Image-Based Artificial Intelligence for Preoperative Differentiation of Pancreatic Cancer from Pancreatitis: A Systematic Review and Meta-Analysis

Juan Lu¹Haiyi Zhang²Zhengzhen Yuan³Jiajun Yue²Wei Deng³Qi Yao²Yong Liu²Pingping Jie²Min Fan²Jie Zhao^2*

• ¹The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University, Luzhou , China, Southwest Medical University, Luzhou, China
• ²The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University, Luzhou, China
• ³School of Physical Education, Southwest Medical University,, Luzhou, China

Background: Pancreatic cancer (PC) and pancreatitis—encompassing acute, chronic, autoimmune, and other inflammatory pancreatic conditions—often exhibit overlapping clinical and imaging features, yet require fundamentally different therapeutic strategies. This similarity frequently leads to diagnostic uncertainty in routine clinical practice. Image-based artificial intelligence (AI) has emerged as a promising tool to enhance diagnostic accuracy. This meta-analysis systematically evaluates the diagnostic performance of AI algorithms in differentiating PC from pancreatitis. Methods: A systematic literature search of PubMed, Embase, and Cochrane Library databases was conducted for studies published through June 30 2025. Eligible studies reporting AI diagnostic performance metrics were selected. Methodological rigor was assessed using the modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Pooled sensitivity (SEN), specificity (SPE), positive/negative likelihood ratios (+LR/-LR), diagnostic odds ratio (DOR), and summary receiver operating characteristic (SROC) curves were derived using Stata 17.0 software. Results: Twenty-five eligible studies (3279 patients) were ultimately eligible for data extraction, of which sixty-eight tables were included in this meta-analysis. The pooled SEN was 89% (95% CI: 87–90%), SPE was 88% (95% CI: 86–90%), and AUC was 0.94 (95% CI: 0.92–0.96) in 28 included studies with 76 contingency tables, however, substantial heterogeneity was observed among the included studies, with I² = 77.14% in SEN and I² = 75.61% in SPE. The pooled SEN and SPE were 91% (95% CI: 88–93%) and 90% (95% CI: 87–93%), with an AUC of 0.96 (95% CI: 0.94–0.97) in 28 included studies with 28 best diagnosis performance tables. Analysis for different algorithms revealed a pooled SEN of 89% (95%CI: 86−90%) and SPE of 88% (95%CI: 86−90%) for machine learning, and a pooled SEN of 89% (95%CI: 82−93%) and SPE of 85% (95%CI: 76−91%) for deep learning. Subsequent subgroup analysis suggested that part of the heterogeneity might be explained by differences in Algorithm, Imaging Modality, Publication Geographical, and Year of publication. Conclusion: AI-based image analysis demonstrates strong diagnostic performance in distinguishing PC from pancreatitis, exceeding thresholds typically achieved with conventional imaging alone. These findings support the potential integration of AI into clinical decision-support workflows to improve the preoperative evaluation of pancreatic lesions.