Pancreatic Adenocarcinoma: Imaging Modalities and the Role of Artificial Intelligence in Analyzing CT and MRI Images

Pancreatic ductal adenocarcinoma (PDAC) stands out as the predominant malignant neoplasm affecting the pancreas, characterized by a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation, and classification could improve diagnosis with better treatment options and increased survival. This review included papers published in the last five years and describes the current trends in AI algorithms used in PDAC. We analyzed the applications of AI in the detection of PDAC, segmentation of the lesion, and classification algorithms used in differential diagnosis, prognosis, and histopathological and genomic prediction. The results show a lack of multi-institutional collaboration and stresses the need for bigger datasets in order for AI models to be implemented in a clinically relevant manner.

Pre-Workout-Induced Pancreatitis

The use of dietary supplements, including pre-workout formulations, has gained widespread popularity among individuals engaged in sports and fitness. This case report presents a unique instance of pre-workout-induced pancreatitis in a previously healthy young adult. The patient, a 35-year-old male, presented to the emergency department with abdominal pain, elevated pancreatic enzymes, and characteristic radiological findings indicative of acute pancreatitis. The patient's history revealed no prior predisposing factors for pancreatitis such as alcohol consumption or gallstone disease. Extensive diagnostic evaluation excluded other potential causes leading to the suspicion of his pre-workout supplement as the source. Pre-workout supplements contain a blend of stimulants, amino acids, and other metabolic ingredients designed to enhance exercise and muscle performance. Research shows that some of these ingredients, such as amino acids, induce metabolic chain reactions which may damage pancreatic cells. However, there is extremely limited literature regarding these amino acids in combination such as in workout supplements. This case prompts an examination of the potential adverse effects of pre-workout supplements, highlighting the need for increased vigilance among healthcare providers and consumers alike. As the use of these products grows, further research is warranted to allow for safe commercial distribution and to protect consumers from serious harm.

PET Imaging of GPR44 by Antagonist [11C]MK-7246 in Pigs

A validated imaging marker for beta-cell mass would improve understanding of diabetes etiology and enable new strategies in therapy development. We previously identified the membrane-spanning protein GPR44 as highly expressed and specific to the beta cells of the pancreas. The selective GPR44 antagonist MK-7246 was radiolabeled with carbon-11 and the resulting positron-emission tomography (PET) tracer [¹¹C]MK-7246 was evaluated in a pig model and in vitro cell lines. The [¹¹C]MK-7246 compound demonstrated mainly hepatobiliary excretion with a clearly defined pancreas, no spillover from adjacent tissues, and pancreatic binding similar in magnitude to the previously evaluated GPR44 radioligand [¹¹C]AZ12204657. The binding could be blocked by preadministration of nonradioactive MK-7246, indicating a receptor-binding mechanism. [¹¹C]MK-7246 showed strong potential as a PET ligand candidate for visualization of beta-cell mass (BCM) and clinical translation of this methodology is ongoing.

Pancreatlas: Applying an Adaptable Framework to Map the Human Pancreas in Health and Disease

Human tissue phenotyping generates complex spatial information from numerous imaging modalities, yet images typically become static figures for publication, and original data and metadata are rarely available. While comprehensive image maps exist for some organs, most resources have limited support for multiplexed imaging or have non-intuitive user interfaces. Therefore, we built a Pancreatlas resource that integrates several technologies into a unique interface, allowing users to access richly annotated web pages, drill down to individual images, and deeply explore data online. The current version of Pancreatlas contains over 800 unique images acquired by whole-slide scanning, confocal microscopy, and imaging mass cytometry, and is available at https://www.pancreatlas.org. To create this human pancreas-specific biological imaging resource, we developed a React-based web application and Python-based application programming interface, collectively called Flexible Framework for Integrating and Navigating Data (FFIND), which can be adapted beyond Pancreatlas to meet countless imaging or other structured data-management needs.

•

Human organ phenotyping databases benefit from intuitive user interfaces

•

Pancreatlas resource enables exploration of bioimaging data from human pancreas

•

The front-end framework of Pancreatlas, FFIND, is modular and easily adaptable

•

FFIND provides structured data-exploration capabilities across countless domains

Scientists need cost-effective yet fully featured database solutions that facilitate large dataset sharing in a structured and easily digestible manner. Flexible Framework for Integrating and Navigating Data (FFIND) is a data-agnostic web application that is designed to easily connect existing databases with data-browsing clients. We used FFIND to build Pancreatlas, an online imaging resource containing datasets linking imaging data with clinical data to facilitate advances in the understanding of diabetes, pancreatitis, and pancreatic cancer. FFIND architecture, which is available as open-source software, can be easily adapted to meet other field- or project-specific needs; we hope it will help data scientists reach a broader audience by reducing the development life cycle and providing familiar interactivity in communicating data and underlying stories.

Improved Quantification of the Beta Cell Mass after Pancreas Visualization with 99mTc-demobesin-4 and Beta Cell Imaging with 111In-exendin-3 in Rodents

OBJECTIVE

Accurate assessment of the ¹¹¹In-exendin-3 uptake within the pancreas requires exact delineation of the pancreas, which is highly challenging by MRI and CT in rodents. In this study, the pancreatic tracer ^99mTc-demobesin-4 was evaluated for accurate delineation of the pancreas to be able to accurately quantify ¹¹¹In-exendin-3 uptake within the pancreas.

METHODS

Healthy and alloxan-induced diabetic Brown Norway rats were injected with the pancreatic tracer ^99mTc-demobesin-4 ([^99mTc-N₄-Pro¹,Tyr⁴,Nle¹⁴]bombesin) and the beta cell tracer ¹¹¹In-exendin-3 ([¹¹¹In-DTPA-Lys⁴⁰]exendin-3). After dual isotope acquisition of SPECT images, ^99mTc-demobesin-4 was used to define a volume of interest for the pancreas in SPECT images subsequently the ¹¹¹In-exendin-3 uptake within this region was quantified. Furthermore, biodistribution and autoradiography were performed in order to gain insight in the distribution of both tracers in the animals.

RESULTS

^99mTc-demobesin-4 showed high accumulation in the pancreas. The uptake was highly homogeneous throughout the pancreas, independent of diabetic status, as demonstrated by autoradiography, whereas ¹¹¹In-exendin-3 only accumulates in the islets of Langerhans. Quantification of both ex vivo and in vivo SPECT images resulted in an excellent linear correlation between the pancreatic uptake, determined with ex vivo counting and ¹¹¹In-exendin-3 uptake, determined from the quantitative analysis of the SPECT images (Pearson r = 0.97, Pearson r = 0.92).

CONCLUSION

^99mTc-demobesin-4 shows high accumulation in the pancreas of rats. It is a suitable tracer for accurate delineation of the pancreas and can be conveniently used for simultaneous acquisition with ¹¹¹In labeled exendin-3. This method provides a straightforward, reliable, and objective method for preclinical beta cell mass (BCM) quantification with ¹¹¹In-exendin-3.

Updated imaging nomenclature for acute pancreatitis. AJR Am J Roentgenol. 2014;203:W464-W469. [PMID: 25341160 DOI: 10.2214/ajr.13.12222]

Key points. 1. CT is used to confirm the diagnosis of acute pancreatitis when the diagnosis is in doubt and to differentiate acute interstitial pancreatitis from necrotizing pancreatitis, which is a key element of the updated Atlanta nomenclature. The acute interstitial variety accounts for 90-95% of cases, with acute necrotizing pancreatitis accounting for the remaining cases. 2. Necrosis due to acute pancreatitis is best assessed on IV contrast-enhanced CT performed 40 seconds after injection. Peripancreatic necrosis is a subtype of necrotizing pancreatitis in which tissue death occurs in peripancreatic tissues. This is seen in isolation in 20% of patients with necrotizing pancreatitis. 3. Simple fluid collections associated with acute interstitial pancreatitis are subdivided chronologically. A collection observed within approximately 4 weeks of acute pancreatitis onset is termed an "acute peripancreatic fluid collection (APFC)." A collection older than 4 weeks should have a thin wall and is termed a "pseudocyst." Both APFCs and pseudocysts can be infected or sterile. 4. Fluid collections associated with necrotizing pancreatitis are labeled on the basis of age and the presence of a capsule. Within 4 weeks of acute pancreatitis onset, a fluid collection associated with necrotizing pancreatitis is termed an "acute necrotic collection (ANC)" whereas an older collection is termed an area of "walled-off necrosis (WON)" if it has a perceptible wall on CT. The term "pseudocyst" is not used in the setting of necrotizing pancreatitis collections. Although an ANC and a (WON can be infected or sterile, infection is far more likely compared with acute interstitial pancreatitis collections. 5. The severity of acute pancreatitis is graded on the basis of the presence of acute complications or organ failure. Mild acute pancreatitis has neither acute complications nor organ failure. Moderate-severity acute pancreatitis is associated with acute complications or organ failure lasting fewer than 48 hours. Severe acute pancreatitis is characterized by single- or multiorgan failure persisting for greater than 48 hours.