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

Radiomics-based histological grading of pancreatic ductal adenocarcinoma using 18F-FDG PET/CT: A two-center study

OBJECTIVE

To explore the value of radiomics features derived from 18F-FDG PET/CT images in predicting the histological grade of pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

A retrospective analysis was conducted using data from patients with suspected pancreatic cancer, who histologically confirmed as PDAC within 14 days after 18F-FDG PET/CT scan in one of two hospitals. Tumors were divided into high-grade (undifferentiated or poorly differentiated), and low-grade (moderately or well differentiated). Two researchers independently used uRP to perform layer-by-layer tumor segmentation in both PET and CT images of each patient, and extract features. Model performance was evaluated using 5-fold cross-validation on the entire multi-center cohort, with results averaged across all folds. The least absolute shrinkage and selection was used for feature selection, and support vector machine (SVM), random forest (RF), and logistic regression (LR) were employed to distinguish the grade of PDAC. The performance of the model was evaluated using the receiver operating characteristic curve.

RESULTS

This study comprised 111 patients (72 males and 39 females), comprising 52 patients with high-grade PDAC tumors and 59 patients with low-grade. A series of models were established by SVM, LR, and RF algorithms based on selected features. In the test set, the mean areas under the curve (AUCs) for PET image-based models using SVM, LR, and RF algorithms were 0.773, 0.772, and 0.760. For CT-based models, the mean AUCs were 0.764, 0.770, and 0.576. For PET/CT-based models, the mean AUCs were 0.840, 0.844, and 0.773.

CONCLUSION

Despite the lack of external validation, the PET/CT-derived radiomics model enables accurate preoperative histological grading of PDAC, offering a clinically actionable tool to neoadjuvant therapy stratification and further guide personalized medical decision-making.

CA19-9/DBil: a promising indicator to distinguish between CA19-9-elevated pancreatic head-type autoimmune pancreatitis and pancreatic head cancer

BACKGROUND

Pancreatic head-type autoimmune pancreatitis (PH-AIP) with elevated CA19-9 is sometimes difficult to distinguish from pancreatic head cancer (PHC) with elevated CA19-9. At times, IgG4 proves inadequate in offering assistance. The study aimed to elucidate the performance of CA19-9/DBil in distinguishing between the two conditions.

METHODS

This was a retrospective study. We collected serologic indicators from participants in PH-AIP and PHC Group. Three logistic regression equations were established ranging from non-adjustment (Model 1, only CA19-9/DBil included) to adjusting for sex, age, and CEA (Model 2 and Model 3) to explore the relationship between CA19-9/DBil and PH-AIP probability. ROC, Decision Curve Analysis (DCA), calibration curve were conducted. P for AUCs and net reclassification improvements (NRI) were computed to evaluate differences in discrimination and the improvement in risk reclassification between models.

RESULTS

The study included 90 PHC and 35 PH-AIP patients, all with elevated CA19-9. The ORs for CA19-9/DBil in three models were similar (0.915 to 0.921). ROC revealed that Model 1 had an AUC of 0.772. The sensitivity, specificity, and accuracy at the best threshold were all > 0.7. Model 1, although simple, was not inferior in its discriminative ability compared to complex models: the difference in discrimination between Model 1 and each of two adjusted models was not statistically significant (P > 0.05, both AUC and NRI). Additionally, calibration curve and DCA suggested that Model 1 had good calibration and clinical utility.

CONCLUSIONS

CA19-9/DBil exhibited promising diagnostic performance in differentiating between CA19-9-elevated PH-AIP and PHC.

The chronic pancreatitis (CP) Type Cambridge 2 as a cause of unclear upper abdominal pain: a radiologically underestimated diagnosis

The time interval from symptom onset to the diagnosis of chronic pancreatitis (CP) remains disproportionately long today due to nonspecific symptoms and the absence of a definitive laboratory marker. Nevertheless, mortality is increased by 3.6 times compared to the general population. Additionally, the risk of developing pancreatic carcinoma is 16 times higher in the presence of CP. According to the current S3 guideline, the morphological staging of CP should be based on the Cambridge Classification for CT/MRCP. Most radiologists morphologically associate CP with Cambridge Stage 4, which is characterized by classic calcifications. The subtle morphologies of earlier Cambridge Stages are often unrecognized, leading to delayed diagnosis. The aim of this study was to diagnose CP at Cambridge Stage 2 as the cause of unexplained upper abdominal discomfort.A retrospective analysis was conducted on 266 patients with unexplained upper abdominal pain who underwent outpatient MRI with MRCP between January 1, 2021, and October 1, 2023. The criteria for Cambridge Stage 2 were evaluated: pancreatic duct in the corpus measuring between 2 and 4 mm, pancreatic hypertrophy, cystic changes < 10 mm, irregularities in the duct, or > 3 pathological side branches. Patients with known tumors or other leading diagnoses, which explained the discomfort, were excluded.25 patients (15 female, 10 male) met the criteria for CP Stage 2 (9%). Ductal dilation between 2 and 4 mm was visible in 21 cases. Pancreatic hypertrophy was observed in six cases. Cystic changes < 10 mm were identified in three cases. Irregularities in the duct ("wavy duct") were diagnosed in 19 patients. Dilation of > 3 side branches was recognized in 17 cases. Lipase levels were additionally determined, with 13 patients showing pathologically elevated levels (> 60 U/l).CP at Cambridge Stage 2 is an important and underestimated diagnosis in patients with unexplained upper abdominal pain in the outpatient setting. Radiologists should pay attention not only to common signs like calcifications, large cysts, or duct strictures but also to subtle changes such as duct irregularities ("wavy duct configuration") and pathologically dilated side branches, which could lead to a significantly earlier diagnosis of CP. Lipase determination may be an additional indication of chronic pancreatitis in this context. · Early-stage Cambridge 2 CP is an important and underestimated diagnosis in patients with unexplained upper abdominal pain in the outpatient setting.. · Radiologists should pay attention to subtle signs of early CP.. · Additional information about lipase levels can be helpful in the diagnostic process..

Quantitative MR imaging biomarkers for distinguishing inflammatory pancreatic mass and pancreatic cancer-a systematic review and meta-analysis

OBJECTIVES

To evaluate the diagnostic performance of quantitative magnetic resonance (MR) imaging biomarkers in distinguishing between inflammatory pancreatic masses (IPM) and pancreatic cancer (PC).

METHODS

A literature search was conducted using PubMed, Embase, the Cochrane Library, and Web of Science through August 2023. Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) was used to evaluate the risk of bias and applicability of the studies. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were calculated using the DerSimonian-Laird method. Univariate meta-regression analysis was used to identify the potential factors of heterogeneity.

RESULTS

Twenty-four studies were included in this meta-analysis. The two main types of IPM, mass-forming pancreatitis (MFP) and autoimmune pancreatitis (AIP), differ in their apparent diffusion coefficient (ADC) values. Compared with PC, the ADC value was higher in MFP but lower in AIP. The pooled sensitivity/specificity of ADC were 0.80/0.85 for distinguishing MFP from PC and 0.82/0.84 for distinguishing AIP from PC. The pooled sensitivity/specificity for the maximal diameter of the upstream main pancreatic duct (dMPD) was 0.86/0.74, with a cutoff of dMPD ≤ 4 mm, and 0.97/0.52, with a cutoff of dMPD ≤ 5 mm. The pooled sensitivity/specificity for perfusion fraction (f) was 0.82/0.68, and 0.82/0.77 for mass stiffness values.

CONCLUSIONS

Quantitative MR imaging biomarkers are useful in distinguishing between IPM and PC. ADC values differ between MFP and AIP, and they should be separated for consideration in future studies.

CLINICAL RELEVANCE STATEMENT

Quantitative MR parameters could serve as non-invasive imaging biomarkers for differentiating malignant pancreatic neoplasms from inflammatory masses of the pancreas, and hence help to avoid unnecessary surgery.

KEY POINTS

• Several quantitative MR imaging biomarkers performed well in differential diagnosis between inflammatory pancreatic mass and pancreatic cancer. • The ADC value could discern pancreatic cancer from mass-forming pancreatitis or autoimmune pancreatitis, if the two inflammatory mass types are not combined. • The diameter of main pancreatic duct had the highest specificity for differentiating autoimmune pancreatitis from pancreatic cancer.

Proliferative features of IgG4-related disease

IgG4-related disease is an immune-mediated disease that can lead to substantial morbidity and organ damage. Capable of affecting nearly any organ system or anatomic site, and showing considerable overlap in clinical presentation with various other diseases, IgG4-related disease often poses a diagnostic challenge for clinicians. Furthermore, there are no diagnostic biomarkers with high specificity for IgG4-related disease, and histopathological examination is nuanced and requires clinical correlation for accurate diagnosis. Therefore, it is crucial for clinicians to recognise the clinical phenotypes of IgG4-related disease. The disease is generally considered to have predominantly fibrotic and proliferative (or inflammatory) manifestations, with distinct clinical, serological and histopathological findings associated with each manifestation. However, the fibrotic and proliferative manifestations of this disease frequently occur together, thereby blurring this dichotomous distinction. In this Series paper, we provide a detailed overview of the clinical manifestations typical of the proliferative features of IgG4-related disease, with an emphasis on the diagnostic evaluation and differential diagnosis of each proliferative disease manifestation. In addition, we summarise the immune mechanisms underlying IgG4-related disease, suggest a framework for how to approach management and monitoring after the diagnosis is established, and highlight current unmet needs for patient care surrounding this disease.

Imaging of the Liver and Pancreas: The Added Value of MRI

MR is a powerful diagnostic tool in the diagnosis and management of most hepatic and pancreatic diseases. Thanks to its multiple sequences, the use of dedicated contrast media and special techniques, it allows a multiparametric approach able to provide both morphological and functional information for many pathological conditions. The knowledge of correct technique is fundamental in order to obtain a correct diagnosis. In this paper, different MR sequences will be illustrated in the evaluation of liver and pancreatic diseases, especially those sequences which provide information not otherwise obtainable with other imaging techniques. Practical MR protocols with the most common indications of MR in the study of the liver and pancreas are provided.

Autoimmune pancreatitis: Cornerstones and future perspectives

Autoimmune pancreatitis (AIP) is an autoimmune subtype of chronic pancreatitis resulting from the aberrant immune response against the pancreas, leading to inflammation and fibrosis. Although AIP is rare, its incidence is increasing and is often misdiagnosed as other pancreatic diseases. AIP is commonly classified into two types. Type 1 AIP (AIP-1) is typically associated with elevated serum immunoglobulin G4 (IgG4) levels and systemic manifestations, while type 2 AIP is typically a more localized form of the disease, and may coexist with other autoimmune disorders, especially inflammatory bowel diseases. Additionally, there is emerging recognition of a third type (type 3 AIP), which refers to immunotherapy-triggered AIP, although this classification is still gaining acceptance in medical literature. The clinical manifestations of AIP mainly include painless jaundice and weight loss. Elevated serum IgG4 levels are particularly characteristic of AIP-1. Diagnosis relies on a combination of clinical, laboratory, radiological, and histological findings, given the similarity of AIP symptoms to other pancreatic disorders. The mainstay of treatment for AIP is steroid therapy, which is effective in most cases. Severe cases might require additional imm-unosuppressive agents. This review aims to summarize the current knowledge of AIP, encompassing its epidemiology, etiology, clinical presentation, diagnosis, and treatment options. We also address the challenges and controversies in diagnosing and treating AIP, such as distinguishing it from pancreatic cancer and managing long-term treatment, highlighting the need for increased awareness and knowledge of this complex disease.

[Autoimmune pancreatitis versus pancreatic cancer]

CLINICAL ISSUE

Autoimmune pancreatitis (AIP) is classified as a distinct form of pancreatitis according to the guidelines. It is characterized by imaging morphologic and histologic features and is associated with extrapancreatic manifestations in type 1 IgG 4-associated disease. Symptoms and findings almost always improve with administration of steroids. Differentiation from pancreatic ductal adenocarcinoma is required, particularly in the presence of AIP with focal parenchymal involvement.

STANDARD RADIOLOGIC PROCEDURES

If AIP is suspected, abdominal ultrasound and/or endosonography, computed tomography (CT), and preferably magnetic resonance imaging (MRI) are indicated. A distinction is made between parenchymal and ductal changes that specifically indicate the presence of AIP.

METHODOLOGICAL INNOVATIONS AND EVALUATION

The diagnosis of autoimmune pancreatitis should be made based on the International Consensus Criteria (ICDC), in which the five main features (imaging, serology, histology, other organ involvement, response to steroid medication) are assessed. In type 1 AIP, typical imaging changes are sufficient to establish the diagnosis even with negative histology, whereas for type 2 AIP, histologic evidence is required. Imaging changes help in the differential diagnosis from pancreatic cancer.

PRACTICAL RECOMMENDATIONS

The following article addresses and evaluates crucial imaging diagnostic CT and MRI criteria for correct classification of findings, description of results, and differentiation of autoimmune pancreatitis from pancreatic cancer.

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.

A review of deep learning and radiomics approaches for pancreatic cancer diagnosis from medical imaging

PURPOSE OF REVIEW

Early and accurate diagnosis of pancreatic cancer is crucial for improving patient outcomes, and artificial intelligence (AI) algorithms have the potential to play a vital role in computer-aided diagnosis of pancreatic cancer. In this review, we aim to provide the latest and relevant advances in AI, specifically deep learning (DL) and radiomics approaches, for pancreatic cancer diagnosis using cross-sectional imaging examinations such as computed tomography (CT) and magnetic resonance imaging (MRI).

RECENT FINDINGS

This review highlights the recent developments in DL techniques applied to medical imaging, including convolutional neural networks (CNNs), transformer-based models, and novel deep learning architectures that focus on multitype pancreatic lesions, multiorgan and multitumor segmentation, as well as incorporating auxiliary information. We also discuss advancements in radiomics, such as improved imaging feature extraction, optimized machine learning classifiers and integration with clinical data. Furthermore, we explore implementing AI-based clinical decision support systems for pancreatic cancer diagnosis using medical imaging in practical settings.

SUMMARY

Deep learning and radiomics with medical imaging have demonstrated strong potential to improve diagnostic accuracy of pancreatic cancer, facilitate personalized treatment planning, and identify prognostic and predictive biomarkers. However, challenges remain in translating research findings into clinical practice. More studies are required focusing on refining these methods, addressing significant limitations, and developing integrative approaches for data analysis to further advance the field of pancreatic cancer diagnosis.

Histogram array and convolutional neural network of DWI for differentiating pancreatic ductal adenocarcinomas from solid pseudopapillary neoplasms and neuroendocrine neoplasms

PURPOSE

This study aimed to investigate the diagnostic performance of the histogram array and convolutional neural network (CNN) based on diffusion-weighted imaging (DWI) with multiple b-values under magnetic resonance imaging (MRI) to distinguish pancreatic ductal adenocarcinomas (PDACs) from solid pseudopapillary neoplasms (SPNs) and pancreatic neuroendocrine neoplasms (PNENs).

METHODS

This retrospective study consisted of patients diagnosed with PDACs (n = 132), PNENs (n = 45) and SPNs (n = 54). All patients underwent 3.0-T MRI including DWI with 10 b values. The regions of interest (ROIs) of pancreatic tumor were manually drawn using ITK-SNAP software, which included entire tumor at DWI (b = 1500 s/m²). The histogram array was obtained through the ROIs from multiple b-value data. PyTorch (version 1.11) was used to construct a CNN classifier to categorize the histogram array into PDACs, PNENs or SPNs.

RESULTS

The area under the curves (AUCs) of the histogram array and the CNN model for differentiating PDACs from PNENs and SPNs were 0.896, 0.846, and 0.839 in the training, validation and testing cohorts, respectively. The accuracy, sensitivity and specificity were 90.22%, 96.23%, and 82.05% in the training cohort, 84.78%, 96.15%, and 70.0% in the validation cohort, and 81.72%, 90.57%, and 70.0% in the testing cohort. The performance of CNN with AUC of 0.865 for this differentiation was significantly higher than that of f with AUC = 0.755 (P = 0.0057) and α with AUC = 0.776 (P = 0.0278) in all patients.

CONCLUSION

The histogram array and CNN based on DWI data with multiple b-values using MRI provided an accurate diagnostic performance to differentiate PDACs from PNENs and SPNs.