NornirNet: A Deep Learning Framework to Distinguish Benign from Malignant Type II Endoleaks Using Preoperative Imaging
Authors:
- Francesco AndreoliFAFrancesco Andreoli
- Fabio MattiussiFabio Mattiussi
- Elias WassehEWElias Wasseh
- Andrea LeonciniAndrea Leoncini
- Ludovica EttorreLELudovica Ettorre
- Jacopo GalafassiJGJacopo Galafassi
- Maria Antonella RuffinoMRMaria Antonella Ruffino
- Luca GiovannacciLGLuca Giovannacci
- Alessandro RobaldoARAlessandro Robaldo
- Giorgio ProuseGPGiorgio Prouse
Preprint
- 2 December 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Background/Objectives: Type II endoleak (T2EL) remains the most frequent complication after endovascular aortic aneurysm repair (EVAR), with uncertain clinical relevance and management. While most resolve spontaneously, persistent T2ELs can lead to sac enlargement and rupture risk. This study proposes a deep learning framework for preoperative prediction of T2EL occurrence and severity using volumetric computed tomography angiography (CTA) data.Methods: A retrospective analysis of 287 patients undergoing standard EVAR (2010–2024) was performed. Preoperative CTA scans were processed for volumetric normalization and fed into a 3D convolutional neural network (CNN) trained to classify patients into three categories: no T2EL, benign T2EL, or malignant T2EL. The model was trained on 224 cases, validated on 33, and tested on an independent cohort of 30 patients. Performance metrics included accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC).Results: The CNN achieved an overall accuracy of 76.7% (95% CI: 0.63–0.90), macro-averaged F1-score of 0.77, and AUC of 0.93. Class-specific AUCs were 0.93 for no T2EL, 0.91 for benign, and 0.96 for malignant cases, confirming high discriminative capacity across outcomes. Most misclassifications occurred between adjacent categories.Conclusion: This study introduces the first end-to-end 3D CNN capable of predicting both presence and severity of T2EL directly from preoperative CTA, without manual segmentation or handcrafted features. These findings suggest that preoperative imaging encodes latent structural information predictive of endoleak-driven sac reperfusion, potentially enabling personalized pre-emptive embolization strategies and tailored surveillance after EVAR.Keywords
All Related Versions
- Version 1, 2025-12-02, Preprints
- Published version: AI, 7 (2), 57.
This publication has 28 references indexed in Scilit:
- Editor's Choice -- European Society for Vascular Surgery (ESVS) 2024 Clinical Practice Guidelines on the Management of Abdominal Aorto-Iliac Artery AneurysmsEuropean Journal of Vascular and Endovascular Surgery, 2024
- Impact of Multidisciplinary Team Meetings on Decision Making in Vascular Surgery: A Prospective Observational StudyEuropean Journal of Vascular and Endovascular Surgery, 2023
- Incidence, Long Term Clinical Outcomes, and Risk Factor Analysis of Type III Endoleaks Following Endovascular Repair of Abdominal Aortic AneurysmEuropean Journal of Vascular and Endovascular Surgery, 2023
- Tailored Sac Embolization During EVAR for Preventing Persistent Type II EndoleakAnnals of Vascular Surgery, 2021
- Type 2 Endoleak With or Without Intervention and Survival After Endovascular Aneurysm RepairEuropean Journal of Vascular and Endovascular Surgery, 2021
- Editor's Choice – Systematic Review and Meta-Analysis of the Outcome of Treatment for Type II Endoleak Following Endovascular Aneurysm RepairEuropean Journal of Vascular and Endovascular Surgery, 2018
- Type II Endoleak after Endovascular Aneurysm Repair: Natural History and Treatment OutcomesAnnals of Vascular Surgery, 2017
- Meta-analysis of individual-patient data from EVAR-1, DREAM, OVER and ACE trials comparing outcomes of endovascular or open repair for abdominal aortic aneurysm over 5 yearsBritish Journal of Surgery, 2017
- Endoleak detection using single-acquisition split-bolus dual-energy computer tomography (DECT)European Radiology, 2016
- Analysis of anatomical risk factors for persistent type II endoleaks following endovascular abdominal aortic aneurysm repair using CT angiographySurgery Today, 2015