How does the pancreatic solid pseudopapillary neoplasm confuse us: Analyzing from the point view of MRI-based radiomics?

Comparison between solid pseudopapillary neoplasms of the pancreas and pancreatic ductal adenocarcinoma with cystic changes using computed tomography

BACKGROUND

Solid pseudopapillary neoplasms of the pancreas (SPN) share similar imaging findings with pancreatic ductal adenocarcinoma with cystic changes (PDAC with cystic changes), which may result in unnecessary surgery.

AIM

To investigate the value of computed tomography (CT) in differentiation of SPN from PDAC with cystic changes.

METHODS

This study retrospectively analyzed the clinical and imaging findings of 32 patients diagnosed with SPN and 14 patients diagnosed with PDAC exhibiting cystic changes, confirmed through pathological diagnosis. Quantitative and qualitative analysis was performed, including assessment of age, sex, tumor size, shape, margin, density, enhancement pattern, CT values of tumors, CT contrast enhancement ratios, "floating cloud sign," calcification, main pancreatic duct dilatation, pancreatic atrophy, and peripancreatic invasion or distal metastasis. Multivariate logistic regression analysis was used to identify relevant features to differentiate between SPN and PDAC with cystic changes, and receiver operating characteristic curves were obtained to evaluate the diagnostic performance of each variable and their combination.

RESULTS

When compared to PDAC with cystic changes, SPN had a lower age (32 years vs 64 years, P < 0.05) and a slightly larger size (5.41 cm vs 3.90 cm, P < 0.05). SPN had a higher frequency of "floating cloud sign" and peripancreatic invasion or distal metastasis than PDAC with cystic changes (both P < 0.05). No significant difference was found with respect to sex, tumor location, shape, margin, density, main pancreatic duct dilatation, calcification, pancreatic atrophy, enhancement pattern, CT values of tumors, or CT contrast enhancement ratios between the two groups (all P > 0.05). The area under the receiver operating characteristic curve of the combination was 0.833 (95% confidence interval: 0.708-0.957) with 78.6% sensitivity, 81.3% specificity, and 80.4% accuracy in differentiation of SPN from PDAC with cystic changes.

CONCLUSION

A larger tumor size, "floating cloud sign," and peripancreatic invasion or distal metastasis are useful CT imaging features that are more common in SPN and may help discriminate SPN from PDAC with cystic changes.

Perioperative safety and prognosis following parenchyma-preserving surgery for solid pseudopapillary neoplasm of the pancreas

BACKGROUND/OBJECTIVES

To evaluate perioperative safety and outcome of parenchyma-preserving pancreatectomy and risk factors of metastasis and recurrence for patients with solid pseudopapillary neoplasm (SPN).

METHODS

Demographic data, operative and pathological parameter, follow-up data of patients with SPN undergoing their first operation were collected in our single center from May 2016 to October 2021 and compared between regular pancreatectomy group and parenchyma-preserving surgery group. Risk factors for metastasis and recurrence were investigated.

RESULTS

A total of 194 patients were included, 154 of whom were female and the average age of all patients was 33 years old. Most patients were asymptomatic, with the most common complaint being abdominal pain or discomfort. Of them, 62 patients underwent parenchyma-preserving pancreatectomy including middle segment pancreatectomy and enucleation, and 132 patients underwent regular pancreatectomy including pancreaticoduodenectomy, distal pancreatectomy and total pancreatectomy. Patients in the parenchyma-preserving surgery group had a shorter duration of operation, less intraoperative bleeding, and decreased risk of combined organ removal and blood transfusion, with no statistical significance yet. The two groups exhibited a similar incidence of postoperative complications including grade B and C pancreatic fistula, delayed gastric emptying, postoperative pancreatic hemorrhage, and other complications, as well as radiological intervention, relaparotomy and the length of postoperative hospital stay. There were no perioperative deaths. All the patients, except 18 of those who discontinued follow-up, were alive with a median follow-up time of 31 months. Three patients in the regular pancreatectomy group were observed to have liver metastasis, and no metastasis was observed in the parenchyma-preserving surgery group. Significant risk factors for tumor metastasis and recurrence were tumor size, angioinvasion, and nerve infiltration.

CONCLUSIONS

Parenchyma-preserving surgery did not significantly increase the frequency of perioperative complications or recurrence and might be preferable if comprehensive conditions allow.

Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions

The rate of incidentally detected pancreatic cystic lesions (PCLs) has increased over the past decade and was recently reported at 8%. These lesions pose a unique challenge, as each subtype of PCL carries a different risk of malignant transformation, ranging from 0% (pancreatic pseudocyst) to 34–68% (main duct intraductal papillary mucinous neoplasm). It is imperative to correctly risk-stratify the malignant potential of these lesions in order to provide the correct care course for the patient, ranging from monitoring to surgical intervention. Even with the multiplicity of guidelines (i.e., the American Gastroenterology Association guidelines and Fukuoka/International Consensus guidelines) and multitude of diagnostic information, risk stratification of PCLs falls short. Studies have reported that 25–64% of patients undergoing PCL resection have pancreatic cysts with no malignant potential, and up to 78% of mucin-producing cysts resected harbor no malignant potential on pathological evaluation. Clinicians are now incorporating artificial intelligence technology to aid in the management of these difficult lesions. This review article focuses on advancements in artificial intelligence within digital pathomics, radiomics, and genomics as they apply to the diagnosis and risk stratification of PCLs.

Using Quantitative Imaging for Personalized Medicine in Pancreatic Cancer: A Review of Radiomics and Deep Learning Applications

Simple Summary

With a five-year survival rate of only 3% for the majority of patients, pancreatic cancer is a global healthcare challenge. Radiomics and deep learning, two novel quantitative imaging methods that treat medical images as minable data instead of just pictures, have shown promise in advancing personalized management of pancreatic cancer through diagnosing precursor diseases, early detection, accurate diagnosis, and treatment personalization. Radiomics and deep learning methods aim to collect hidden information in medical images that is missed by conventional radiology practices through expanding the data search and comparing information across different patients. Both methods have been studied and applied in pancreatic cancer. In this review, we focus on the current progress of these two methods in pancreatic cancer and provide a comprehensive narrative review on the topic. With better regulation, enhanced workflow, and larger prospective patient datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through personalized precision medicine.

Abstract

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.