Differential EUS findings in focal type 1 autoimmune pancreatitis and pancreatic cancer
Bibliographic record
Abstract
Background and Objectives: Autoimmune pancreatitis (AIP) often mimics pancreatic cancer (PC), particularly if presenting as a focal lesion. EUS may orient the differential diagnosis between them. This study aims to identify EUS findings that might be useful to differentiate type 1 focal autoimmune pancreatitis (f-AIP1) and PC. Materials and Methods: F-AIP1 and PC patients were retrospectively collected, matched, and compared. EUS findings considered were: focal mass echogenicity, loss of lobularity, distal atrophy, peripancreatic hypoechoic margins (PHM), pancreatic duct dilation, duct-penetrating sign (DPS), pancreatic/common bile duct thickened walls (PD/CBD-TW), and vessel infiltration (VI). Elastography findings were also recorded. Variables with a P < 0.05 at univariate analysis were included in logistic multiple regression. Results: Fifteen patients with f-AIP and 60 with PC were studied. FE was hypoechoic in all patients from both groups. PHM was observed in 40% of f-AIP1 cases but not in PC ones (P < 0.001). DPS was found in 10/15 (66.7%) f-AIP1 and in 7/60 (11.7%) PC patients (P < 0.001). PD-TW and CBD-TW were observed in 66.7%/60% f-AIP1 cases and in 6.7%/13.6% PC patients, respectively (P < 0.001 for both comparisons). Pancreatic masses were significantly different at EUS elastography (elastic respectively in 71.4% f-AIP1 and 3.8% PC, P < 0.001). VI was suspected in 20% of f-AIPs and 85% of PCs (P < 0.001). At multiple regression, PD-TW, CBD-TW, elastic pattern, and the absence of VI independently supported a diagnosis of f-AIP1. Conclusions: Our results suggest that EUS findings deserve consideration in the diagnostic workup of AIP to improve the differential diagnosis with PC.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".