It is undeniable that we are living in the era of “omics.” Over the last decade, we have witnessed the emergence of various fields of study, such as genomics, proteomics, transcriptomics, metabolomics, and radiomics. Radiomics involves extracting a vast number of quantitative features from radiological images, resulting in an enormous amount of data for each image. This clearly underscores that we are also living in the era of big data. Data, which has always been the foundation of research, has now become the fuel that powers artificial intelligence models. Like all engines, artificial intelligence (AI) models also need to be fueled with high-quality data. Using good data is essential for building AI models that perform well. But what does it truly mean to source good data? Radiomics researchers have become data seekers, and finding high-quality data is not always straightforward. In the following paragraphs, we will examine the key steps in sourcing good data: starting with the generation of high-quality data during image acquisition, followed by a crucial preprocessing step to refine the data, and concluding with the selection of the data that truly matters through image segmentation.
Sourcing good data: from image acquisition to segmentation / Borgheresi, A., Mariotti, F., Agostini, A.. - (2026), pp. 9-37. [10.1016/B978-0-443-29242-2.00007-0]
Sourcing good data: from image acquisition to segmentation
Borgheresi A.Primo
;Mariotti F.;Agostini A.Ultimo
2026-01-01
Abstract
It is undeniable that we are living in the era of “omics.” Over the last decade, we have witnessed the emergence of various fields of study, such as genomics, proteomics, transcriptomics, metabolomics, and radiomics. Radiomics involves extracting a vast number of quantitative features from radiological images, resulting in an enormous amount of data for each image. This clearly underscores that we are also living in the era of big data. Data, which has always been the foundation of research, has now become the fuel that powers artificial intelligence models. Like all engines, artificial intelligence (AI) models also need to be fueled with high-quality data. Using good data is essential for building AI models that perform well. But what does it truly mean to source good data? Radiomics researchers have become data seekers, and finding high-quality data is not always straightforward. In the following paragraphs, we will examine the key steps in sourcing good data: starting with the generation of high-quality data during image acquisition, followed by a crucial preprocessing step to refine the data, and concluding with the selection of the data that truly matters through image segmentation.| File | Dimensione | Formato | |
|---|---|---|---|
|
Borgheresi_Sourcing-good-data-image_2026.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza d'uso:
Tutti i diritti riservati
Dimensione
1.58 MB
Formato
Adobe PDF
|
1.58 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


