Scholarlink

Objective <p>We developed and evaluated a deep learning (DL) model for image-based detection of acute pancreatitis (AP) on abdominal contrast-enhanced CT (CECT).</p> Methods <p>A total of 552 patients from two university centers (January 2010–January 2026) were included. The internal dataset comprised 207 patients with clinically and radiologically confirmed AP (499 scans) and 250 control patients with suspected AP (368 scans). An independent external validation cohort included 95 patients. Convolutional neural network–based models were trained using monophasic and biphasic CECT data. The final model was evaluated on a 20% patient-level hold-out test set from the internal cohort and on the external cohort. Performance was assessed using the F1 score and area under the receiver operating characteristic curve (AUROC).</p> Results <p>A single-input multiphase model incorporating arterial and portal venous phase scans achieved the best performance, with ensembling applied for biphasic studies. On the internal hold-out test set (<i>n</i> = 116), the model achieved an F1 score of 0.83 (95% confidence interval 0.75–0.89) and an AUROC of 0.89 (0.82–0.95). Performance remained robust on external validation (<i>n</i> = 95), with an AUROC of 0.99 (0.96–1.00) and an F1 score of 0.92 (0.86–0.97).</p> Conclusion <p>DL enabled accurate CECT-based identification of AP in this retrospective multicenter cohort, with performance maintained in an independent external dataset. Prospective validation using broader and independently adjudicated clinical populations remains necessary.</p> Relevance statement <p>The model showed promising performance for CECT-based acute pancreatitis detection but was not designed or tested as a triage system.</p> Key Points <p><UnorderedList Mark="Bullet"> <ItemContent> <p>Diagnostic uncertainty in acute pancreatitis often arises from nonspecific abdominal symptoms and inter-reader variability in CECT interpretation.</p> </ItemContent> <ItemContent> <p>The DL model achieved high internal accuracy (AUROC 0.89) and maintained robust performance in an independent external validation cohort (AUROC 0.99).</p> </ItemContent> </UnorderedList></p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning-based detection of acute pancreatitis on abdominal contrast-enhanced CT

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月31日

查看全文
  • Oleksandra Seidel,
  • Maike Theis,
  • Sebastian Nowak,
  • Laura Garajová,
  • Benjamin Wulff,
  • Wolfgang Block,
  • Lukas Müller,
  • Tilmann Emrich,
  • Julian A. Luetkens,
  • Dariusch R. Hadizadeh,
  • Alois M. Sprinkart,
  • Dmitrij Kravchenko

摘要

Objective

We developed and evaluated a deep learning (DL) model for image-based detection of acute pancreatitis (AP) on abdominal contrast-enhanced CT (CECT).

Methods

A total of 552 patients from two university centers (January 2010–January 2026) were included. The internal dataset comprised 207 patients with clinically and radiologically confirmed AP (499 scans) and 250 control patients with suspected AP (368 scans). An independent external validation cohort included 95 patients. Convolutional neural network–based models were trained using monophasic and biphasic CECT data. The final model was evaluated on a 20% patient-level hold-out test set from the internal cohort and on the external cohort. Performance was assessed using the F1 score and area under the receiver operating characteristic curve (AUROC).

Results

A single-input multiphase model incorporating arterial and portal venous phase scans achieved the best performance, with ensembling applied for biphasic studies. On the internal hold-out test set (n = 116), the model achieved an F1 score of 0.83 (95% confidence interval 0.75–0.89) and an AUROC of 0.89 (0.82–0.95). Performance remained robust on external validation (n = 95), with an AUROC of 0.99 (0.96–1.00) and an F1 score of 0.92 (0.86–0.97).

Conclusion

DL enabled accurate CECT-based identification of AP in this retrospective multicenter cohort, with performance maintained in an independent external dataset. Prospective validation using broader and independently adjudicated clinical populations remains necessary.

Relevance statement

The model showed promising performance for CECT-based acute pancreatitis detection but was not designed or tested as a triage system.

Key Points

Diagnostic uncertainty in acute pancreatitis often arises from nonspecific abdominal symptoms and inter-reader variability in CECT interpretation.

The DL model achieved high internal accuracy (AUROC 0.89) and maintained robust performance in an independent external validation cohort (AUROC 0.99).

Graphical Abstract