Artificial Intelligence in Interventional Radiology: A Literature Review and Future Perspectives.

Roberto Iezzi,R Manfredi,S N Goldberg,V Valentini,B Merlino,A Posa

doi:10.1155/2019/6153041

Abstract

The term “artificial intelligence” (AI) includes computational algorithms that can perform tasks considered typical of human intelligence, with partial to complete autonomy, to produce new beneficial outputs from specific inputs. The development of AI is largely based on the introduction of artificial neural networks (ANN) that allowed the introduction of the concepts of “computational learning models,” machine learning (ML) and deep learning (DL). AI applications appear promising for radiology scenarios potentially improving lesion detection, segmentation, and interpretation with a recent application also for interventional radiology (IR) practice, including the ability of AI to offer prognostic information to both patients and physicians about interventional oncology procedures. This article integrates evidence-reported literature and experience-based perceptions to assist not only residents and fellows who are training in interventional radiology but also practicing colleagues who are approaching to locoregional mini-invasive treatments.

Highlights

E term “artificial intelligence” (AI) includes computational algorithms that can perform tasks considered typical of human intelligence, with partial to complete autonomy, to produce new beneficial outputs from specific inputs. e development of AI is largely based on the introduction of artificial neural networks (ANN) that allowed the introduction of the concepts of “computational learning models,” machine learning (ML) and deep learning (DL)
It has been quite clear that computers could be potentially useful in assisting the radiologist in the routine tasks of detection and diagnosis. e idea fostering the use of the so-called computer-aided detection/ diagnosis (CAD) systems, precursors of modern AI, was to provide radiologists with the assistance in the detection and interpretations of potential lesions in order to discriminate between benign and malignant lesions, reduce false negatives, and boost radiologists’ productivity, Journal of Oncology especially in terms of discovery and identification of significant findings requiring a prompt human validation [3]
E development of AI is largely based on the introduction of artificial neural networks (ANN) in the early 1950s [4] and their subsequent further evolution, introducing the concepts of “computational learning models,” machine learning (ML) and deep learning (DL)

Summary

Introduction

Academic Editor: Francesca De Felice e term “artificial intelligence” (AI) includes computational algorithms that can perform tasks considered typical of human intelligence, with partial to complete autonomy, to produce new beneficial outputs from specific inputs. e development of AI is largely based on the introduction of artificial neural networks (ANN) that allowed the introduction of the concepts of “computational learning models,” machine learning (ML) and deep learning (DL). E term “artificial intelligence” (AI) includes computational algorithms that can perform tasks considered typical of human intelligence, with partial to complete autonomy, to produce new beneficial outputs from specific inputs.

Results

Conclusion