assessment in lung ultrasound analysis  

Master Degree Theses

  • Deep learning approaches for detecting lung cancer on CT images (A. Dorano)
  • Generative Adversarial Networks for Domain Translation in medical imaging (P. Maione)
  • A physiologically-aware image disentangling for breast lesion classification in DCE-MRI (M.  D’Orso)
  • A subtyping and staging Machine Learning algorithm for detecting multiple sclerosis from MRI (S. Penna) 

References

  • Carlo Sansone, Full Professor (This email address is being protected from spambots. You need JavaScript enabled to view it.)
  • Michela Gravina, PhD student (This email address is being protected from spambots. You need JavaScript enabled to view it.)