Diagnostic performance of F-18 FDG PET/CT in differentiating autoimmune pancreatitis from pancreatic cancer: a systemic review and meta-analysis.

OBJECTIVES: This study aims to evaluate the utility of F-18 FDG PET/CT in the non-invasive diagnosis of autoimmune pancreatitis (AIP) and differentiating it from pancreatic cancer (CaP) based on the amount and pattern of FDG uptake, as well as involvement of extra-pancreatic sites. METHODS: A systematic search was conducted using PubMed, Scopus, Cochrane Library and Google Scholar. Only those studies that compared the findings of F-18 FDG PET/CT in terms of SUVmax, pattern of FDG uptake and presence of FDG-avid extra-pancreatic sites in both AIP and CaP were included. Studies were qualitatively assessed for risk of bias and publication bias. The diagnostic performance of parameters on PET/CT was examined through pooled sensitivity, specificity, diagnostic odd's ratio (DOR) and summary receiver operator characteristic (SROC) curve analysis. RESULTS: Six studies were included with a total of 580 patients. 178 patients had AIP (Age 18-90 years, male, M: female, F ratio-8.4:1) and 402 patients had CaP (Age 22-88 years, M:F ratio-1.5:1). Type of AIP was reported in only 3 studies, with the included cases predominantly being type 1 AIP. All studies were retrospective with heterogeneity and a risk on patient selection and index test. The FDG uptake, expressed as SUVmax, was lower in AIP with a weighted mean difference of -3.11 (95% confidence interval, CI: -5.28 to -0.94). To diagnose AIP, the pooled sensitivity, specificity and DOR of diffuse pattern of FDG uptake were 0.59 (95% CI: 0.51-0.66), 0.89 (95% CI: 0.86-0.92) and 21.07 (95% CI: 5.07-88.32), respectively, with an area under curve (AUC) of 0.717 on SROC analysis. The pooled sensitivity, specificity and DOR of FDG-avid extra pancreatic sites were 0.55 (95% CI: 0.45-0.65), 0.58 (95% CI: 0.52-0.64) and 2.33 (95% CI: 1.40-3.89), respectively, with an AUC of 0.632. CONCLUSION: On F-18 FDG PET/CT, a pancreatic lesion of AIP has a lower SUVmax value than CaP. A diffuse pattern of FDG uptake and presence of an extra-pancreatic FDG-avid site are nearly 21 times and twice more likely in AIP than CaP, respectively.

Differentiation of autoimmune pancreatitis from pancreatic adenocarcinoma using CT characteristics: a systematic review and meta-analysis.

OBJECTIVES: To determine informational CT findings for distinguishing autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC) and to review their diagnostic accuracy. METHODS: A systematic and detailed literature review was performed through PubMed, EMBASE, and the Cochrane library. Similar descriptors to embody the identical image finding were labeled as a single CT characteristic. We calculated the pooled diagnostic odds ratios (DORs) of each CT characteristic using a bivariate random-effects model. RESULTS: A total of 145 various descriptors from 15 studies (including 562 AIP and 869 PDAC patients) were categorized into 16 CT characteristics. According to the pooled DOR, 16 CT characteristics were classified into three groups (suggesting AIP, suggesting PDAC, and not informational). Seven characteristics suggesting AIP were diffuse pancreatic enlargement (DOR, 48), delayed homogeneous enhancement (DOR, 46), capsule-like rim (DOR, 34), multiple pancreatic masses (DOR, 16), renal involvement (DOR, 15), retroperitoneal fibrosis (DOR, 13), and bile duct involvement (DOR, 8). Delayed homogeneous enhancement showed a pooled sensitivity of 83% and specificity of 85%. The other six characteristics showed relatively low sensitivity (12-63%) but high specificity (93-99%). Four characteristics suggesting PDAC were discrete pancreatic mass (DOR, 23), pancreatic duct cutoff (DOR, 16), upstream main pancreatic duct dilatation (DOR, 8), and upstream parenchymal atrophy (DOR, 7). CONCLUSION: Eleven CT characteristics were informational to distinguish AIP from PDAC. Diffuse pancreatic enlargement, delayed homogeneous enhancement, and capsule-like rim suggested AIP with the highest DORs, whereas discrete pancreatic mass suggested PDAC. However, pooled sensitivities of informational CT characteristics were moderate. CLINICAL RELEVANCE STATEMENT: This meta-analysis underscores eleven distinctive CT characteristics that aid in differentiating autoimmune pancreatitis from pancreatic adenocarcinoma, potentially preventing misdiagnoses in patients presenting with focal/diffuse pancreatic enlargement. KEY POINTS: • Diffuse pancreatic enlargement (pooled diagnostic odds ratio [DOR], 48), delayed homogeneous enhancement (46), and capsule-like rim (34) were CT characteristics suggesting autoimmune pancreatitis. • The CT characteristics suggesting autoimmune pancreatitis, except delayed homogeneous enhancement, had a general tendency to show relatively low sensitivity (12-63%) but high specificity (93-99%). • Discrete pancreatic mass (pooled diagnostic odds ratio, 23) was the CT characteristic suggesting pancreatic ductal adenocarcinoma with the highest pooled DORs.

Concomitant Pancreatic Ductal Adenocarcinoma and Type 1 Autoimmune Pancreatitis: A Potential Issue in the Diagnosis of Carcinoma by Endoscopic Ultrasound-guided Fine-needle Biopsy.

We herein report a 64-year-old man with concomitant pancreatic ductal adenocarcinoma (PDAC) and type 1 autoimmune pancreatitis (AIP). An endoscopic ultrasound-guided fine-needle biopsy (EUS-FNB) from the pancreatic head mass revealed level 2 histology of AIP and atypical glands. We diagnosed definitive focal AIP using the clinical diagnostic criteria. Computed tomography revealed that the pancreatic mass had not been reduced by steroid therapy. Surgery was performed after a histological PDAC diagnosis was made via a transpapillary biliary biopsy. The resected specimen revealed PDAC associated with AIP. It is important to consider the cooccurrence of PDAC and AIP even if the histological diagnosis via an EUS-FNB is AIP.

Radiomics based on diffusion-weighted imaging for differentiation between focal-type autoimmune pancreatitis and pancreatic carcinoma.

OBJECTIVE: To evaluate the parameters of support vector machine (SVM) using imaging data generated from the apparent diffusion coefficient (ADC) to differentiate between focal-type autoimmune pancreatitis (f-AIP) and pancreatic ductal adenocarcinoma (PDAC) when using SVM based on diffusion-weighted imaging. METHODS: The 2D-ADCmean and texture parameters (16 texture features × [non-filter+17 filters]) were retrospectively segmented by 2 readers in 28 patients with f-AIP and 77 patients with pathologically proven PDAC. The diagnostic accuracy of the SVM model was evaluated by receiver operating characteristic curve analysis and calculation of the area under the curve (AUC). Interreader reliability was assessed by intraclass correlation coefficient (ICC). RESULTS: The 2D-ADCmean and 3D-ADCmean were significantly lower in cases of f-AIP (1.10-1.15 × 10-3 mm2/s and 1.21-1.23× 10-3 mm2/s, respectively) vs PDAC (1.29-1.33 × 10-3 mm2/s and 1.41-1.43 × 10-3 mm2/s, respectively), with excellent and good interreader reliability, respectively (ICC = 0.909 and 0.891, respectively). Among the texture parameters, energy with exponential filtering yielded the highest AUC (Reader 1: 74.7%, Reader 2: 81.5%), with fair interreader reliability (ICC = 0.707). The non-linear SVM, a combination of 2D-ADCmean, object volume and exponential-energy showed an AUC value of 96.2% in the testing cohorts. CONCLUSION: Our results suggest that non-linear SVM using a combination of 2D-ADCmean, object volume, and exponential-energy may assist in differentiating f-AIP from PDAC. ADVANCES IN KNOWLEDGE: The radiomics based on an apparent diffusion coefficient value may assist in differentiating f-AIP from PDAC.

Analysis of Clinical, Serological, and Imaging Features of Autoimmune Pancreatitis and a Case-Control Study on Prognostic Factors in Response to Hormone Therapy.

Objective: The paper aimed to analyze the clinical, serological, and imaging features of autoimmune pancreatitis (AIP) and the prognostic factors affecting hormone therapy. Methods: A total of 106 patients with AIP enrolled in our hospital from March 2016 to August 2018 were treated with the hormone. The curative effect and recurrence were followed up. The patients were divided into relapse group (n = 42) and nonrelapse group (n = 64) according to the recurrence within 3 years after initial hormone therapy. The symptoms and signs, laboratory examination, and treatment were compared, and binary logistic regression was employed to explore the risk factors of AIP recurrence. Results: Among the 106 patients included in this study, there were 78 males and 28 females, with a male-to-female ratio of 3:1. The average age of onset was 56.25 ± 8.87 years; the minimum age was 39 years; and the maximum age was 7 years. The main clinical symptoms were jaundice (67.92%), abdominal pain (48.11%), and abdominal distension (33.96%). In addition, there were symptoms of weight loss, nausea, vomiting, itching, and gray stool. Previous complications included 27.35% diabetes (29/106), 22.64% hypertension (24/106), 35.84% smoking (38/106), and 28.30% alcohol consumption (30/106). The serological characteristics were mainly the increase in serum IgG4 level; 92.45% (98/106) level was higher compared to the upper limit of normal value; the median level was 11.65 g/L; and the highest level was 35.79 g/L. A total of 88.67% (94/106) had an abnormal liver function. The results of imaging examination indicated that 58.49% (62/106) of extrapancreatic organs were involved, of which 46.22% (49/106) were the most common bile duct involvement. All the patients in the group reached a state of remission after hormone treatment. After the disease was relieved, the patients were followed up for 3 years. The recurrence rate was 39.62% (42/106), and the median time of recurrence (month) was 9 (range 2-36). The recurrence rates within 1, 2, and 3 years were 20.75%, 31.13%, and 39.62%, respectively. Among the recurrent patients, 52.38% (22/42) relapsed within 1 year, 78.57% (33/42) within 2 years, and 100.00% (42/42) within 3 years. Multivariate analysis showed that the short duration of glucocorticoid therapy and involvement of extrapancreatic organs were risk factors for relapse after glucocorticoid therapy in patients with type I AIP. Conclusion: Type 1 AIP is more common in middle-aged and elderly men. The clinical symptoms of jaundice, abdominal pain, and abdominal distension are common, often accompanied by involvement of extrapancreatic organs, of which bile duct involvement is the most common. Type 1 AIP glucocorticoid treatment acceptance and disease remission are better, but the recurrence rate is higher after glucocorticoid treatment. Patients with a short time of glucocorticoid treatment and involvement of extrapancreatic organs may have a higher risk of recurrence.

The effect of CT texture-based analysis using machine learning approaches on radiologists' performance in differentiating focal-type autoimmune pancreatitis and pancreatic duct carcinoma.

PURPOSE: To develop a support vector machine (SVM) classifier using CT texture-based analysis in differentiating focal-type autoimmune pancreatitis (AIP) and pancreatic duct carcinoma (PD), and to assess the radiologists' diagnostic performance with or without SVM. MATERIALS AND METHODS: This retrospective study included 50 patients (20 patients with focal-type AIP and 30 patients with PD) who underwent dynamic contrast-enhanced CT. Sixty-two CT texture-based features were extracted from 2D images of the arterial and portal phase CTs. We conducted data compression and feature selections using principal component analysis (PCA) and produced the SVM classifier. Four readers participated in this observer performance study and the statistical significance of differences with and without the SVM was assessed by receiver operating characteristic (ROC) analysis. RESULTS: The SVM performance indicated a high performance in differentiating focal-type AIP and PD (AUC = 0.920). The AUC for all 4 readers increased significantly from 0.827 to 0.911 when using the SVM outputs (p = 0.010). The AUC for inexperienced readers increased significantly from 0.781 to 0.905 when using the SVM outputs (p = 0.310). The AUC for experienced readers increased from 0.875 to 0.912 when using the SVM outputs, however, there was no significant difference (p = 0.018). CONCLUSION: The use of SVM classifier using CT texture-based features improved the diagnostic performance for differentiating focal-type AIP and PD on CT.

Systematic review and meta-analysis of MRI features for differentiating autoimmune pancreatitis from pancreatic adenocarcinoma.

OBJECTIVES: To identify reliable MRI features for differentiating autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC) and to summarize their diagnostic accuracy. METHODS: We conducted a systematic literature review and meta-analysis using PubMed, EMBASE, and the Cochrane Library to identify original articles published between January 2006 and July 2021. The pooled diagnostic accuracy, including the diagnostic odds ratios (DORs) with 95% confidence intervals (CIs) of the identified features, was calculated using a bivariate random effects model. RESULTS: Twelve studies were included, and 92 overlapping descriptors were subsumed under 16 MRI features. Ten features favoring AIP were diffuse enlargement (DOR, 75; 95% CI, 9-594), capsule-like rim (DOR, 52; 95% CI, 20-131), multiple main pancreatic duct (MPD) strictures (DOR, 47; 95% CI, 17-129), homogeneous delayed enhancement (DOR, 46; 95% CI, 21-104), low apparent diffusion coefficient value (DOR, 30), speckled enhancement (DOR, 30), multiple pancreatic masses (DOR, 29), tapered narrowing of MPD (DOR, 15), penetrating duct sign (DOR, 14), and delayed enhancement (DOR, 13). Six features favoring PDAC were target type enhancement (DOR, 41; 95% CI, 11-158), discrete pancreatic mass (DOR, 35; 95% CI, 15-80), upstream MPD dilatation (DOR, 13), peripancreatic fat infiltration (DOR, 10), upstream parenchymal atrophy (DOR, 5), and vascular involvement (DOR, 3). CONCLUSION: This study identified 16 informative MRI features to differentiate AIP from PDAC. Among them, diffuse enlargement, capsule-like rim, multiple MPD strictures, and homogeneous delayed enhancement favored AIP with the highest DORs, whereas discrete mass and target type enhancement favored PDAC. KEY POINTS: • The MRI features with the highest pooled diagnostic odds ratios (DORs) for autoimmune pancreatitis were diffuse enlargement of the pancreas (75), capsule-like rim (52), multiple strictures of the main pancreatic duct (47), and homogeneous delayed enhancement (46). • The MRI features with the highest pooled DORs for pancreatic ductal adenocarcinoma were target type enhancement (41) and discrete pancreatic mass (35).

Diffuse Involvement of Pancreas is not Always Autoimmune Pancreatitis.

RATIONALE AND OBJECTIVES: To determine the prevalence of diffuse involvement of pancreas and to identify the findings of malignancies using enhancement computed tomography (CT). MATERIALS AND METHODS: A total of 1,0249 patients performed enhancement CT in our hospital over 62 months were investigated and the final study cohort includes 245 patients (170 males, 75 females; mean age, 56.94 ± 12.17 years). The reference standard is the final clinical/pathological diagnosis. The lesion-to-aorta enhancement ratio (LAR) on the pancreatic arterial phase, portal phase and delayed phase (DP) and the traditional CT findings were evaluated. Intergroup comparisons between malignancies and non-malignancies lesions were performed. Univariate and multivariate analyses were conducted to identify findings predicting malignancies. RESULTS: The prevalence of malignancy was 45.3% (111/245) of diffuse enlargement of pancreas. All benign lesions were autoimmune pancreatitis 54.7% (n = 134). The most common malignant lesion was pancreatic ductal adenocarcinoma (n = 88, 35.9%). Other rare lesions with malignant potential included pancreatic neuroendocrine tumor (n = 11, 4.5%), lymphoma (n = 4, 1.6%), metastasis (n = 4, 1.6%), solid pseudopapillary neoplasm (n = 3, 1.2%) and acinar cell carcinoma (n = 1, 0.4%). Residual normal pancreas parenchyma, heterogeneity, short axis (cut-off value, 3.15 cm) and LARDP (cut-off value, 0.75) were independent predictors of malignancies. When the above predictors were combined, a sensitivity of 94.2%, a specificity of 90.8% were attained. CONCLUSION: Diffuse involvement of the pancreas is rare and is not a specific sign of autoimmune pancreatitis, and it is associated with a wide spectrum of malignant conditions. Dynamic enhancement CT is helpful to identifying malignancies.

MRI features for differentiation of autoimmune pancreatitis from pancreatic ductal adenocarcinoma: A systematic review and meta-analysis.

BACKGROUND AND AIMS: The accurate differential diagnosis between autoimmune pancreatitis (AIP) and pancreatic ductal adenocarcinoma (PDAC) is clinically important. We aimed to determine significant MRI features for differentiating AIP from PDAC, including assessment of diffusion-weighted imaging (DWI). METHODS: We performed a systematic search using three databases. The pooled diagnostic odds ratio was calculated using a bivariate random effects model to determine significant MRI features for differentiating AIP from PDAC. The pooled sensitivity and specificity were calculated. The qualitative systematic review for DWI assessment was performed. RESULTS: Of nine studies (775 patients), multiple main pancreatic duct (MPD) strictures, absence of upstream marked MPD dilatation, peripancreatic rim, and duct penetration sign were significant MRI features for differentiating AIP from PDAC. Absence of MPD dilatation had the highest pooled sensitivity (87%, 95% CI=68-96%), whereas peripancreatic rim had the highest pooled specificity (100%, 95% CI=88-100%). Of 12 studies evaluating DWI, seven reported statistically significant differences in apparent diffusion coefficient (ADC) values between AIP and PDAC; however, four reported lower ADC values in AIP than in PDAC, but three reported the opposite result. CONCLUSION: The four significant MRI features can be useful to differentiate AIP from PDAC, but DWI assessment might be limited.

Use of MRI signal intensity ratio to differentiate between autoimmune pancreatitis and pancreatic ductal adenocarcinoma.

AIM: To evaluate the accuracy of the lesion-to-erector spinae signal intensity ratio (SIR) on magnetic resonance imaging (MRI) for distinguishing autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDA). MATERIALS AND METHODS: The MRI data of 21 patients with AIP and 27 patients with PDA were analysed retrospectively, and the signal intensity in pancreatic lesions and erector spinae muscles at the same level on T2-weighted imaging (T2WI), arterial phase (AP) imaging, and delayed phase (DP) imaging was measured for calculation of SIRs. RESULTS: The mean SIRs of the pancreatic lesions and erector spinae from T2WI, AP, and DP images of AIP patients were 0.96, 1.27, and 1.42, respectively, while those of PDA patients were 1.35, 0.80, and 0.91, respectively. The differences in the SIRs between the AIP and PDA groups were statistically significant (p<0.001), with corresponding area under curve (AUC) values of 0.925, 0.906, and 0.961, respectively. The optimal cut-off values for the SIRs on T2WI, AP and DP images were 1.21, 1.01, and 1.08, respectively. SIR values < 1.21 on T2WI, >1.01 on AP imaging, and >1.08 on DP imaging identified AIP with sensitivities of 85.7%, 90.5%, and 90.5%, respectively, and specificities of 81.5%, 74.6%, and 81.5%, respectively. The AUC values for SIRs did not differ significantly between T2WI and DP imaging or AP and DP imaging (Z = 0.778, p=0.436; Z = 1.279, p=0.201). CONCLUSION: The SIRs of pancreatic lesions and erector spinae on T2WI, AP, and DP images can be used to differentiate AIP from PDA.

Endoscopic ultrasound-guided pancreatic sampling for the histopathological diagnosis of autoimmune pancreatitis.

Autoimmune pancreatitis (AIP), which is characterized by pancreatic enlargement and irregular narrowing of the main pancreatic duct, is difficult to differentiate from malignancy. The irregular narrowing of the pancreatic duct, which can be detected via endoscopic retrograde cholangiopancreatography, is a characteristic feature of AIP; however, distinguishing between localized AIP and pancreatic cancer based on pancreatic duct imaging is difficult. This study overviews the efficacy of endoscopic ultrasound (EUS)-guided pancreatic sampling for the histopathological diagnosis of AIP. Recent enhancements in needle biopsy methodologies and technologies have contributed to improvement in the diagnostic efficacy of this technique. The guidance provided in this study for the histological diagnosis of AIP is anticipated to further advance in the histopathological diagnosis of AIP using EUS-guided pancreatic sampling.

CT Radiomics Features in Differentiation of Focal-Type Autoimmune Pancreatitis from Pancreatic Ductal Adenocarcinoma: A Propensity Score Analysis.

PURPOSE: To evaluate the diagnostic performance of the radiomics score (rad-score) for differentiating focal-type autoimmune pancreatitis (fAIP) from pancreatic ductal adenocarcinoma (PDAC). METHODS: This retrospective review included 42 consecutive patients with fAIP diagnosed according to the International Consensus Diagnostic Criteria between January 2011 and December 2018. Furthermore, 334 consecutive patients with PDAC confirmed by pathology were also reviewed during the same period. Patients with PDAC and fAIP were matched via propensity score matching (PSM). All patients underwent multidetector computed tomography (MDCT). For each patient, 1409 radiomics features of the portal phase were extracted and reduced using the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm. The portal rad-score performance was assessed based on its discriminative ability. RESULTS: After PSM, we matched 55 patients with PDAC to 42 patients with fAIP, based on clinical and CT characteristics (e.g., patient age, sex, body mass index, location, size, enhanced mode). A rad-score for discriminating fAIP from PDAC, which contained four CT derived radiomic features, was developed (area under the curve = 0.97). The sensitivity, specificity, and accuracy of the radiomics model were 95.24%, 92.73% and 0.94, respectively. CONCLUSION: The portal rad-score can accurately and noninvasively differentiate fAIP from PDAC.

Multimodel magnetic resonance imaging of mass-forming autoimmune pancreatitis: differential diagnosis with pancreatic ductal adenocarcinoma.

PURPOSE: To assess the value of the multimodel magnetic resonance imaging (MRI), including unenhanced images, dynamic contrast-enhanced MRI (DCE-MRI), MR-cholangiopancreatography (MRCP), and diffusion-weighted imaging (DWI), in differentiation of mass-forming autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC). METHODS: Twelve patients with mass-forming AIP and 30 with PDAC were included. All patients underwent unenhanced MRI, DCE-MRI, DWI, and MRCP. Relevant values including sensitivity and specificity of the imaging features and their diagnostic performance for predicting mass-forming AIP were analyzed. RESULTS: Several statistically significant MR findings and quantitative indexes differentiating mass-forming AIP from PDAC, including multiplicity, irregularity or conformation, capsule-like rim enhancement, absence of internal cystic or necrotic portion, homogeneous enhancement during pancreatic, venous, and delayed phases, skipped stricture or stricture of MPD, absence of side branch dilation, maximum upstream MPD diameter < 2.4 mm, ContrastUP > 0.739, ContrastAP > 0.710, ContrastPP > 0.879, and ContrastVP or ContrastDP > 0.949, indicated mass-forming AIP (P < 0.05). The apparent diffusion coefficient (ADC) value was also significantly lower in mass-forming AIP compared to that in PDAC (P = 0.006). The cutoff value of ADC for distinguishing mass-forming AIP from PDAC was 1.099 × 10-3 mm2/s. CONCLUSION: Multimodel MRI, including unenhanced MRI, DCE-MRI with DWI and MRCP can provide qualitative and quantitative information about mass-forming AIP characterization. Multimodel MRI are valuable for differentiating mass-forming AIP from PDAC.

Autoimmune Pancreatitis: A Critical Analysis of the Surgical Experience in an Era of Modern Diagnostics.

OBJECTIVE: The aim of this study was to critically analyze the surgical experience of managing autoimmune pancreatitis (AIP) in an era of modern diagnostics and compare these patients with those who were managed conservatively. METHODS: Two prospectively maintained databases were used to retrospectively identify patients with AIP who were either managed conservatively or underwent pancreatectomy. RESULTS: Eighty-eight patients were included in the study, of which 56 (63.6%) underwent resection and 32 (36.4%) were managed conservatively. Patients who underwent resection were more likely to present with jaundice (64.3% vs 18.1%, P < 0.001) and weight loss (53.6% vs 15.6%, P = 0.005). The cohort who underwent resection had a significantly higher median carbohydrate antigen 19-9 (40.0 vs 18.6 U/mL, P = 0.034) and was less likely to have elevated immunoglobulin G4 (26.1% vs 50.0%, P < 0.001). The most frequent initial diagnosis in the cohort who underwent resection was ductal adenocarcinoma (82.1%). Nine patients (28.1%) in the conservatively managed cohort experienced AIP relapse compared with 6 patients (10.7%) in the cohort who underwent resection. CONCLUSIONS: The most frequent reason for surgical resection of AIP is concern for malignancy. Carbohydrate antigen 19-9 elevations were more common than immunoglobulin G4 in our cohort, suggesting that this laboratory profile is suboptimal for this population.

DWI of Autoimmune Pancreatitis: Is It an Imaging Biomarker for Disease Activity?

OBJECTIVE. The purpose of this article was to evaluate the DWI features of autoimmune pancreatitis (AIP) at baseline, under treatment, and at relapse, and to assess the diagnostic accuracy of the ADC for determining disease activity. MATERIALS AND METHODS. This retrospective study was approved by the institutional review board. Sixty-two patients with AIP (48 at initial attack and 14 at relapse) underwent MRI with DWI (b = 0 and 800 s/mm2) at 3 T before receiving corticosteroid therapy (CST) and during follow-up. Seventeen patients had disease relapse during follow-up, whereas the others remained clinically stable. Forty age- and sex-matched patients without pancreatic disease served as the control group. RESULTS. The ADC value of AIP at baseline was significantly lower than that for a disease-free pancreas (0.99 ± 0.12 vs 1.26 ± 0.10 × 10-3 mm2/s, p < .001). Under CST, the ADC value increased gradually at the short-term and long-term follow-up (1.16 ± 0.12 and 1.23 ± 0.12 × 10-3 mm2/s, respectively, both p < .001). At relapse, the ADC had a relative decrease (1.11 ± 0.20 × 10-3 mm2/s) but was significantly higher compared with the initial attack (p = .003). The AUC of ADC serum IgG4 level at ROC analysis for baseline versus clinically stable AIP was 0.867 and 0.700, the AUC for clinically active AIP versus clinically stable AIP was 0.762 and 0.686, and the AUC for relapsed AIP versus clinically stable AIP was 0.648 and 0.669. CONCLUSION. DWI reflected the dynamic change of AIP under CST, and the ADC value for DWI outperformed the serum IgG4 value for determining disease activity. However, relapsed disease showed less diffusion restriction, and the ADC value was less accurate for predicting relapse.

Comparison of five-phase computed tomography images of type 1 autoimmune pancreatitis and pancreatic cancer: Emphasis on cases with atypical images.

BACKGROUND/OBJECTIVES: International consensus diagnostic criteria (ICDC) include characteristic images of autoimmune pancreatitis (AIP); however, reports on atypical cases are increasing. The aims of this study were to compare CT findings between AIP and pancreatic cancer (PC), and to analyze type 1 AIPs showing atypical images. METHODS: Five-phase CT images were compared between 80 type 1-AIP lesions and 80 size- and location-matched PCs in the case-control study. Atypical AIPs were diagnosed based on the four ICDC items. RESULTS: ICDC items were recognized in most AIP lesions; pancreatic enlargement (87.7%), narrowing of the main pancreatic duct (98.8%), delayed enhancement (100%), and no marked upstream-duct dilation (97.5%). CT values of AIPs increased rapidly until the pancreatic phase and decreased afterward, while those of PCs gradually increased until the delayed phase (P < 0.0001). Atypical images were recognized in 14.8% of AIPs, commonly without pancreatic enlargement (18.5 mm) and sometimes mimicking intraductal neoplasms. The CT values and their ratios were different between atypical AIPs and size-matched PCs most significantly in the pancreatic phase, but similar in the delayed phase. CONCLUSIONS: Ordinary type 1 AIPs can be diagnosed with the ICDC, but atypical AIPs represented a small fraction. "Delayed enhancement" is characteristic to ordinary AIPs, however, "pancreatic-phase enhancement" is more diagnostic for atypical AIPs.

Utilisation of artificial intelligence for the development of an EUS-convolutional neural network model trained to enhance the diagnosis of autoimmune pancreatitis.

OBJECTIVE: The diagnosis of autoimmune pancreatitis (AIP) is challenging. Sonographic and cross-sectional imaging findings of AIP closely mimic pancreatic ductal adenocarcinoma (PDAC) and techniques for tissue sampling of AIP are suboptimal. These limitations often result in delayed or failed diagnosis, which negatively impact patient management and outcomes. This study aimed to create an endoscopic ultrasound (EUS)-based convolutional neural network (CNN) model trained to differentiate AIP from PDAC, chronic pancreatitis (CP) and normal pancreas (NP), with sufficient performance to analyse EUS video in real time. DESIGN: A database of still image and video data obtained from EUS examinations of cases of AIP, PDAC, CP and NP was used to develop a CNN. Occlusion heatmap analysis was used to identify sonographic features the CNN valued when differentiating AIP from PDAC. RESULTS: From 583 patients (146 AIP, 292 PDAC, 72 CP and 73 NP), a total of 1 174 461 unique EUS images were extracted. For video data, the CNN processed 955 EUS frames per second and was: 99% sensitive, 98% specific for distinguishing AIP from NP; 94% sensitive, 71% specific for distinguishing AIP from CP; 90% sensitive, 93% specific for distinguishing AIP from PDAC; and 90% sensitive, 85% specific for distinguishing AIP from all studied conditions (ie, PDAC, CP and NP). CONCLUSION: The developed EUS-CNN model accurately differentiated AIP from PDAC and benign pancreatic conditions, thereby offering the capability of earlier and more accurate diagnosis. Use of this model offers the potential for more timely and appropriate patient care and improved outcome.