Quantitative imaging to evaluate malignant potential of IPMNs. Oncotarget. 2016;7:85776-85784. [PMID: 27588410 PMCID: PMC5349873 DOI: 10.18632/oncotarget.11769]

Current and Emerging Applications of Artificial Intelligence (AI) in the Management of Pancreatobiliary (PB) disorders

PURPOSE OF REVIEW: In this review, we aim to summarize the existing literature and future directions on the use of artificial intelligence (AI) for the diagnosis and treatment of PB (pancreaticobiliary) disorders. RECENT FINDINGS: AI models have been developed to aid in the diagnosis and management of PB disorders such as pancreatic adenocarcinoma (PDAC), pancreatic neuroendocrine tumors (pNETs), acute pancreatitis, chronic pancreatitis, autoimmune pancreatitis, choledocholithiasis, indeterminate biliary strictures, cholangiocarcinoma and endoscopic procedures such as ERCP, EUS, and cholangioscopy. Recent studies have integrated radiological, endoscopic and pathological data to develop models to aid in better detection and prognostication of these disorders. AI is an indispensable proponent in the future practice of medicine. It has been extensively studied and approved for use in the detection of colonic polyps. AI models based on clinical, laboratory, and radiomics have been developed to aid in the diagnosis and management of various PB disorders and its application is ever expanding. Despite promising results, these AI-based models need further external validation to be clinically applicable.

Comprehensive analysis of clinical data and radiomic features from contrast enhanced CT for differentiating benign and malignant pancreatic intraductal papillary mucinous neoplasms

The primary aim of this investigation was to leverage radiomics features derived from contrast-enhanced abdominal computed tomography (CT) scans to devise a predictive model to discern the benign and malignant nature of intraductal papillary mucinous neoplasms (IPMNs). Radiomic signatures were meticulously crafted to delineate benign from malignant IPMNs by extracting pertinent features from contrast-enhanced CT images within a designated training cohort (n = 84). Subsequent validation was conducted with data from an independent test cohort (n = 37). The discriminative ability of the model was quantitatively evaluated through receiver operating characteristic (ROC) curve analysis, with the integration of carefully selected clinical features to improve the comparative analysis. Arterial-phase images were utilized to construct a model comprising 8 features for distinguishing between benign and malignant cases. The model achieved an accuracy of 0.891 [95% confidence interval (95% CI), 0.816-0.996] in the cross-validation set and 0.553 (95% CI 0.360-0.745) in the test set. Conversely, employing 9 features from the venous-phase resulted in a model with a cross-validation accuracy of 0.862 (95%CI 0.777-0.946) and a test set accuracy of 0.801 (95% CI 0.653-0.950).Integrating the identified clinical features with imaging features yielded a model with a cross-validation accuracy of 0.934 (95% CI 0.879-0.990) and a test set accuracy of 0.904 (95% CI 0.808-0.999), thereby further improving its discriminatory ability. Our findings distinctly illustrate that venous-phase radiomics features eclipse arterial-phase radiomic features in terms of predictive accuracy regarding the nature of IPMNs. Furthermore, the synthesis and meticulous screening of clinical features with radiomic data significantly increased the diagnostic efficacy of our model, underscoring the pivotal importance of a comprehensive and integrated approach for accurate risk stratification in IPMN management.

Development of a CT-based radiomics-clinical model to diagnose acute pancreatitis on nonobvious findings on CT in children with pancreaticobiliary maljunction

OBJECTIVES

Since neither abdominal pain nor pancreatic enzyme elevation is specific for acute pancreatitis (AP), the diagnosis of AP in patients with pancreaticobiliary maljunction (PBM) may be challenging when the pancreas appears normal or nonobvious on CT. This study aimed to develop a quantitative radiomics-based nomogram of pancreatic CT for identifying AP in children with PBM who have nonobvious findings on CT.

METHODS

PBM patients with a diagnosis of AP evaluated at the Children's Hospital of Soochow University from June 2015 to October 2022 were retrospectively reviewed. The radiological features and clinical factors associated with AP were evaluated. Based on the selected variables, multivariate logistic regression was used to construct clinical, radiomics, and combined models.

RESULTS

Two clinical parameters and 6 radiomics characteristics were chosen based on their significant association with AP, as demonstrated in the training (area under curve [AUC]: 0.767, 0.892) and validation (AUC: 0.757, 0.836) datasets. The radiomics-clinical nomogram demonstrated superior performance in both the training (AUC, 0.938) and validation (AUC, 0.864) datasets, exhibiting satisfactory calibration (P > .05).

CONCLUSIONS

Our radiomics-based nomogram is an accurate, noninvasive diagnostic technique that can identify AP in children with PBM even when CT presentation is not obvious.

ADVANCES IN KNOWLEDGE

This study extracted imaging features of nonobvious pancreatitis. Then it developed and evaluated a combined model with these features.

Radiomics advances in the evaluation of pancreatic cystic neoplasms

With the development of medical imaging, the detection rate of pancreatic cystic neoplasms (PCNs) has increased greatly. Serous cystic neoplasm, solid pseudopapillary neoplasm, intraductal papillary mucinous neoplasm and mucinous cystic neoplasm are the main subtypes of PCN, and their treatment options vary greatly due to the different biological behaviours of the tumours. Different from conventional qualitative imaging evaluation, radiomics is a promising noninvasive approach for the diagnosis, classification, and risk stratification of diseases involving high-throughput extraction of medical image features. We present a review of radiomics in the diagnosis of serous cystic neoplasm and mucinous cystic neoplasm, risk classification of intraductal papillary mucinous neoplasm and prediction of solid pseudopapillary neoplasm invasiveness compared to conventional imaging diagnosis. Radiomics is a promising tool in the field of medical imaging, providing a noninvasive, high-performance model for preoperative diagnosis and risk stratification of PCNs and improving prospects regarding management of these diseases. Further studies are warranted to investigate MRI image radiomics in connection with PCNs to improve the diagnosis and treatment strategies in the management of PCN patients.

Clinical value of CT imaging features in the diagnosis of acute and chronic pancreatitis: A retrospective study

BACKGROUND

Recurrent acute pancreatitis is a common acute abdominal disease in surgery.

OBJECTIVE

To evaluate the radiographic features of pancreatic computed tomography (CT) imaging in the diagnosis of acute and chronic pancreatitis.

METHODS

48 pancreatitis patients who met the criteria were selected in this retrospective study from 2010 to 2019. Each diagnosis was evaluated as functional abdominal pain, recurrent acute pancreatitis, or chronic pancreatitis. All clinical data were collected from the patient's medical records. 54 radiological features were extracted from each region of interest in outline the pancreas and divided into five categories: first order statistics, the gray level co-occurrence matrix (GLCM), the gray level run-length matrix (GLRLM), the neighborhood gray level difference matrix (NGTDM), and morphological features by the MATLAB program.

RESULTS

Of the 48 patients, 16 had functional abdominal pain (33.3%), 18 had recurrent acute pancreatitis (37.5%), and 14 had chronic pancreatitis (29.2%). In the univariate analysis, nine radiological features, eight GLCM features and one NGTDM feature were significantly different between groups. Nine radiological characteristics had important reference values with AUC values ranging from 0.73-0.91.

CONCLUSION

Nine radiographic features of CT imaging demonstrate good evaluation efficiency in the diagnosis of pancreatitis and can distinguish patients with functional abdominal pain, recurrent acute pancreatitis, and chronic pancreatitis.

Radiomics in CT and MR imaging of the liver and pancreas: tools with potential for clinical application

Radiomics allows the extraction of quantitative imaging features from clinical magnetic resonance imaging (MRI) and computerized tomography (CT) studies. The advantages of radiomics have primarily been exploited in oncological applications, including better characterization and staging of oncological lesions and prediction of patient outcomes and treatment response. The potential introduction of radiomics in the clinical setting requires the establishment of a standardized radiomics pipeline and a quality assurance program. Radiomics and texture analysis of the liver have improved the differentiation of hypervascular lesions such as adenomas, focal nodular hyperplasia, and hepatocellular carcinoma (HCC) during the arterial phase, and in the pretreatment determination of HCC prognostic factors (e.g., tumor grade, microvascular invasion, Ki-67 proliferation index). Radiomics of pancreatic CT and MR images has enhanced pancreatic ductal adenocarcinoma detection and its differentiation from pancreatic neuroendocrine tumors, mass-forming chronic pancreatitis, or autoimmune pancreatitis. Radiomics can further help to better characterize incidental pancreatic cystic lesions, accurately discriminating benign from malignant intrapancreatic mucinous neoplasms. Nonetheless, despite their encouraging results and exciting potential, these tools have yet to be implemented in the clinical setting. This non-systematic review will describe the essential steps in the implementation of the radiomics and feature extraction workflow from liver and pancreas CT and MRI studies for their potential clinical application. A succinct overview of reported radiomics applications in the liver and pancreas and the challenges and limitations of their implementation in the clinical setting is also discussed, concluding with a brief exploration of the future perspectives of radiomics in the gastroenterology field.

Pancreatic Cystic Lesions: Next Generation of Radiologic Assessment

Pancreatic cystic lesions are frequently identified on cross-sectional imaging. As many of these are presumed branch-duct intraductal papillary mucinous neoplasms, these lesions generate much anxiety for the patients and clinicians, often necessitating long-term follow-up imaging and even unnecessary surgical resections. However, the incidence of pancreatic cancer is overall low for patients with incidental pancreatic cystic lesions. Radiomics and deep learning are advanced tools of imaging analysis that have attracted much attention in addressing this unmet need, however, current publications on this topic show limited success and large-scale research is needed.

Intraductal Papillary Mucinous Neoplasm of the Pancreas: A Challenging Diagnosis

Intraductal papillary mucinous neoplasm of the pancreas (IPMN) was classified as a distinct entity from mucinous cystic neoplasm by the WHO in 1995. It represents a mucin-producing tumor that originates from the ductal epithelium and can evolve from slight dysplasia to invasive carcinoma. In addition, different aspects of tumor progression may be seen in the same lesion. Three types are recognized, the branch duct variant, the main duct variant, which shows a much higher prevalence for malignancy, and the mixed-type variant, which combines branch and main duct characteristics. Advances in cross-sectional imaging have led to an increased rate of IPMN detection. The main imaging characteristic of IPMN is the dilatation of the pancreatic duct without the presence of an obstructing lesion. The diagnosis of a branch duct IPMN is based on the proof of its communication with the main pancreatic duct on MRI-MRCP examination. Early identification by imaging of the so-called worrisome features or predictors for malignancy is an important and challenging task. In this review, we will present recent imaging advances in the diagnosis and characterization of different types of IPMNs, as well as imaging tools available for early recognition of worrisome features for malignancy. A critical appraisal of current IPMN management guidelines from both a radiologist's and surgeon's perspective will be made. Special mention is made of complications that might arise during the course of IPMNs as well as concomitant pancreatic neoplasms including pancreatic adenocarcinoma and pancreatic endocrine neoplasms. Finally, recent research on prognostic and predictive biomarkers including radiomics will be discussed.

Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma

Pancreatic cancer is projected to become the second leading cause of cancer-related mortality in the United States by 2030. This is in part due to the paucity of reliable screening and diagnostic options for early detection. Amongst known pre-malignant pancreatic lesions, pancreatic intraepithelial neoplasia (PanIN) and intraductal papillary mucinous neoplasms (IPMNs) are the most prevalent. The current standard of care for the diagnosis and classification of pancreatic cystic lesions (PCLs) involves cross-sectional imaging studies and endoscopic ultrasound (EUS) and, when indicated, EUS-guided fine needle aspiration and cyst fluid analysis. However, this is suboptimal for the identification and risk stratification of PCLs, with accuracy of only 65-75% for detecting mucinous PCLs. Artificial intelligence (AI) is a promising tool that has been applied to improve accuracy in screening for solid tumors, including breast, lung, cervical, and colon cancer. More recently, it has shown promise in diagnosing pancreatic cancer by identifying high-risk populations, risk-stratifying premalignant lesions, and predicting the progression of IPMNs to adenocarcinoma. This review summarizes the available literature on artificial intelligence in the screening and prognostication of precancerous lesions in the pancreas, and streamlining the diagnosis of pancreatic cancer.

Potential of artificial intelligence in the risk stratification for and early detection of pancreatic cancer

Pancreatic ductal adenocarcinoma (PDAC) is the third most lethal cancer in the United States, with a 5-year life expectancy of 11%. Most symptoms manifest at an advanced stage of the disease when surgery is no longer appropriate. The dire prognosis of PDAC warrants new strategies to improve the outcomes of patients, and early detection has garnered significant attention. However, early detection of PDAC is most often incidental, emphasizing the importance of developing new early detection screening strategies. Due to the low incidence of the disease in the general population, much of the focus for screening has turned to individuals at high risk of PDAC. This enriches the screening population and balances the risks associated with pancreas interventions. The cancers that are found in these high-risk individuals by MRI and/or EUS screening show favorable 73% 5-year overall survival. Even with the emphasis on screening in enriched high-risk populations, only a minority of incident cancers are detected this way. One strategy to improve early detection outcomes is to integrate artificial intelligence (AI) into biomarker discovery and risk models. This expert review summarizes recent publications that have developed AI algorithms for the applications of risk stratification of PDAC using radiomics and electronic health records. Furthermore, this review illustrates the current uses of radiomics and biomarkers in AI for early detection of PDAC. Finally, various challenges and potential solutions are highlighted regarding the use of AI in medicine for early detection purposes.

Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs): an MRI-based radiomic model to determine the malignant degeneration potential

BACKGROUND

Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs) are the most common pancreatic cystic tumors and have a low risk of malignant transformation. Features able to early identify high-risk BD-IPMNs are lacking, and guidelines currently rely on the occurrence of worrisome features (WF) and high-risk stigmata (HRS).

AIM

In our study, we aimed to use a magnetic resonance imaging (MRI) radiomic model to identify features linked to a higher risk of malignant degeneration, and whether these appear before the occurrence of WF and HRS.

METHODS

We retrospectively evaluated adult patients with a known BD-IPMN who had had at least two contrast-enhanced MRI studies at our center and a 24-month minimum follow-up time. MRI acquisition protocol for the two examinations included pre- and post-contrast phases and diffusion-weighted imaging (DWI)/apparent diffusion coefficient (ADC) map. Patients were divided into two groups according to the development of WF or HRS at the end of the follow-up (Group 0 = no WF or HRS; Group 1 = WF or HRS). We segmented the MRI images and quantitative features were extracted and compared between the two groups. Features that showed significant differences (SF) were then included in a LASSO regression method to build a radiomic-based predictive model.

RESULTS

We included 50 patients: 31 in Group 0 and 19 in Group 1. No patients in this cohort developed HRS. At baseline, 47, 67, 38, and 68 SF were identified for pre-contrast T1-weighted (T1-W) sequence, post-contrast T1-W sequence, T2-weighted (T2- W) sequence, and ADC map, respectively. At the end of follow-up, we found 69, 78, 53, and 91 SF, respectively. The radiomic-based predictive model identified 16 SF: more particularly, 5 SF for pre-contrast T1-W sequence, 6 for post-contrast T1-W sequence, 3 for T2-W sequence, and 2 for ADC.

CONCLUSION

We identified radiomic features that correlate significantly with WF in patients with BD-IPMNs undergoing contrast-enhanced MRI. Our MRI-based radiomic model can predict the occurrence of WF.

A CT based radiomics nomogram for differentiation between focal-type autoimmune pancreatitis and pancreatic ductal adenocarcinoma

Objectives

The purpose of this study was to develop and validate an CT-based radiomics nomogram for the preoperative differentiation of focal-type autoimmune pancreatitis from pancreatic ductal adenocarcinoma.

Methods

96 patients with focal-type autoimmune pancreatitis and pancreatic ductal adenocarcinoma have been enrolled in the study (32 and 64 cases respectively). All cases have been confirmed by imaging, clinical follow-up and/or pathology. The imaging data were considered as: 70% training cohort and 30% test cohort. Pancreatic lesions have been manually delineated by two radiologists and image segmentation was performed to extract radiomic features from the CT images. Independent-sample T tests and LASSO regression were used for feature selection. The training cohort was classified using a variety of machine learning-based classifiers, and 5-fold cross-validation has been performed. The classification performance was evaluated using the test cohort. Multivariate logistic regression analysis was then used to develop a radiomics nomogram model, containing the CT findings and Rad-Score. Calibration curves have been plotted showing the agreement between the predicted and actual probabilities of the radiomics nomogram model. Different patients have been selected to test and evaluate the model prediction process. Finally, receiver operating characteristic curves and decision curves were plotted, and the radiomics nomogram model was compared with a single model to visually assess its diagnostic ability.

Results

A total of 158 radiomics features were extracted from each image. 7 features were selected to construct the radiomics model, then a variety of classifiers were used for classification and multinomial logistic regression (MLR) was selected to be the optimal classifier. Combining CT findings with radiomics model, a prediction model based on CT findings and radiomics was finally obtained. The nomogram model showed a good sensitivity and specificity with AUCs of 0.87 and 0.83 in training and test cohorts, respectively. The areas under the curve and decision curve analysis showed that the radiomics nomogram model may provide better diagnostic performance than the single model and achieve greater clinical net benefits than the CT finding model and radiomics signature model individually.

Conclusions

The CT image-based radiomics nomogram model can accurately distinguish between focal-type autoimmune pancreatitis and pancreatic ductal adenocarcinoma patients and provide additional clinical benefits.

Differential diagnosis of pancreatic cystic neoplasms through a radiomics-assisted system

Pancreatic cystic neoplasms (PCNs) are a group of heterogeneous diseases with distinct prognosis. Existing differential diagnosis methods require invasive biopsy or prolonged monitoring. We sought to develop an inexpensive, non-invasive differential diagnosis system for PCNs based on radiomics features and clinical characteristics for a higher total PCN screening rate. We retrospectively analyzed computed tomography images and clinical data from 129 patients with PCN, including 47 patients with intraductal papillary mucinous neoplasms (IPMNs), 49 patients with serous cystadenomas (SCNs), and 33 patients with mucinous cystic neoplasms (MCNs). Six clinical characteristics and 944 radiomics features were tested, and nine features were finally selected for model construction using DXScore algorithm. A five-fold cross-validation algorithm and a test group were applied to verify the results. In the five-fold cross-validation section, the AUC value of our model was 0.8687, and the total accuracy rate was 74.23%, wherein the accuracy rates of IPMNs, SCNs, and MCNs were 74.26%, 78.37%, and 68.00%, respectively. In the test group, the AUC value was 0.8462 and the total accuracy rate was 73.61%. In conclusion, our research constructed an end-to-end powerful PCN differential diagnosis system based on radiomics method, which could assist decision-making in clinical practice.

Classification of pancreatic cystic neoplasms using radiomic feature analysis is equivalent to an experienced academic radiologist: a step toward computer-augmented diagnostics for radiologists

PURPOSE

A wide array of benign and malignant lesions of the pancreas can be cystic and these cystic lesions can have overlapping imaging appearances. The purpose of this study is to compare the diagnostic accuracy of a radiomics-based pancreatic cyst classifier to an experienced academic radiologist.

METHODS

In this IRB-approved retrospective single-institution study, patients with surgically resected pancreatic cysts who underwent preoperative abdominal CT from 2003 to 2016 were identified. Pancreatic cyst(s) and background pancreas were manually segmented, and 488 radiomics features were extracted. Random forest classification based on radiomics features, age, and gender was evaluated with fourfold cross-validation. An academic radiologist blinded to the final pathologic diagnosis reviewed each case and provided the most likely diagnosis.

RESULTS

214 patients were included (64 intraductal papillary mucinous neoplasms, 33 mucinous cystic neoplasms, 60 serous cystadenomas, 24 solid pseudopapillary neoplasms, and 33 cystic neuroendocrine tumors). The radiomics-based machine learning approach showed AUC of 0.940 in pancreatic cyst classification, compared with AUC of 0.895 for the radiologist.

CONCLUSION

Radiomics-based machine learning achieved equivalent performance as an experienced academic radiologist in the classification of pancreatic cysts. The high diagnostic accuracy can potentially maximize the efficiency of healthcare utilization by maximizing detection of high-risk lesions.

Radiomics-based machine learning (ML) classifier for detection of type 2 diabetes on standard-of-care abdomen CTs: a proof-of-concept study

PURPOSE

To determine if pancreas radiomics-based AI model can detect the CT imaging signature of type 2 diabetes (T2D).

METHODS

Total 107 radiomic features were extracted from volumetrically segmented normal pancreas in 422 T2D patients and 456 age-matched controls. Dataset was randomly split into training (300 T2D, 300 control CTs) and test subsets (122 T2D, 156 control CTs). An XGBoost model trained on 10 features selected through top-K-based selection method and optimized through threefold cross-validation on training subset was evaluated on test subset.

RESULTS

Model correctly classified 73 (60%) T2D patients and 96 (62%) controls yielding F1-score, sensitivity, specificity, precision, and AUC of 0.57, 0.62, 0.61, 0.55, and 0.65, respectively. Model's performance was equivalent across gender, CT slice thicknesses, and CT vendors (p values > 0.05). There was no difference between correctly classified versus misclassified patients in the mean (range) T2D duration [4.5 (0-15.4) versus 4.8 (0-15.7) years, p = 0.8], antidiabetic treatment [insulin (22% versus 18%), oral antidiabetics (10% versus 18%), both (41% versus 39%) (p > 0.05)], and treatment duration [5.4 (0-15) versus 5 (0-13) years, p = 0.4].

CONCLUSION

Pancreas radiomics-based AI model can detect the imaging signature of T2D. Further refinement and validation are needed to evaluate its potential for opportunistic T2D detection on millions of CTs that are performed annually.

Update on quantitative radiomics of pancreatic tumors

Radiomics is a newer approach for analyzing radiological images obtained from conventional imaging modalities such as computed tomography, magnetic resonance imaging, endoscopic ultrasonography, and positron emission tomography. Radiomics involves extracting quantitative data from the images and assessing them to identify diagnostic or prognostic features such as tumor grade, resectability, tumor response to neoadjuvant therapy, and survival. The purpose of this review is to discuss the basic principles of radiomics and provide an overview of the current clinical applications of radiomics in the field of pancreatic tumors.

Artificial Intelligence Applied to Pancreatic Imaging: A Narrative Review

The diagnosis, evaluation, and treatment planning of pancreatic pathologies usually require the combined use of different imaging modalities, mainly, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). Artificial intelligence (AI) has the potential to transform the clinical practice of medical imaging and has been applied to various radiological techniques for different purposes, such as segmentation, lesion detection, characterization, risk stratification, or prediction of response to treatments. The aim of the present narrative review is to assess the available literature on the role of AI applied to pancreatic imaging. Up to now, the use of computer-aided diagnosis (CAD) and radiomics in pancreatic imaging has proven to be useful for both non-oncological and oncological purposes and represents a promising tool for personalized approaches to patients. Although great developments have occurred in recent years, it is important to address the obstacles that still need to be overcome before these technologies can be implemented into our clinical routine, mainly considering the heterogeneity among studies.

Radiomics in pancreatic cancer for oncologist: Present and future

Radiomics is changing the world of medicine and more specifically the world of oncology. Early diagnosis and treatment improve the prognosis of patients with cancer. After treatment, the evaluation of the response will determine future treatments. In oncology, every change in treatment means a loss of therapeutic options and this is key in pancreatic cancer. Radiomics has been developed in oncology in the early diagnosis and differential diagnosis of benign and malignant lesions, in the evaluation of response, in the prediction of possible side effects, marking the risk of recurrence, survival and prognosis of the disease. Some studies have validated its use to differentiate normal tissues from tumor tissues with high sensitivity and specificity, and to differentiate cystic lesions and pancreatic neuroendocrine tumor grades with texture parameters. In addition, these parameters have been related to survival in patients with pancreatic cancer and to response to radiotherapy and chemotherapy. This review aimed to establish the current status of the use of radiomics in pancreatic cancer and future perspectives.

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.

Cystic Neoplasms of the Pancreas: Differential Diagnosis and Radiology Correlation

Although the probability of pancreatic cystic neoplasms (PCNs) being detected is raising year by year, their differential diagnosis and individualized treatment are still a challenge in clinical work. PCNs are tumors containing cystic components with different biological behaviors, and their clinical manifestations, epidemiology, imaging features, and malignant risks are different. Some are benign [e.g., serous cystic neoplasms (SCNs)], with a barely possible that turning into malignant, while others display a low or higher malignant risk [e.g., solid pseudopapillary neoplasms (SPNs), intraductal papillary mucinous neoplasms (IPMNs), and mucinous cystic neoplasms (MCNs)]. PCN management should concentrate on preventing the progression of malignant tumors while preventing complications caused by unnecessary surgical intervention. Clinically, various advanced imaging equipment are usually combined to obtain a more reliable preoperative diagnosis. The challenge for clinicians and radiologists is how to accurately diagnose PCNs before surgery so that corresponding surgical methods and follow-up strategies can be developed or not, as appropriate. The objective of this review is to sum up the clinical features, imaging findings and management of the most common PCNs according to the classic literature and latest guidelines.

Radiomics Analysis for Predicting Malignant Potential of Intraductal Papillary Mucinous Neoplasms of the Pancreas: Comparison of CT and MRI

RATIONALE AND OBJECTIVES

To compare the performance of CT and MRI radiomics for predicting the malignant potential of intraductal papillary mucinous neoplasms (IPMNs) of the pancreas, and to investigate their value compared to the revised 2017 international consensus Fukuoka guidelines.

MATERIALS AND METHODS

Sixty patients with surgically confirmed IPMNs (37 malignant and 23 benign) were included. Radiomics features were extracted from arterial and venous phase images of CT and T2-weighted images of MRI, respectively. Intraclass correlation coefficients for the radiomics features were calculated to assess the interobserver reproducibility. The least absolute shrinkage and selection operator algorithm was used for feature selection. Radiomics models were constructed based on selected features with logistic regression (LR) and support vector machine (SVM). A clinical and imaging model was constructed based on independent predictors of the revised 2017 Fukuoka guidelines determined in multivariate logistic regression with forward elimination.

RESULTS

The reproducibility of MRI radiomics features was higher than that of CT radiomics features, regardless of arterial or venous phase features (all p < 0.001). MRI radiomics models achieved improved AUCs (0.879 with LR and 0.940 with SVM, respectively), than that of CT radiomics models (0.811 with LR and 0.864 with SVM, respectively). All radiomics models provided better predictive performance than the clinical and imaging model (AUC = 0.764).

CONCLUSION

The MRI radiomics models with higher reproducibility radiomics features performed better than CT radiomics models for predicting the malignant potential of IPMNs. The performance of radiomics models was superior to the clinical and imaging model based on Fukuoka guidelines.

Baseline CT-based Radiomic Features Aid Prediction of Nodal Positivity after Neoadjuvant Therapy in Pancreatic Cancer

Purpose To study the association between CT-derived textural features of pancreatic cancer and patient outcome. Materials and Methods This retrospective study evaluated 54 patients (median age, 62 years [range, 40-88 years]; 32 men) with pancreatic cancer who underwent chemoradiation followed by surgical resection and lymph node dissection from May 2012 to June 2016. Three-dimensional segmentation of the pancreatic tumor was performed on baseline dual-energy CT images: 70-keV pancreatic parenchymal phase (PPP) images and iodine material density images. Then, 15 and 19 radiomic features were extracted from each phase, respectively. Logistic regression with elastic net regularization was used to select textural features associated with outcome, and receiver operating characteristic analysis evaluated feature performance. Survival curves were generated using the Kaplan-Meier method. Results The feature of integral total (∫ T), representing the mean intensity in Hounsfield units times the contour volume in milliliters of PPP imaging (hereafter, "∫ T (HU·mL) (PPP)"), is inversely associated with posttherapy pathologic lymph node (ypN) category. A threshold ∫ T (HU·mL) (PPP) less than 507.85 predicted ypN1-2 classification with 96% sensitivity, 34% specificity, and area under the curve of 0.61. Patients with an ∫ T (HU·mL) (PPP) of less than 507.85 had decreased overall survival (median, 2.8 years) compared with patients with an ∫ T (HU·mL) (PPP) of 507.85 or greater (one event at 3.4 years) (P = .006). Patients with an ∫ T (HU·mL) (PPP) of less than 507.85 had decreased progression-free survival (median, 1.5 years) compared with patients with an ∫ T (HU·mL) (PPP) of 507.85 or greater (median, 2.7 years) (P = .001). Conclusion A CT-based radiomic signature may help predict ypN category in patients with pancreatic cancer. Keywords: CT-Dual Energy, Abdomen/GI, Pancreas, Tumor Response, Outcomes Analysis © RSNA, 2022 Supplemental material is available for this article.

Recent advances in the diagnostic evaluation of pancreatic cystic lesions

Pancreatic cystic lesions (PCLs) are becoming more prevalent due to more frequent abdominal imaging and the increasing age of the general population. It has become crucial to identify these PCLs and subsequently risk stratify them to guide management. Given the high morbidity associated with pancreatic surgery, only those PCLs at high risk for malignancy should undergo such treatment. However, current diagnostic testing is suboptimal at accurately diagnosing and risk stratifying PCLs. Therefore, research has focused on developing new techniques for differentiating mucinous from non-mucinous PCLs and identifying high risk lesions for malignancy. Cross sectional imaging radiomics can potentially improve the predictive accuracy of primary risk stratification of PCLs at the time of detection to guide invasive testing. While cyst fluid glucose has reemerged as a potential biomarker, cyst fluid molecular markers have improved accuracy for identifying specific types of PCLs. Endoscopic ultrasound guided approaches such as confocal laser endomicroscopy and through the needle microforceps biopsy have shown a good correlation with histopathological findings and are evolving techniques for identifying and risk stratifying PCLs. While most of these recent diagnostics are only practiced at selective tertiary care centers, they hold a promise that management of PCLs will only get better in the future.

Retrospective Analysis of the Value of Enhanced CT Radiomics Analysis in the Differential Diagnosis Between Pancreatic Cancer and Chronic Pancreatitis

Purpose

To investigate the feasibility of enhanced computed tomography (CT) radiomics analysis to differentiate between pancreatic cancer (PC) and chronic pancreatitis.

Methods and materials

The CT images of 151 PCs and 24 chronic pancreatitis were retrospectively analyzed in the three-dimensional regions of interest on arterial phase (AP) and venous phase (VP) and segmented by MITK software. A multivariable logistic regression model was established based on the selected radiomics features. The radiomics score was calculated, and the nomogram was established. The discrimination of each model was analyzed by the receiver operating characteristic curve (ROC). Decision curve analysis (DCA) was used to evaluate clinical utility. The precision recall curve (PRC) was used to evaluate whether the model is affected by data imbalance. The Delong test was adopted to compare the diagnostic efficiency of each model.

Results

Significant differences were observed in the distribution of gender (P = 0.034), carbohydrate antigen 19-9 (P < 0.001), and carcinoembryonic antigen (P < 0.001) in patients with PC and chronic pancreatitis. The area under the ROC curve (AUC) value of AP multivariate regression model, VP multivariate regression model, AP combined with VP features model (Radiomics), clinical feature model, and radiomics combined with clinical feature model (COMB) was 0.905, 0.941, 0.941, 0.822, and 0.980, respectively. The sensitivity and specificity of the COMB model were 0.947 and 0.917, respectively. The results of DCA showed that the COMB model exhibited net clinical benefits and PRC shows that COMB model have good precision and recall (sensitivity).

Conclusion

The COMB model could be a potential tool to distinguish PC from chronic pancreatitis and aid in clinical decisions.

Machine learning principles applied to CT radiomics to predict mucinous pancreatic cysts

PURPOSE

Current diagnostic and treatment modalities for pancreatic cysts (PCs) are invasive and are associated with patient morbidity. The purpose of this study is to develop and evaluate machine learning algorithms to delineate mucinous from non-mucinous PCs using non-invasive CT-based radiomics.

METHODS

A retrospective, single-institution analysis of patients with non-pseudocystic PCs, contrast-enhanced computed tomography scans within 1 year of resection, and available surgical pathology were included. A quantitative imaging software platform was used to extract radiomics. An extreme gradient boosting (XGBoost) machine learning algorithm was used to create mucinous classifiers using texture features only, or radiomic/radiologic and clinical combined models. Classifiers were compared using performance scoring metrics. Shapely additive explanation (SHAP) analyses were conducted to identify variables most important in model construction.

RESULTS

Overall, 99 patients and 103 PCs were included in the analyses. Eighty (78%) patients had mucinous PCs on surgical pathology. Using multiple fivefold cross validations, the texture features only and combined XGBoost mucinous classifiers demonstrated an area under the curve of 0.72 ± 0.14 and 0.73 ± 0.14, respectively. By SHAP analysis, root mean square, mean attenuation, and kurtosis were the most predictive features in the texture features only model. Root mean square, cyst location, and mean attenuation were the most predictive features in the combined model.

CONCLUSION

Machine learning principles can be applied to PC texture features to create a mucinous phenotype classifier. Model performance did not improve with the combined model. However, specific radiomic, radiologic, and clinical features most predictive in our models can be identified using SHAP analysis.

Application of artificial intelligence to pancreatic adenocarcinoma

BACKGROUND AND OBJECTIVES

Pancreatic cancer (PC) is one of the deadliest cancers worldwide although substantial advancement has been made in its comprehensive treatment. The development of artificial intelligence (AI) technology has allowed its clinical applications to expand remarkably in recent years. Diverse methods and algorithms are employed by AI to extrapolate new data from clinical records to aid in the treatment of PC. In this review, we will summarize AI's use in several aspects of PC diagnosis and therapy, as well as its limits and potential future research avenues.

METHODS

We examine the most recent research on the use of AI in PC. The articles are categorized and examined according to the medical task of their algorithm. Two search engines, PubMed and Google Scholar, were used to screen the articles.

RESULTS

Overall, 66 papers published in 2001 and after were selected. Of the four medical tasks (risk assessment, diagnosis, treatment, and prognosis prediction), diagnosis was the most frequently researched, and retrospective single-center studies were the most prevalent. We found that the different medical tasks and algorithms included in the reviewed studies caused the performance of their models to vary greatly. Deep learning algorithms, on the other hand, produced excellent results in all of the subdivisions studied.

CONCLUSIONS

AI is a promising tool for helping PC patients and may contribute to improved patient outcomes. The integration of humans and AI in clinical medicine is still in its infancy and requires the in-depth cooperation of multidisciplinary personnel.

Texture analysis imaging "what a clinical radiologist needs to know"

Texture analysis has arisen as a tool to explore the amount of data contained in images that cannot be explored by humans visually. Radiomics is a method that extracts a large number of features from radiographic medical images using data-characterisation algorithms. These features, termed radiomic features, have the potential to uncover disease characteristics. The goal of both radiomics and texture analysis is to go beyond size or human-eye based semantic descriptors, to enable the non-invasive extraction of quantitative radiological data to correlate them with clinical outcomes or pathological characteristics. In the latest years there has been a flourishing sub-field of radiology where texture analysis and radiomics have been used in many settings. It is difficult for the clinical radiologist to cope with such amount of data in all the different radiological sub-fields and to identify the most significant papers. The aim of this review is to provide a tool to better understand the basic principles underlining texture analysis and radiological data mining and a summary of the most significant papers of the latest years.

Radiomic analysis to predict local response in locally advanced pancreatic cancer treated with stereotactic body radiation therapy

PURPOSE

Aim of this study is to assess the ability of contrast-enhanced CT image-based radiomic analysis to predict local response (LR) in a retrospective cohort of patients affected by pancreatic cancer and treated with stereotactic body radiation therapy (SBRT). Secondary aim is to evaluate progression free survival (PFS) and overall survival (OS) at long-term follow-up.

METHODS

Contrast-enhanced-CT images of 37 patients who underwent SBRT were analyzed. Two clinical variables (BED, CTV volume), 27 radiomic features were included. LR was used as the outcome variable to build the predictive model. The Kaplan-Meier method was used to evaluate PFS and OS.

RESULTS

Three variables were statistically correlated with the LR in the univariate analysis: Intensity Histogram (StdValue feature), Gray Level Cooccurrence Matrix (GLCM25_Correlation feature) and Neighbor Intensity Difference (NID25_Busyness feature). Multivariate model showed GLCM25_Correlation (P = 0.007) and NID25_Busyness (P = 0.03) as 2 independent predictive variables for LR. The odds ratio values of GLCM25_Correlation and NID25_Busyness were 0.07 (95%CI 0.01-0.49) and 8.10 (95%CI 1.20-54.40), respectively. The area under the curve for the multivariate logistic regressive model was 0.851 (95%CI 0.724-0.978). At a median follow-up of 30 months, median PFS was 7 months (95%CI 6-NA); median OS was 11 months (95%CI 10-22 months).

CONCLUSIONS

This analysis identified a radiomic signature that correlates with LR. To confirm these results, prospective studies could identify patient sub-groups with different rates of radiation dose-response to define a more personalized SBRT approach.

Machine Learning: Applications and Advanced Progresses of Radiomics in Endocrine Neoplasms

Endocrine neoplasms remain a great threat to human health. It is extremely important to make a clear diagnosis and timely treatment of endocrine tumors. Machine learning includes radiomics, which has long been utilized in clinical cancer research. Radiomics refers to the extraction of valuable information by analyzing a large amount of standard data with high-throughput medical images mainly including computed tomography, positron emission tomography, magnetic resonance imaging, and ultrasound. With the quantitative imaging analysis and model building, radiomics can reflect specific underlying characteristics of a disease that otherwise could not be evaluated visually. More and more promising results of radiomics in oncological practice have been seen in recent years. Radiomics may have the potential to supplement traditional imaging analysis and assist in providing precision medicine for patients. Radiomics had developed rapidly in endocrine neoplasms practice in the past decade. In this review, we would introduce the general workflow of radiomics and summarize the applications and developments of radiomics in endocrine neoplasms in recent years. The limitations of current radiomic research studies and future development directions would also be discussed.

Cystic pancreatic lesions: MR imaging findings and management

Cystic pancreatic lesions (CPLs) are frequently casual findings in radiological examinations performed for other reasons in patients with unrelated symptoms. As they require different management according to their histological nature, differential diagnosis is essential. Radiologist plays a key role in the diagnosis and management of these lesions as imaging is able to correctly characterize most of them and thus address to a correct management. The first step for a correct characterization is to look for a communication between the CPLs and the main pancreatic duct, and then, it is essential to evaluate the morphology of the lesions. Age, sex and a history of previous pancreatic pathologies are important information to be used in the differential diagnosis. As some CPLs with different pathologic backgrounds can show the same morphological findings, differential diagnosis can be difficult, and thus, the final diagnosis can require other techniques, such as endoscopic ultrasound, endoscopic ultrasound-fine needle aspiration and endoscopic ultrasound-through the needle biopsy, and multidisciplinary management is important for a correct management.

Modeling Texture in Deep 3D CNN for Survival Analysis

Radiomics has shown remarkable potential for predicting the survival outcome for various types of cancers such as pancreatic ductal adenocarcinoma (PDAC). However, to date, there has been limited research using convolutional neural networks (CNN) with radiomic methods for this task, due to their requirement for large training sets. To overcome this issue, we propose a new type of radiomic descriptor modeling the distribution of learned features with a Gaussian mixture model (GMM). These parametric features (GMM-CNN) are computed from gross tumor volumes of PDAC patients defined semi-automatically in pre-operative computed tomography (CT) scans. We use the proposed GMM-CNN features as input to a robust classifier based on random forests (RF) to predict the survival outcome of patients with PDAC. Our experiments assess the advantage of GMM-CNN compared to employing the same 3D CNN model directly, standard radiomic (i.e., histogram, texture and shape), conditional entropy (CENT) based on 3DCNN, and clinical features (i.e., serum carbohydrate antigen 19-9 and chemotherapy neoadjuvant). Using the RF model (100 samples for training; 59 samples for validation), GMM-CNN features provided the highest area under the ROC curve (AUC) of 72.0% (p =  6.4×10^-5) compared to 64.0% (p = 0.01) for the 3D CNN model output, 66.8% (p = 0.01) for standard radiomic features, 64.2% (p = 0.003) for CENT, and 57.6% (p = 0.3) for clinical variables. Our results suggest that the proposed GMM-CNN features used with a RF classifier can significantly improve the capacity to prognosticate PDAC patients prior to surgery via routinely-acquired imaging data.

Comparison of Radiomic Features in a Diverse Cohort of Patients With Pancreatic Ductal Adenocarcinomas

Background

Significant racial disparities in pancreatic cancer incidence and mortality rates exist, with the highest rates in African Americans compared to Non-Hispanic Whites and Hispanic/Latinx populations. Computer-derived quantitative imaging or “radiomic” features may serve as non-invasive surrogates for underlying biological factors and heterogeneity that characterize pancreatic tumors from African Americans, yet studies are lacking in this area. The objective of this pilot study was to determine if the radiomic tumor profile extracted from pretreatment computed tomography (CT) images differs between African Americans, Non-Hispanic Whites, and Hispanic/Latinx with pancreatic cancer.

Methods

We evaluated a retrospective cohort of 71 pancreatic cancer cases (23 African American, 33 Non-Hispanic White, and 15 Hispanic/Latinx) who underwent pretreatment CT imaging at Moffitt Cancer Center and Research Institute. Whole lesion semi-automated segmentation was performed on each slice of the lesion on all pretreatment venous phase CT exams using Healthmyne Software (Healthmyne, Madison, WI, USA) to generate a volume of interest. To reduce feature dimensionality, 135 highly relevant non-texture and texture features were extracted from each segmented lesion and analyzed for each volume of interest.

Results

Thirty features were identified and significantly associated with race/ethnicity based on Kruskal-Wallis test. Ten of the radiomic features were highly associated with race/ethnicity independent of tumor grade, including sphericity, volumetric mean Hounsfield units (HU), minimum HU, coefficient of variation HU, four gray level texture features, and two wavelet texture features. A radiomic signature summarized by the first principal component partially differentiated African American from non-African American tumors (area underneath the curve = 0.80). Poorer survival among African Americans compared to Non-African Americans was observed for tumors with lower volumetric mean CT [HR: 3.90 (95% CI:1.19–12.78), p=0.024], lower GLCM Avg Column Mean [HR:4.75 (95% CI: 1.44,15.37), p=0.010], and higher GLCM Cluster Tendency [HR:3.36 (95% CI: 1.06–10.68), p=0.040], and associations persisted in volumetric mean CT and GLCM Avg Column after adjustment for key clinicopathologic factors.

Conclusions

This pilot study identified several textural radiomics features associated with poor overall survival among African Americans with PDAC, independent of other prognostic factors such as grade. Our findings suggest that CT radiomic features may serve as surrogates for underlying biological factors and add value in predicting clinical outcomes when integrated with other parameters in ongoing and future studies of cancer health disparities.

Pancreatic cyst characterization: maximum axial diameter does not measure up

BACKGROUND

Unidimensional size is commonly used to risk stratify pancreatic cysts (PCs) despite inconsistent performance. The current study aimed to determine if unidimensional size, demonstrated by maximum axial diameter (MAD), is an appropriate surrogate measurement for volume and surface area.

METHODS

Patients with cross-sectional imaging of PCs from 2012 to 2013 were identified. Cyst MAD, volume, and surface area were measured using quantitative imaging software. Non-pseudocystic PCs >1 cm were selected for inclusion to assess MAD correlation with volume and surface area. Cysts imaged twice >1 year apart were selected to evaluate volumetric growth rate.

RESULTS

In total, 195 cysts were included. Overall, MAD was strongly correlated with volume (r = 0.83) and surface area (r = 0.93). However, cysts 1-2 cm and 2-3 cm were weakly correlated with volume and surface area: r = 0.78, 0.57 and 0.82, 0.61, respectively. Cyst volumes and surface areas varied widely within unidimensional size groups with 51% and 40% of volumes and surface areas overlapping unidimensional size groups, respectively. Estimated changes in volume poorly predicted measured changes in volume with 42% of cysts having >100% absolute percent difference.

CONCLUSIONS

Pancreatic cyst volume and surface area may be useful adjunct measurements to risk stratify patients and surveil cyst changes and deserves further study.

Preoperative differentiation of serous cystic neoplasms from mucin-producing pancreatic cystic neoplasms using a CT-based radiomics nomogram

PURPOSE

To develop and validate a CT-based radiomics nomogram in preoperative differential diagnosis of SCNs from mucin-producing PCNs.

MATERIAL AND METHODS

A total of 89 patients consisting of 31 SCNs, 30 IPMNs, and 28 MCNs who underwent preoperative CT were analyzed. A total of 710 radiomics features were extracted from each case. Patients were divided into training (n = 63) and validation cohorts (n = 26) with a ratio of 7:3. Least absolute shrinkage and selection operator (LASSO) method and logistic regression analysis were used for feature selection and model construction. A nomogram was created from a comprehensive model consisting of clinical features and the fusion radiomics signature. A decision curve analysis was used for clinical decisions.

RESULTS

The radiomics features extracted from CT could assist with the differentiation of SCNs from mucin-producing PCNs in both the training and validation cohorts. The signature of the combination of the plain, late arterial, and venous phases had the largest areas under the curve (AUCs) of 0.960 (95% CI 0.910-1) in the training cohort and 0.817 (95% CI 0.651-0.983) in the validation cohort with good calibration. The value and efficacy of the nomogram was verified using decision curve analysis.

CONCLUSION

A comprehensive nomogram incorporating clinical features and fusion radiomics signature can differentiate SCNs from mucin-producing PCNs.

Decoding incidental ovarian lesions: use of texture analysis and machine learning for characterization and detection of malignancy

PURPOSE

To compare CT texture features of benign and malignant ovarian lesions and to build a machine learning model to detect malignancy in incidental ovarian lesions.

METHODS

In this IRB-approved, HIPAA-compliant, retrospective study, 427 consecutive patients with incidental ovarian lesions detected on contrast-enhanced CT (348, 81.5% benign and 79, 18.5% malignant) were included. The following CT texture features were analyzed using commercially available software (TexRAD, Feedback Plc, Cambridge, UK): total pixel, mean, standard deviation (SD), entropy, mean value of positive pixels (MPP), skewness, kurtosis and entropy. Three machine learning models were created by combining texture features and patients' age, and performance of these models was assessed using tenfold cross-validation. Receiver operating characteristics (ROC) were constructed to assess sensitivity and specificity. The cutoff value was picked using a cost-weighted method.

RESULTS

Total pixels, mean, SD, entropy, MPP, and skewness were significantly different between benign and malignant groups (p < 0.05). With a selected 10 as a cost factor to optimize cutoff value selection, sensitivity 92%, specificity 60% in the random forest (RF) model, sensitivity 91%, specificity 69% in SVM model, and sensitivity 92%, specificity 61% in the logistic regression, respectively.

CONCLUSION

CT texture analysis could provide objective imaging analysis of incidental ovarian lesions and ML models using CT texture features and age demonstrated high sensitivity and moderate specificity for detection of malignant lesions.

Radiomic nomogram based on MRI to predict grade of branching type intraductal papillary mucinous neoplasms of the pancreas: a multicenter study

Background

Accurate diagnosis of high-grade branching type intraductal papillary mucinous neoplasms (BD-IPMNs) is challenging in clinical setting. We aimed to construct and validate a nomogram combining clinical characteristics and radiomic features for the preoperative prediction of low and high-grade in BD-IPMNs.

Methods

Two hundred and two patients from three medical centers were enrolled. The high-grade BD-IPMN group comprised patients with high-grade dysplasia and invasive carcinoma in BD-IPMN (n = 50). The training cohort comprised patients from the first medical center (n = 103), and the external independent validation cohorts comprised patients from the second and third medical centers (n = 48 and 51). Within 3 months prior to surgery, all patients were subjected to magnetic resonance examination. The volume of interest was delineated on T1-weighted (T1-w) imaging, T2-weighted (T2-w) imaging, and contrast-enhanced T1-weighted (CET1-w) imaging, respectively, on each tumor slice. Quantitative image features were extracted using MITK software (G.E.). The Mann-Whitney U test or independent-sample t-test, and LASSO regression, were applied for data dimension reduction, after which a radiomic signature was constructed for grade assessment. Based on the training cohort, we developed a combined nomogram model incorporating clinical variables and the radiomic signature. Decision curve analysis (DCA), a receiver operating characteristic curve (ROC), a calibration curve, and the area under the ROC curve (AUC) were used to evaluate the utility of the constructed model based on the external independent validation cohorts.

Results

To predict tumor grade, we developed a nine-feature-combined radiomic signature. For the radiomic signature, the AUC values of high-grade disease were 0.836 in the training cohort, 0.811 in external validation cohort 1, and 0.822 in external validation cohort 2. The CA19–9 level and main pancreatic duct size were identified as independent parameters of high-grade of BD-IPMNs using multivariate logistic regression analysis. The CA19–9 level and main pancreatic duct size were then used to construct the radiomic nomogram. Using the radiomic nomogram, the high-grade disease-associated AUC values were 0.903 (training cohort), 0.884 (external validation cohort 1), and 0.876 (external validation cohort 2). The clinical utility of the developed nomogram was verified using the calibration curve and DCA.

Conclusions

The developed radiomic nomogram model could effectively distinguish high-grade patients with BD-IPMNs preoperatively. This preoperative identification might improve treatment methods and promote personalized therapy in patients with BD-IPMNs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-021-00395-6.

Artificial Intelligence and Early Detection of Pancreatic Cancer: 2020 Summative Review

ABSTRACT

Despite considerable research efforts, pancreatic cancer is associated with a dire prognosis and a 5-year survival rate of only 10%. Early symptoms of the disease are mostly nonspecific. The premise of improved survival through early detection is that more individuals will benefit from potentially curative treatment. Artificial intelligence (AI) methodology has emerged as a successful tool for risk stratification and identification in general health care. In response to the maturity of AI, Kenner Family Research Fund conducted the 2020 AI and Early Detection of Pancreatic Cancer Virtual Summit (www.pdac-virtualsummit.org) in conjunction with the American Pancreatic Association, with a focus on the potential of AI to advance early detection efforts in this disease. This comprehensive presummit article was prepared based on information provided by each of the interdisciplinary participants on one of the 5 following topics: Progress, Problems, and Prospects for Early Detection; AI and Machine Learning; AI and Pancreatic Cancer-Current Efforts; Collaborative Opportunities; and Moving Forward-Reflections from Government, Industry, and Advocacy. The outcome from the robust Summit conversations, to be presented in a future white paper, indicate that significant progress must be the result of strategic collaboration among investigators and institutions from multidisciplinary backgrounds, supported by committed funders.

Multi-Omic Biomarkers as Potential Tools for the Characterisation of Pancreatic Cystic Lesions and Cancer: Innovative Patient Data Integration

Pancreatic cancer (PC) is regarded as one of the most lethal malignant diseases in the world, with GLOBOCAN 2020 estimates indicating that PC was responsible for almost half a million deaths worldwide in 2020. Pancreatic cystic lesions (PCLs) are fluid-filled structures found within or on the surface of the pancreas, which can either be pre-malignant or have no malignant potential. While some PCLs are found in symptomatic patients, nowadays many PCLs are found incidentally in patients undergoing cross-sectional imaging for other reasons-so called 'incidentalomas'. Current methods of characterising PCLs are imperfect and vary hugely between institutions and countries. As such, there is a profound need for improved diagnostic algorithms. This could facilitate more accurate risk stratification of those PCLs that have malignant potential and reduce unnecessary surveillance. As PC continues to have such a poor prognosis, earlier recognition and risk stratification of PCLs may lead to better treatment protocols. This review will focus on the importance of biomarkers in the context of PCLs and PCand outline how current 'omics'-related work could contribute to the identification of a novel integrated biomarker profile for the risk stratification of patients with PCLs and PC.

S100A4 overexpression in pancreatic ductal adenocarcinoma: imaging biomarkers from whole-tumor evaluation with MRI and texture analysis

OBJECTIVE

To investigate the relationship between imaging findings and S100A4 overexpression in pancreatic ductal adenocarcinoma (PDAC) and to determine imaging biomarkers of S100A4 overexpression from whole-tumor evaluation with MRI and texture analysis.

METHODS

A total of 60 patients with pathologically confirmed PDAC were included in the study. All patients underwent preoperative abdominal contrast-enhanced MRI examination with Magnetom Aera (Siemens Healthcare, Germany, 1.5 T) at our institute. Whole-tumor evaluation including texture analysis was performed. Sections of specimens were reviewed, and the S100A4 expression status was quantitatively evaluated. Univariate and multivariate logistic regression analyses were conducted to find imaging biomarkers that could predict S100A4 overexpression.

RESULTS

Twenty-four tumors (40.0%) had negative results for S100A4 overexpression, and 36 tumors (60.0%) exhibited overexpression. After univariate and multivariate analysis, distal pancreatic duct dilatation, T₁WI_10th percentile and the enhancement rate difference between delayed phase (DP) and portal venous phase (PVP) were identified to predict S100A4 overexpression in PDAC independently (p = 0.009, 0.012 and 0.044), with odds ratios (ORs) of 0.102, 0.139 and 4.645, respectively. The area under the ROC curve (AUC) values were 0.715, 0.707 and 0.691. The AUC value of the proposed model was 0.877 with a sensitivity of 80.6% and specificity of 75.0%.

CONCLUSION

A model including distal pancreatic duct dilatation, T₁WI_10th percentile and the enhancement rate difference between the DP and PVP could predict S100A4 overexpression in PDAC as imaging biomarkers.

Applications of artificial intelligence in pancreatic and biliary diseases

The application of artificial intelligence (AI) in medicine has increased rapidly with respect to tasks including disease detection/diagnosis, risk stratification, and prognosis prediction. With recent advances in computing power and algorithms, AI has shown promise in taking advantage of vast electronic health data and imaging studies to supplement clinicians. Machine learning and deep learning are the most widely used AI methodologies for medical research and have been applied in pancreatobiliary diseases for which diagnosis and treatment selection are often complicated and require joint consideration of data from multiple sources. The aim of this review is to provide a concise introduction of the major AI methodologies and the current landscape of AI research in pancreatobiliary diseases.

Impact of quantization algorithm and number of gray level intensities on variability and repeatability of low field strength magnetic resonance image-based radiomics texture features

PURPOSE

The purpose of this work was to investigate the impact of quantization preprocessing parameter selection on variability and repeatability of texture features derived from low field strength magnetic resonance (MR) images.

METHODS

Texture features were extracted from low field strength images of a daily image QA phantom with four texture inserts. Feature variability over time was quantified using all combinations of three quantization algorithms and four different numbers of gray level intensities. In addition, texture features were extracted using the same combinations from the low field strength MR images of the gross tumor volume (GTV) and left kidney of patients with repeated set up scans. The impact of region of interest (ROI) preprocessing on repeatability was investigated with a test-retest study design.

RESULTS

The phantom ROIs quantized to 64 Gy level intensities using the histogram equalization method resulted in the greatest number of features with the least variability. There was no clear method that resulted in the highest repeatability in the GTV or left kidney. However, eight texture features extracted from the GTV were repeatable regardless of ROI processing combination.

CONCLUSION

Low field strength MR images can provide a stable basis for texture analysis with ROIs quantized to 64 Gy levels using histogram equalization, but there is no clear optimal combination for repeatability.

Pancreas image mining: a systematic review of radiomics

OBJECTIVES

To systematically review published studies on the use of radiomics of the pancreas.

METHODS

The search was conducted in the MEDLINE database. Human studies that investigated the applications of radiomics in diseases of the pancreas were included. The radiomics quality score was calculated for each included study.

RESULTS

A total of 72 studies encompassing 8863 participants were included. Of them, 66 investigated focal pancreatic lesions (pancreatic cancer, precancerous lesions, or benign lesions); 4, pancreatitis; and 2, diabetes mellitus. The principal applications of radiomics were differential diagnosis between various types of focal pancreatic lesions (n = 19), classification of pancreatic diseases (n = 23), and prediction of prognosis or treatment response (n = 30). Second-order texture features were most useful for the purpose of differential diagnosis of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature), whereas filtered image features were most useful for the purpose of classification of diseases of the pancreas and prediction of diseases of the pancreas (with 100% of studies investigating them found a statistically significant feature). The median radiomics quality score of the included studies was 28%, with the interquartile range of 22% to 36%. The radiomics quality score was significantly correlated with the number of extracted radiomics features (r = 0.52, p < 0.001) and the study sample size (r = 0.34, p = 0.003).

CONCLUSIONS

Radiomics of the pancreas holds promise as a quantitative imaging biomarker of both focal pancreatic lesions and diffuse changes of the pancreas. The usefulness of radiomics features may vary depending on the purpose of their application. Standardisation of image acquisition protocols and image pre-processing is warranted prior to considering the use of radiomics of the pancreas in routine clinical practice.

KEY POINTS

• Methodologically sound studies on radiomics of the pancreas are characterised by a large sample size and a large number of extracted features. • Optimisation of the radiomics pipeline will increase the clinical utility of mineable pancreas imaging data. • Radiomics of the pancreas is a promising personalised medicine tool in diseases of the pancreas.

Assessment of malignant potential in intraductal papillary mucinous neoplasms of the pancreas using MR findings and texture analysis

OBJECTIVES

To investigate the utility of MR findings and texture analysis for predicting the malignant potential of pancreatic intraductal papillary mucinous neoplasms (IPMNs).

METHODS

Two hundred forty-eight patients with surgically confirmed IPMNs (106 malignant [invasive carcinoma/high-grade dysplasia] and 142 benign [low/intermediate-grade dysplasia]) and who underwent magnetic resonance imaging (MRI) with MR cholangiopancreatography (MRCP) were included. Two reviewers independently analyzed MR findings as proposed by the 2017 international consensus guidelines. Texture analysis of MRCP was also performed. A multivariate logistic regression analysis was used to identify predictors for malignant IPMNs. Diagnostic performance was also analyzed using receiver operating curve analysis.

RESULTS

Among MR findings, enhancing mural nodule size ≥ 5 mm, main pancreatic duct (MPD) ≥ 10 mm or MPD of 5 to 9 mm, and abrupt change of MPD were significant predictors for malignant IPMNs (p < 0.05). Among texture variables, significant predictors were effective diameter, surface area, sphericity, compactness, entropy, and gray-level co-occurrence matrix entropy (p < 0.05). At multivariate analysis, enhancing mural nodule ≥ 5 mm (odds ratios (ORs), 6.697 and 6.968, for reviewers 1 and 2, respectively), MPD ≥ 10 mm or MPD of 5 to 9 mm (ORs, 4.098 and 4.215, and 2.517 and 3.055, respectively), larger entropy (ORs, 1.485 and 1.515), and smaller compactness (ORs, 0.981 and 0.977) were significant predictors for malignant IPMNs (p < 0.05). When adding texture variable to MR findings, diagnostic performance for predicting malignant IPMNs improved from 0.80 and 0.78 to 0.85 and 0.85 in both reviewers (p < 0.05), respectively.

CONCLUSIONS

MRCP-derived texture features are useful for predicting malignant IPMNs, and the addition of texture analysis to MR features may improve diagnostic performance for predicting malignant IPMNs.

KEY POINTS

• Among the MR imaging findings, an enhancing mural nodule size ≥ 5 mm and dilated main pancreatic ducts are independent predictors for malignant IPMNs. • Greater entropy and smaller compactness on MR texture analysis are independent predictors for malignant IPMNs. • The addition of MR texture analysis improved the diagnostic performance for predicting malignant IPMNs from 0.80 and 0.78 to 0.85 and 0.85, respectively.

Multimodality Imaging and Artificial Intelligence for Tumor Characterization: Current Status and Future Perspective

Research in medical imaging has yet to do to achieve precision oncology. Over the past 30 years, only the simplest imaging biomarkers (RECIST, SUV,…) have become widespread clinical tools. This may be due to our inability to accurately characterize tumors and monitor intratumoral changes in imaging. Artificial intelligence, through machine learning and deep learning, opens a new path in medical research because it can bring together a large amount of heterogeneous data into the same analysis to reach a single outcome. Supervised or unsupervised learning may lead to new paradigms by identifying unrevealed structural patterns across data. Deep learning will provide human-free, undefined upstream, reproducible, and automated quantitative imaging biomarkers. Since tumor phenotype is driven by its genotype and thus indirectly defines tumoral progression, tumor characterization using machine learning and deep learning algorithms will allow us to monitor molecular expression noninvasively, anticipate therapeutic failure, and lead therapeutic management. To follow this path, quality standards have to be set: standardization of imaging acquisition as it has been done in the field of biology, transparency of the model development as it should be reproducible by different institutions, validation, and testing through a high-quality process using large and complex open databases and better interpretability of these algorithms.

CT-Based Radiomics Analysis to Predict Malignancy in Patients with Intraductal Papillary Mucinous Neoplasm (IPMN) of the Pancreas

To assess the performance of CT-based radiomics analysis in differentiating benign from malignant intraductal papillary mucinous neoplasms of the pancreas (IPMN), preoperative scans of 408 resected patients with IPMN were retrospectively analyzed. IPMNs were classified as benign (low-grade dysplasia, n = 181), or malignant (high grade, n = 128, and invasive, n = 99). Clinicobiological data were reported. Patients were divided into a training cohort (TC) of 296 patients and an external validation cohort (EVC) of 112 patients. After semi-automatic tumor segmentation, PyRadiomics was used to extract radiomics features. A multivariate model was developed using a logistic regression approach. In the training cohort, 85/107 radiomics features were significantly different between patients with benign and malignant IPMNs. Unsupervised clustering analysis revealed four distinct clusters of patients with similar radiomics features patterns with malignancy as the most significant association. The multivariate model differentiated benign from malignant tumors in TC with an area under the ROC curve (AUC) of 0.84, sensitivity (Se) of 0.82, specificity (Spe) of 0.74, and in EVC with an AUC of 0.71, Se of 0.69, Spe of 0.57. This large study confirms the high diagnostic performance of preoperative CT-based radiomics analysis to differentiate between benign from malignant IPMNs.

CT and MRI of pancreatic tumors: an update in the era of radiomics

Radiomics is a relatively new approach for image analysis. As a part of radiomics, texture analysis, which consists in extracting a great amount of quantitative data from original images, can be used to identify specific features that can help determining the actual nature of a pancreatic lesion and providing other information such as resectability, tumor grade, tumor response to neoadjuvant therapy or survival after surgery. In this review, the basic of radiomics, recent developments and the results of texture analysis using computed tomography and magnetic resonance imaging in the field of pancreatic tumors are presented. Future applications of radiomics, such as artificial intelligence, are discussed.

Pancreatic Cancer Imaging: A New Look at an Old Problem

Computed tomography is the most commonly used imaging modality to detect and stage pancreatic cancer. Previous advances in pancreatic cancer imaging have focused on optimizing image acquisition parameters and reporting standards. However, current state-of-the-art imaging approaches still misdiagnose some potentially curable pancreatic cancers and do not provide prognostic information or inform optimal management strategies beyond stage. Several recent developments in pancreatic cancer imaging, including artificial intelligence and advanced visualization techniques, are rapidly changing the field. The purpose of this article is to review how these recent advances have the potential to revolutionize pancreatic cancer imaging.

Radiomics for the Diagnosis and Differentiation of Pancreatic Cystic Lesions

Radiomics, also known as quantitative imaging or texture analysis, involves extracting a large number of features traditionally unmeasured in conventional radiological cross-sectional images and converting them into mathematical models. This review describes this approach and its use in the evaluation of pancreatic cystic lesions (PCLs). This discipline has the potential of more accurately assessing, classifying, risk stratifying, and guiding the management of PCLs. Existing studies have provided important insight into the role of radiomics in managing PCLs. Although these studies are limited by the use of retrospective design, single center data, and small sample sizes, radiomic features in combination with clinical data appear to be superior to the current standard of care in differentiating cyst type and in identifying mucinous PCLs with high-grade dysplasia. Combining radiomic features with other novel endoscopic diagnostics, including cyst fluid molecular analysis and confocal endomicroscopy, can potentially optimize the predictive accuracy of these models. There is a need for multicenter prospective studies to elucidate the role of radiomics in the management of PCLs.

Feasibility of computed tomography texture analysis of hepatic fibrosis using dual-energy spectral detector computed tomography

PURPOSE

To evaluate feasibility of computer tomography texture analysis (CTTA) at different energy level using dual-energy spectral detector CT for liver fibrosis.

MATERIALS AND METHODS

Eighty-seven patients who underwent a spectral CT examination and had a reference standard of liver fibrosis (histopathologic findings, n = 61, or clinical findings for normal, n = 26) were included. Mean gray-level intensity, mean number of positive pixels (MPP), entropy, skewness, and kurtosis using commercially available software (TexRAD) were compared at different energy levels. Optimal CTTA parameter cutoffs to diagnose liver fibrosis were evaluated. CTTA parameters at different energy levels correlated with liver fibrosis. The association of CTTA parameters with energy level was evaluated.

RESULTS

Mean gray-level intensity, skewness, kurtosis, and entropy showed significant differences between patients with and without clinically significant hepatic fibrosis (P < 0.05). Mean gray-level intensity at 50 keV was significantly positively correlated with liver fibrosis (ρ = 0.502, P < 0.001). To diagnose stages F2-F4, entropy and mean gray-level intensity at low keV level showed the largest area under the curve (AUC; 0.79 and 0.79). Estimated marginal means (EMMs) of mean gray-level intensity showed prominent differences at low energy levels.

CONCLUSION

CTTA parameters from different keV levels demonstrated meaningful accuracy for diagnosis of liver fibrosis or clinically significant hepatic fibrosis.