This chapter is devoted to an overview of data preparation for clinical image analysis using artificial intelligence methods, particularly machine learning. Starting with image acquisition and the information it contains, concepts related to the quality of the data and its impact on the final analysis results are addressed. Methods of data preprocessing such as imputation of missing values, standardisation, harmonisation of multicentre data, dimensionality reduction, feature selection, up to the definition of a machine learning pipeline are discussed.
Data Preparation for AI Analysis / Barucci, Andrea; Diciotti, Stefano; Giannelli, Marco; Marzi, Chiara. - ELETTRONICO. - (2023), pp. 133-150. [10.1007/978-3-031-25928-9_7]
Data Preparation for AI Analysis
Marzi, ChiaraWriting – Original Draft Preparation
2023
Abstract
This chapter is devoted to an overview of data preparation for clinical image analysis using artificial intelligence methods, particularly machine learning. Starting with image acquisition and the information it contains, concepts related to the quality of the data and its impact on the final analysis results are addressed. Methods of data preprocessing such as imputation of missing values, standardisation, harmonisation of multicentre data, dimensionality reduction, feature selection, up to the definition of a machine learning pipeline are discussed.I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.