Objectives To develop and validate APEX-NET for early diagnosis and severity stratification of acute pancreatitis (AP) using non-contrast CT (NCCT), by leveraging contrast-enhanced CT (CECT) feature learning. Materials and methods This five-center retrospective and prospective study included 3383 patients, comprising AP and Non-AP (abdominal pain patients and healthy individuals) patients. APEX-NET was trained and evaluated to perform pancreas segmentation, AP diagnosis (AP vs Non-AP), and severity prediction (mild, moderately severe, or severe per the revised Atlanta classification) using 3 internal and 2 external cohorts. A feature mapping module was employed to derive simulated CECT features from NCCT based on paired NCCT-CECT feature learning. The model was further evaluated with subgroup analyses, and a reader study was conducted by comparing its performance with six radiologists of varying experiences. Evaluation metrics included the Dice similarity coefficient, area under the receiver operating characteristic curve (AUC), and accuracy. Results For AP diagnosis, APEX-NET achieved AUCs of 0.949, 0.958, 0.981, and 0.955 in the validation, internal, and two external testing cohorts, respectively. For severity prediction, APEX-NET significantly outperformed the NCCT model (p < 0.05), with macro-average AUCs of 0.873 (validation) and 0.872 (internal testing). The advantage of APEX-NET had been demonstrated in almost all the age, gender, and etiology subgroups. In the reader study, APEX-NET performed comparably to senior radiologists and superior to junior radiologists (p < 0.05). Conclusion APEX-NET enables accurate NCCT-based diagnosis and early severity stratification of AP, demonstrating strong potential for clinical integration to overcome the inherent delay of CECT-based assessment. Key Points <Emphasis Type="BoldItalic">Question</Emphasis> The absence of an accurate method for predicting AP severity from early NCCT, the initial diagnostic scan, thus forgoing the critical intervention window. <Emphasis Type="BoldItalic">Findings</Emphasis> Achieve accurate severity prediction for AP by incorporating contrast-enhanced feature learning. Demonstrate robust performance across diverse demographic groups, etiologies, and imaging parameters. <Emphasis Type="BoldItalic">Clinical relevance</Emphasis> The APEX-NET, an integrated deep learning framework using NCCT, accelerated the diagnosis and severity stratification of AP, demonstrating performance comparable to senior radiologists and direct potential for clinical workflow integration by reducing reliance on delayed contrast-enhanced scans. Graphical Abstract

APEX-NET: automated pancreatic evaluation network using early non-contrast CT

期刊论文
发表日期：

2026年6月30日

查看全文

Fang Wang,
Zixing Huang,
Zhong Xue,
Qing Zhou,
Qian Li,
Yuxi Liu,
Jinjie Qin,
ShiZe Qin,
Yi Wang,
Dinggang Shen

摘要

Objectives

To develop and validate APEX-NET for early diagnosis and severity stratification of acute pancreatitis (AP) using non-contrast CT (NCCT), by leveraging contrast-enhanced CT (CECT) feature learning.

Materials and methods

This five-center retrospective and prospective study included 3383 patients, comprising AP and Non-AP (abdominal pain patients and healthy individuals) patients. APEX-NET was trained and evaluated to perform pancreas segmentation, AP diagnosis (AP vs Non-AP), and severity prediction (mild, moderately severe, or severe per the revised Atlanta classification) using 3 internal and 2 external cohorts. A feature mapping module was employed to derive simulated CECT features from NCCT based on paired NCCT-CECT feature learning. The model was further evaluated with subgroup analyses, and a reader study was conducted by comparing its performance with six radiologists of varying experiences. Evaluation metrics included the Dice similarity coefficient, area under the receiver operating characteristic curve (AUC), and accuracy.

Results

For AP diagnosis, APEX-NET achieved AUCs of 0.949, 0.958, 0.981, and 0.955 in the validation, internal, and two external testing cohorts, respectively. For severity prediction, APEX-NET significantly outperformed the NCCT model (p < 0.05), with macro-average AUCs of 0.873 (validation) and 0.872 (internal testing). The advantage of APEX-NET had been demonstrated in almost all the age, gender, and etiology subgroups. In the reader study, APEX-NET performed comparably to senior radiologists and superior to junior radiologists (p < 0.05).

Conclusion

APEX-NET enables accurate NCCT-based diagnosis and early severity stratification of AP, demonstrating strong potential for clinical integration to overcome the inherent delay of CECT-based assessment.

Key Points

Question The absence of an accurate method for predicting AP severity from early NCCT, the initial diagnostic scan, thus forgoing the critical intervention window.

Findings Achieve accurate severity prediction for AP by incorporating contrast-enhanced feature learning. Demonstrate robust performance across diverse demographic groups, etiologies, and imaging parameters.

Clinical relevance The APEX-NET, an integrated deep learning framework using NCCT, accelerated the diagnosis and severity stratification of AP, demonstrating performance comparable to senior radiologists and direct potential for clinical workflow integration by reducing reliance on delayed contrast-enhanced scans.

Graphical Abstract