Multi-center evaluation of radiomics and deep learning to stratify malignancy risk of IPMNs

The fusion model, which combines DL with radiomics features from routine T2W MRI, shows promise for objective, cyst-level risk stratification of IPMNs in a multi-center cohort, outperforming radiomics-only models and nearly matching expert radiologists using only T2W and T1-weighted (T1W) sequences. While performance requires improvement for standalone clinical use, this approach offers a scalable, non-invasive method to potentially improve diagnostic accuracy and reduce unnecessary surgical interventions.

Authors

Institutions

Publication Details

Journal
Abdominal Radiology
Published
2026-01-12
DOI
https://doi.org/10.1007/s00261-025-05371-3
Primary Topic
Pancreatic and Hepatic Oncology Research
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Multi-center evaluation of radiomics and deep learning to stratify malignancy risk of IPMNs

Emil Agarunov, Ivo G. Schoots, Pallavi Tiwari, A Medetalibeyoglu et al.
Abdominal Radiology
Pancreatic and Hepatic Oncology Research
article

Multi-center evaluation of radiomics and deep learning to stratify malignancy risk of IPMNs

Emil Agarunov, Ivo G. Schoots, Pallavi Tiwari, A Medetalibeyoglu, Candice W. Bolan, Andrea Bejar, Görkem DURAK, Chao Chen, Zheyuan Zhang, MJ Bruno, Bagci Ulas, Ziliang Hong, Ziyue Xu, Halil Ertugrul Aktas, Gulbiz Dagoglu Kartal, Fergan Bol, Lili Zhao, Elif Keles, Sachin Jambawalikar, Hongyi Pan, Michael B Wallace, Rajesh N Keswani, Tamas Gonda, Zeynep Sue Jozwiak, Sukru Mehmet Erturk, Frank H Miller, Chenchang Huang, Yury Velichko, Maria Jaramillo Gonzalez
article en

Abstract

The fusion model, which combines DL with radiomics features from routine T2W MRI, shows promise for objective, cyst-level risk stratification of IPMNs in a multi-center cohort, outperforming radiomics-only models and nearly matching expert radiologists using only T2W and T1-weighted (T1W) sequences. While performance requires improvement for standalone clinical use, this approach offers a scalable, non-invasive method to potentially improve diagnostic accuracy and reduce unnecessary surgical interventions.

Abdominal Radiology
Northwestern University (US), University of Wisconsin–Madison (US), Stony Brook University Hospital (US), Jacksonville College (US), Erasmus MC (NL), WinnMed (US), University of Catania (IT), Bakırköy Dr.Sadi Konuk Eğitim ve Araştırma Hastanesi (TR), Nvidia (United States) (US), William S. Middleton Memorial Veterans Hospital (US), Mayo Clinic in Florida (US), Northwestern Medicine (US), New York University (US), Istanbul University (TR), Columbia University (US), Erasmus University Rotterdam (NL)
Wisconsin Alumni Research Foundation, National Institutes of Health
Reduced inequalities
Openalex Percentile: Top 91%
Pancreatic and Hepatic Oncology Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.