Radiomics in differential diagnosis of pancreatic tumors

The aim of this study was to assess whether radiomics could predict histotype of pancreatic ductal adenocarcinomas (PDAC) and pancreatic neuroendocrine tumors (PNET). Contrast-enhanced CT scans of 193 patients were retrospectively reviewed, encompassing 97 PDACs and 96 PNETs. Additionally, anamnesti...

Full description

Saved in:
Bibliographic Details
Main Authors: Riccardo De Robertis, Beatrice Mascarin, Eda Bardhi, Flavio Spoto, Nicolò Cardobi, Mirko D’Onofrio
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:European Journal of Radiology Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352047725000188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850186783470387200
author Riccardo De Robertis
Beatrice Mascarin
Eda Bardhi
Flavio Spoto
Nicolò Cardobi
Mirko D’Onofrio
author_facet Riccardo De Robertis
Beatrice Mascarin
Eda Bardhi
Flavio Spoto
Nicolò Cardobi
Mirko D’Onofrio
author_sort Riccardo De Robertis
collection DOAJ
description The aim of this study was to assess whether radiomics could predict histotype of pancreatic ductal adenocarcinomas (PDAC) and pancreatic neuroendocrine tumors (PNET). Contrast-enhanced CT scans of 193 patients were retrospectively reviewed, encompassing 97 PDACs and 96 PNETs. Additionally, anamnestic data and laboratory data were evaluated. A total of 107 features were extracted for both the arterial and venous phases. ROC curves were constructed for the parameters with the highest AUC, considering two groups: one including all lesions and the other including only lesions smaller than 5 cm. The following feature differences were found to be statistically significant (p < 0.05). Without considering lesion size: for the arterial phase, 16 first-order and 38 s-order features; for the venous phase, 10 first-order and 20 s-order features. When considering lesion size: for the arterial phase, 16 first-order and 52 s-order features; for the venous phase, 11 first-order and 36 s-order features. The radiomics features with the highest AUC values included ART_firstorder_RootMeanSquared (AUC = 0.896, p < 0.01) in the arterial phase and VEN_firstorder_Median (AUC = 0.737, p < 0.05) in the venous phase for all lesions, and ART_firstorder_RootMeanSquared (AUC = 0.859, p < 0.01) and VEN_firstorder_Median (AUC = 0.713, p < 0.05) for lesions smaller than 5 cm. Texture analysis of pancreatic pathology has shown good predictability in defining the PNET histotype. This analysis potentially offering a non-invasive, imaging-based method to accurately differentiate between pancreatic tumor types. Such advancements could lead to more precise and personalized treatment planning, ultimately optimizing the use of medical resources.
format Article
id doaj-art-9f7a08d765104d9bb52697d8a1b49530
institution OA Journals
issn 2352-0477
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series European Journal of Radiology Open
spelling doaj-art-9f7a08d765104d9bb52697d8a1b495302025-08-20T02:16:17ZengElsevierEuropean Journal of Radiology Open2352-04772025-06-011410065110.1016/j.ejro.2025.100651Radiomics in differential diagnosis of pancreatic tumorsRiccardo De Robertis0Beatrice Mascarin1Eda Bardhi2Flavio Spoto3Nicolò Cardobi4Mirko D’Onofrio5Department of Radiology, G.B. Rossi Hospital, University of Verona, Piazzale L.A. Scuro 10, Verona 37134, ItalyDepartment of Radiology, University of Verona, Verona, Italy; Corresponding author.Department of Radiology, University of Verona, Verona, ItalyDepartment of Radiology, University of Verona, Verona, ItalyDepartment of Radiology, G.B. Rossi Hospital, University of Verona, Piazzale L.A. Scuro 10, Verona 37134, ItalyDepartment of Radiology, G.B. Rossi Hospital, University of Verona, Piazzale L.A. Scuro 10, Verona 37134, ItalyThe aim of this study was to assess whether radiomics could predict histotype of pancreatic ductal adenocarcinomas (PDAC) and pancreatic neuroendocrine tumors (PNET). Contrast-enhanced CT scans of 193 patients were retrospectively reviewed, encompassing 97 PDACs and 96 PNETs. Additionally, anamnestic data and laboratory data were evaluated. A total of 107 features were extracted for both the arterial and venous phases. ROC curves were constructed for the parameters with the highest AUC, considering two groups: one including all lesions and the other including only lesions smaller than 5 cm. The following feature differences were found to be statistically significant (p < 0.05). Without considering lesion size: for the arterial phase, 16 first-order and 38 s-order features; for the venous phase, 10 first-order and 20 s-order features. When considering lesion size: for the arterial phase, 16 first-order and 52 s-order features; for the venous phase, 11 first-order and 36 s-order features. The radiomics features with the highest AUC values included ART_firstorder_RootMeanSquared (AUC = 0.896, p < 0.01) in the arterial phase and VEN_firstorder_Median (AUC = 0.737, p < 0.05) in the venous phase for all lesions, and ART_firstorder_RootMeanSquared (AUC = 0.859, p < 0.01) and VEN_firstorder_Median (AUC = 0.713, p < 0.05) for lesions smaller than 5 cm. Texture analysis of pancreatic pathology has shown good predictability in defining the PNET histotype. This analysis potentially offering a non-invasive, imaging-based method to accurately differentiate between pancreatic tumor types. Such advancements could lead to more precise and personalized treatment planning, ultimately optimizing the use of medical resources.http://www.sciencedirect.com/science/article/pii/S2352047725000188RadiomicsPancreatic TumorsTexture AnalysisContrast-Enhanced CT ScansPancreatic Ductal AdenocarcinomaPancreatic Neuroendocrine Tumors
spellingShingle Riccardo De Robertis
Beatrice Mascarin
Eda Bardhi
Flavio Spoto
Nicolò Cardobi
Mirko D’Onofrio
Radiomics in differential diagnosis of pancreatic tumors
European Journal of Radiology Open
Radiomics
Pancreatic Tumors
Texture Analysis
Contrast-Enhanced CT Scans
Pancreatic Ductal Adenocarcinoma
Pancreatic Neuroendocrine Tumors
title Radiomics in differential diagnosis of pancreatic tumors
title_full Radiomics in differential diagnosis of pancreatic tumors
title_fullStr Radiomics in differential diagnosis of pancreatic tumors
title_full_unstemmed Radiomics in differential diagnosis of pancreatic tumors
title_short Radiomics in differential diagnosis of pancreatic tumors
title_sort radiomics in differential diagnosis of pancreatic tumors
topic Radiomics
Pancreatic Tumors
Texture Analysis
Contrast-Enhanced CT Scans
Pancreatic Ductal Adenocarcinoma
Pancreatic Neuroendocrine Tumors
url http://www.sciencedirect.com/science/article/pii/S2352047725000188
work_keys_str_mv AT riccardoderobertis radiomicsindifferentialdiagnosisofpancreatictumors
AT beatricemascarin radiomicsindifferentialdiagnosisofpancreatictumors
AT edabardhi radiomicsindifferentialdiagnosisofpancreatictumors
AT flaviospoto radiomicsindifferentialdiagnosisofpancreatictumors
AT nicolocardobi radiomicsindifferentialdiagnosisofpancreatictumors
AT mirkodonofrio radiomicsindifferentialdiagnosisofpancreatictumors