Differentiation of atypical non-functional pancreatic neuroendocrine tumor and pancreatic ductal adenocarcinoma using CT based radiomics

Differentiating small (< 2 cm) pancreatic ductal adenocarcinoma from neuroendocrine tumors with multiparametric MRI-based radiomic features

OBJECTIVES

To assess MR-based radiomic analysis in preoperatively discriminating small (< 2 cm) pancreatic ductal adenocarcinomas (PDACs) from neuroendocrine tumors (PNETs).

METHODS

A total of 197 patients (146 in the training cohort, 51 in the validation cohort) from two centers were retrospectively collected. A total of 7338 radiomics features were extracted from T2-weighted, diffusion-weighted, T1-weighted, arterial phase, portal venous phase and delayed phase imaging. The optimal features were selected by the Mann-Whitney U test, Spearman's rank correlation test and least absolute shrinkage and selection operator method and used to construct the radiomic score (Rad-score). Conventional radiological and clinical features were also assessed. Multivariable logistic regression was used to construct a radiological model, a radiomic model and a fusion model.

RESULTS

Nine optimal features were identified and used to build the Rad-score. The radiomic model based on the Rad-score achieved satisfactory results with AUCs of 0.905 and 0.930, sensitivities of 0.780 and 0.800, specificities of 0.906 and 0.952 and accuracies of 0.836 and 0.863 for the training and validation cohorts, respectively. The fusion model, incorporating CA19-9, tumor margins, pancreatic duct dilatation and the Rad-score, exhibited the best performance with AUCs of 0.977 and 0.941, sensitivities of 0.914 and 0.852, specificities of 0.954 and 0.950, and accuracies of 0.932 and 0.894 for the training and validation cohorts, respectively.

CONCLUSIONS

The MR-based Rad-score is a novel image biomarker for discriminating small PDACs from PNETs. A fusion model combining radiomic, radiological and clinical features performed very well in differentially diagnosing these two tumors.

CLINICAL RELEVANCE STATEMENT

A fusion model combining MR-based radiomic, radiological, and clinical features could help differentiate between small pancreatic ductal adenocarcinomas and pancreatic neuroendocrine tumors.

KEY POINTS

Preoperatively differentiating small pancreatic ductal adenocarcinomas (PDACs) and pancreatic neuroendocrine tumors (PNETs) is challenging. Multiparametric MRI-based Rad-score can be used for discriminating small PDACs from PNETs. A fusion model incorporating radiomic, radiological, and clinical features differentiated small PDACs from PNETs well.

A clinical-radiomics nomogram based on dual-layer spectral detector CT to predict cancer stage in pancreatic ductal adenocarcinoma

BACKGROUND

This study aimed to evaluate the efficacy of radiomics signatures derived from polyenergetic images (PEIs) and virtual monoenergetic images (VMIs) obtained through dual-layer spectral detector CT (DLCT). Moreover, it sought to develop a clinical-radiomics nomogram based on DLCT for predicting cancer stage (early stage: stage I-II, advanced stage: stage III-IV) in pancreatic ductal adenocarcinoma (PDAC).

METHODS

A total of 173 patients histopathologically diagnosed with PDAC and who underwent contrast-enhanced DLCT were enrolled in this study. Among them, 49 were in the early stage, and 124 were in the advanced stage. Patients were randomly categorized into training (n = 122) and test (n = 51) cohorts at a 7:3 ratio. Radiomics features were extracted from PEIs and 40-keV VMIs were reconstructed at both arterial and portal venous phases. Radiomics signatures were constructed based on both PEIs and 40-keV VMIs. A radiomics nomogram was developed by integrating the 40-keV VMI-based radiomics signature with selected clinical predictors. The performance of the nomogram was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curves analysis (DCA).

RESULTS

The PEI-based radiomics signature demonstrated satisfactory diagnostic efficacy, with the areas under the ROC curves (AUCs) of 0.92 in both the training and test cohorts. The optimal radiomics signature was based on 40-keV VMIs, with AUCs of 0.96 and 0.94 in the training and test cohorts. The nomogram, which integrated a 40-keV VMI-based radiomics signature with two clinical parameters (tumour diameter and normalized iodine density at the portal venous phase), demonstrated promising calibration and discrimination in both the training and test cohorts (0.97 and 0.91, respectively). DCA indicated that the clinical-radiomics nomogram provided the most significant clinical benefit.

CONCLUSIONS

The radiomics signature derived from 40-keV VMI and the clinical-radiomics nomogram based on DLCT both exhibited exceptional performance in distinguishing early from advanced stages in PDAC, aiding clinical decision-making for patients with this condition.

Prognostic value of CT-based radiomics in grade 1-2 pancreatic neuroendocrine tumors

BACKGROUND

Surgically resected grade 1-2 (G1-2) pancreatic neuroendocrine tumors (PanNETs) exhibit diverse clinical outcomes, highlighting the need for reliable prognostic biomarkers. Our study aimed to develop and validate CT-based radiomics model for predicting postsurgical outcome in patients with G1-2 PanNETs, and to compare its performance with the current clinical staging system.

METHODS

This multicenter retrospective study included patients who underwent dynamic CT and subsequent curative resection for G1-2 PanNETs. A radiomics-based model (R-score) for predicting recurrence-free survival (RFS) was developed from a development set (441 patients from one institution) using least absolute shrinkage and selection operator-Cox regression analysis. A clinical model (C-model) consisting of age and tumor stage according to the 8th American Joint Committee on Cancer staging system was built, and an integrative model combining the C-model and the R-score (CR-model) was developed using multivariable Cox regression analysis. Using an external test set (159 patients from another institution), the models' performance for predicting RFS and overall survival (OS) was evaluated using Harrell's C-index. The incremental value of adding the R-score to the C-model was evaluated using net reclassification improvement (NRI) and integrated discrimination improvement (IDI).

RESULTS

The median follow-up periods were 68.3 and 59.7 months in the development and test sets, respectively. In the development set, 58 patients (13.2%) experienced recurrence and 35 (7.9%) died. In the test set, tumors recurred in 14 patients (8.8%) and 12 (7.5%) died. In the test set, the R-score had a C-index of 0.716 for RFS and 0.674 for OS. Compared with the C-model, the CR-model showed higher C-index (RFS, 0.734 vs. 0.662, p = 0.012; OS, 0.781 vs. 0.675, p = 0.043). CR-model also showed improved classification (NRI, 0.330, p < 0.001) and discrimination (IDI, 0.071, p < 0.001) for prediction of 3-year RFS.

CONCLUSIONS

Our CR-model outperformed the current clinical staging system in prediction of the prognosis for G1-2 PanNETs and added incremental value for predicting postoperative recurrence. The CR-model enables precise identification of high-risk patients, guiding personalized treatment planning to improve outcomes in surgically resected grade 1-2 PanNETs.

Dual-energy CT improves differentiation of non-hypervascular pancreatic neuroendocrine neoplasms from CA 19-9-negative pancreatic ductal adenocarcinomas

PURPOSE

To evaluate the utility of dual-energy CT (DECT) in differentiating non-hypervascular pancreatic neuroendocrine neoplasms (PNENs) from pancreatic ductal adenocarcinomas (PDACs) with negative carbohydrate antigen 19-9 (CA 19-9).

METHODS

This retrospective study included 26 and 39 patients with pathologically confirmed non-hypervascular PNENs and CA 19-9-negative PDACs, respectively, who underwent contrast-enhanced DECT before treatment between June 2019 and December 2021. The clinical, conventional CT qualitative, conventional CT quantitative, and DECT quantitative parameters of the two groups were compared using univariate analysis and selected by least absolute shrinkage and selection operator regression (LASSO) analysis. Multivariate logistic regression analyses were performed to build qualitative, conventional CT quantitative, DECT quantitative, and comprehensive models. The areas under the receiver operating characteristic curve (AUCs) of the models were compared using DeLong's test.

RESULTS

The AUCs of the DECT quantitative (based on normalized iodine concentrations [nICs] in the arterial and portal venous phases: 0.918; 95% confidence interval [CI] 0.852-0.985) and comprehensive (based on tumour location and nICs in the arterial and portal venous phases: 0.966; 95% CI 0.889-0.995) models were higher than those of the qualitative (based on tumour location: 0.782; 95% CI 0.665-0.899) and conventional CT quantitative (based on normalized conventional CT attenuation in the arterial phase: 0.665; 95% CI 0.533-0.797; all P < 0.05) models. The DECT quantitative and comprehensive models had comparable performances (P = 0.076).

CONCLUSIONS

Higher nICs in the arterial and portal venous phases were associated with higher blood supply improving the identification of non-hypervascular PNENs.

Prognostic Assessment of Gastropancreatic Neuroendocrine Neoplasm: Prospects and Limits of Radiomics

Neuroendocrine neoplasms (NENs) are a group of lesions originating from cells of the diffuse neuroendocrine system. NENs may involve different sites, including the gastrointestinal tract (GEP-NENs). The incidence and prevalence of GEP-NENs has been constantly rising thanks to the increased diagnostic power of imaging and immuno-histochemistry. Despite the plethora of biochemical markers and imaging techniques, the prognosis and therapeutic choice in GEP-NENs still represents a challenge, mainly due to the great heterogeneity in terms of tumor lesions and clinical behavior. The concept that biomedical images contain information about tissue heterogeneity and pathological processes invisible to the human eye is now well established. From this substrate comes the idea of radiomics. Computational analysis has achieved promising results in several oncological settings, and the use of radiomics in different types of GEP-NENs is growing in the field of research, yet with conflicting results. The aim of this narrative review is to provide a comprehensive update on the role of radiomics on GEP-NEN management, focusing on the main clinical aspects analyzed by most existing reports: predicting tumor grade, distinguishing NET from other tumors, and prognosis assessment.

A primer on artificial intelligence in pancreatic imaging

Artificial Intelligence (AI) is set to transform medical imaging by leveraging the vast data contained in medical images. Deep learning and radiomics are the two main AI methods currently being applied within radiology. Deep learning uses a layered set of self-correcting algorithms to develop a mathematical model that best fits the data. Radiomics converts imaging data into mineable features such as signal intensity, shape, texture, and higher-order features. Both methods have the potential to improve disease detection, characterization, and prognostication. This article reviews the current status of artificial intelligence in pancreatic imaging and critically appraises the quality of existing evidence using the radiomics quality score.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Nuclear Medicine and Radiological Imaging of Pancreatic Neuroendocrine Neoplasms: A Multidisciplinary Update

Pancreatic neuroendocrine neoplasms (panNENs) are part of a large family of tumors arising from the neuroendocrine system. PanNENs show low-intermediate tumor grade and generally high somatostatin receptor (SSTR) expression. Therefore, panNENs benefit from functional imaging with ⁶⁸Ga-somatostatin analogues (SSA) for diagnosis, staging, and treatment choice in parallel with morphological imaging. This narrative review aims to present conventional imaging techniques and new perspectives in the management of panNENs, providing the clinicians with useful insight for clinical practice. The ⁶⁸Ga-SSA PET/CT is the most widely used in panNENs, not only fr diagnosis and staging purpose but also to characterize the biology of the tumor and its responsiveness to SSAs. On the contrary, the ¹⁸F-Fluordeoxiglucose (FDG) PET/CT is not employed systematically in all panNEN patients, being generally preferred in G2-G3, to predict aggressiveness and progression rate. The combination of ⁶⁸Ga-SSA PET/CT and ¹⁸F-FDG PET/CT can finally suggest the best therapeutic strategy. Other radiopharmaceuticals are ⁶⁸Ga-exendin-4 in case of insulinomas and ¹⁸F-dopamine (DOPA), which can be helpful in SSTR-negative tumors. New promising but still-under-investigation radiopharmaceuticals include radiolabeled SSTR antagonists and ¹⁸F-SSAs. Conventional imaging includes contrast enhanced CT and multiparametric MRI. There are now enriched by radiomics, a new non-invasive imaging approach, very promising to early predict tumor response or progression.

Radiomics Combined with Multiple Machine Learning Algorithms in Differentiating Pancreatic Ductal Adenocarcinoma from Pancreatic Neuroendocrine Tumor: More Hands Produce a Stronger Flame

The aim of this study was to assess the diagnostic ability of radiomics combined with multiple machine learning algorithms to differentiate pancreatic ductal adenocarcinoma (PDAC) from pancreatic neuroendocrine tumor (pNET). This retrospective study included a total of 238 patients diagnosed with PDAC or pNET. Using specialized software, radiologists manually mapped regions of interest (ROIs) from computed tomography images and automatically extracted radiomics features. A total of 45 discriminative models were built by five selection algorithms and nine classification algorithms. The performances of the discriminative models were assessed by sensitivity, specificity and the area under receiver operating characteristic curve (AUC) in the training and validation datasets. Using the combination of Gradient Boosting Decision Tree (GBDT) as the selection algorithm and Random Forest (RF) as the classification algorithm, the optimal diagnostic ability with the highest AUC was presented in the training and validation datasets. The sensitivity, specificity and AUC of the model were 0.804, 0.973 and 0.971 in the training dataset and 0.742, 0.934 and 0.930 in the validation dataset, respectively. The combination of radiomics and multiple machine learning algorithms showed the potential ability to discriminate PDAC from pNET. We suggest that multi-algorithm modeling should be considered for similar studies in the future rather than using a single algorithm empirically.

New frontiers in imaging including radiomics updates for pancreatic neuroendocrine neoplasms

OBJECTIVE

To illustrate the applications of various imaging tools including conventional MDCT, MRI including DWI, CT & MRI radiomics, FDG & DOTATATE PET-CT for diagnosis, staging, grading, prognostication, treatment planning and assessing treatment response in cases of pancreatic neuroendocrine neoplasms (PNENs).

BACKGROUND

Gastroenteropancreatic neuroendocrine neoplasms (GEP NENs) are very diverse clinically & biologically. Their treatment and prognosis depend on staging and primary site, as well as histological grading, the importance of which is also reflected in the recently updated WHO classification of GEP NENs. Grade 3 poorly differentiated neuroendocrine carcinomas (NECs) are aggressive & nearly always advanced at diagnosis with poor prognosis; whereas Grades-1 and 2 well-differentiated neuroendocrine tumors (NETs) can be quite indolent. Grade 3 well-differentiated NETs represent a new category of neoplasm with an intermediate prognosis. Importantly, the evidence suggest grade heterogeneity can occur within a given tumor and even grade progression can occur over time. Emerging evidence suggests that several non-invasive qualitative and quantitative imaging features on CT, dual-energy CT (DECT), MRI, PET and somatostatin receptor imaging with new tracers, as well as texture analysis, may be useful to grade, prognosticate, and accurately stage primary NENs. Imaging features may also help to inform choice of treatment and follow these neoplasms post-treatment.

CONCLUSION

GEP NENs treatment and prognosis depend on the stage as well as histological grade of the tumor. Traditional ways of imaging evaluation for diagnosis and staging does not yet yield sufficient information to replace operative and histological evaluation. Recognition of important qualitative imaging features together with quantitative features and advanced imaging tools including functional imaging with DWI MRI, DOTATATE PET/CT, texture analysis with radiomics and radiogenomic features appear promising for more accurate staging, tumor risk stratification, guiding management and assessing treatment response.

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.

GEP-NET radiomics: a systematic review and radiomics quality score assessment

OBJECTIVE

The number of radiomics studies in gastroenteropancreatic neuroendocrine tumours (GEP-NETs) is rapidly increasing. This systematic review aims to provide an overview of the available evidence of radiomics for clinical outcome measures in GEP-NETs, to understand which applications hold the most promise and which areas lack evidence.

METHODS

PubMed, Embase, and Wiley/Cochrane Library databases were searched and a forward and backward reference check of the identified studies was executed. Inclusion criteria were (1) patients with GEP-NETs and (2) radiomics analysis on CT, MRI or PET. Two reviewers independently agreed on eligibility and assessed methodological quality with the radiomics quality score (RQS) and extracted outcome data.

RESULTS

In total, 1364 unique studies were identified and 45 were included for analysis. Most studies focused on GEP-NET grade and differential diagnosis of GEP-NETs from other neoplasms, while only a minority analysed treatment response or long-term outcomes. Several studies were able to predict tumour grade or to differentiate GEP-NETs from other lesions with a good performance (AUCs 0.74-0.96 and AUCs 0.80-0.99, respectively). Only one study developed a model to predict recurrence in pancreas NETs (AUC 0.77). The included studies reached a mean RQS of 18%.

CONCLUSION

Although radiomics for GEP-NETs is still a relatively new area, some promising models have been developed. Future research should focus on developing robust models for clinically relevant aims such as prediction of response or long-term outcome in GEP-NET, since evidence for these aims is still scarce.

KEY POINTS

• The majority of radiomics studies in gastroenteropancreatic neuroendocrine tumours is of low quality. • Most evidence for radiomics is available for the identification of tumour grade or differentiation of gastroenteropancreatic neuroendocrine tumours from other neoplasms. • Radiomics for the prediction of response or long-term outcome in gastroenteropancreatic neuroendocrine tumours warrants further research.

Setting the Research Agenda for Clinical Artificial Intelligence in Pancreatic Adenocarcinoma Imaging

Simple Summary

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest cancers worldwide, associated with a 98% loss of life expectancy and a 30% increase in disability-adjusted life years. Image-based artificial intelligence (AI) can help improve outcomes for PDAC given that current clinical guidelines are non-uniform and lack evidence-based consensus. However, research on image-based AI for PDAC is too scattered and lacking in sufficient quality to be incorporated into clinical workflows. In this review, an international, multi-disciplinary team of the world’s leading experts in pancreatic cancer breaks down the patient pathway and pinpoints the current clinical touchpoints in each stage. The available PDAC imaging AI literature addressing each pathway stage is then rigorously analyzed, and current performance and pitfalls are identified in a comprehensive overview. Finally, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.

Abstract

Pancreatic ductal adenocarcinoma (PDAC), estimated to become the second leading cause of cancer deaths in western societies by 2030, was flagged as a neglected cancer by the European Commission and the United States Congress. Due to lack of investment in research and development, combined with a complex and aggressive tumour biology, PDAC overall survival has not significantly improved the past decades. Cross-sectional imaging and histopathology play a crucial role throughout the patient pathway. However, current clinical guidelines for diagnostic workup, patient stratification, treatment response assessment, and follow-up are non-uniform and lack evidence-based consensus. Artificial Intelligence (AI) can leverage multimodal data to improve patient outcomes, but PDAC AI research is too scattered and lacking in quality to be incorporated into clinical workflows. This review describes the patient pathway and derives touchpoints for image-based AI research in collaboration with a multi-disciplinary, multi-institutional expert panel. The literature exploring AI to address these touchpoints is thoroughly retrieved and analysed to identify the existing trends and knowledge gaps. The results show absence of multi-institutional, well-curated datasets, an essential building block for robust AI applications. Furthermore, most research is unimodal, does not use state-of-the-art AI techniques, and lacks reliable ground truth. Based on this, the future research agenda for clinically relevant, image-driven AI in PDAC is proposed.

CT-based radiomics for prediction of therapeutic response to Everolimus in metastatic neuroendocrine tumors

Aim

To test radiomic approach in patients with metastatic neuroendocrine tumors (NETs) treated with Everolimus, with the aim to predict progression-free survival (PFS) and death.

Materials and methods

Twenty-five patients with metastatic neuroendocrine tumors, 15/25 pancreatic (60%), 9/25 ileal (36%), 1/25 lung (4%), were retrospectively enrolled between August 2013 and December 2020. All patients underwent contrast-enhanced CT before starting Everolimus, histological diagnosis, tumor grading, PFS, overall survival (OS), death, and clinical data collected. Population was divided into two groups: responders (PFS ≤ 11 months) and non-responders (PFS > 11 months). 3D segmentation was performed on whole liver of naïve CT scans in arterial and venous phases, using a dedicated software (3DSlicer v4.10.2). A total of 107 radiomic features were extracted and compared between two groups (T test or Mann–Whitney), radiomics performance assessed with receiver operating characteristic curve, Kaplan–Meyer curves used for survival analysis, univariate and multivariate logistic regression performed to predict death, and interobserver variability assessed. All significant radiomic comparisons were validated by using a synthetic external cohort. P < 0.05 is considered significant.

Results

15/25 patients were classified as responders (median PFS 25 months and OS 29 months) and 10/25 as non-responders (median PFS 4.5 months and OS 23 months). Among radiomic parameters, Correlation and Imc1 showed significant differences between two groups (P < 0.05) with the best performance (internal cohort AUC 0.86–0.84, P < 0.0001; external cohort AUC 0.84–0.90; P < 0.0001). Correlation < 0.21 resulted correlated with death at Kaplan–Meyer analysis (P = 0.02). Univariate analysis showed three radiomic features independently correlated with death, and in multivariate analysis radiomic model showed good performance with AUC 0.87, sensitivity 100%, and specificity 66.7%. Three features achieved 0.77 ≤ ICC < 0.83 and one ICC = 0.92.

Conclusions

In patients affected by metastatic NETs eligible for Everolimus treatment, radiomics could be used as imaging biomarker able to predict PFS and death.

A deep learning algorithm to improve readers' interpretation and speed of pancreatic cystic lesions on dual-phase enhanced CT

PURPOSE

To develop a deep learning model (DLM) to improve readers' interpretation and speed in the differentiation of pancreatic cystic lesions (PCLs) on dual-phase enhanced CT, and a low contrast media dose, external testing set validated the model.

MATERIALS AND METHODS

Dual-phase enhanced CT images of 363 patients with 368 PCLs obtained from two centers were retrospectively assessed. Based on the examination date, a training and validation set of 266 PCLs, an internal testing set of 52 PCLs were designated from center 1. An external testing set included 50 PCLs from center 2. Clinical and radiological characteristics were compared. The DLM was developed using 3D specially designed densely connected convolutional networks for PCL differentiation. Radiomic features were extracted to build a traditional radiomics model (RM). Performance of the DLM, traditional RM, and three readers was compared.

RESULTS

The accuracy for differential diagnosis was 0.904 with DLM, which was the highest in the internal testing set. Accuracy differences between the DLM and senior radiologist were not significant both in the internal and external testing set (both p > 0.05). With the help of the DLM, the accuracy and specificity of the junior radiologist were significantly improved (all p < 0.05), and all readers' diagnostic time was shortened (all p < 0.05).

CONCLUSION

The DLM achieved senior radiologist-level performance in differentiating benign and malignant PCLs which could improve the junior radiologist's interpretation and speed of PCLs on CT.

MRI Feature-Based Nomogram Model for Discrimination Between Non-Hypervascular Pancreatic Neuroendocrine Tumors and Pancreatic Ductal Adenocarcinomas

This study aimed to investigate whether magnetic resonance imaging (MRI) features could differentiate non-hypervascular pancreatic neuroendocrine tumors (PNETs) from pancreatic ductal adenocarcinomas (PDACs). In this study, 131 patients with surgically and pathologically proven non-hypervascular PNETs (n = 44) or PDACs (n = 87) were enrolled. Two radiologists independently analyzed MRI imaging findings and clinical features. Relevant features in differentiating non-hypervascular PNETs from PDACs were identified via univariate and multivariate logistic regression models. The MRI feature-based nomogram was constructed based on multivariable logistic analysis and the reliability of the constructed nomogram was further validated. The results showed that tumor margin (P = 0.012; OR: 6.622; 95% CI: 1.510, 29.028), MPD dilation (P = 0.047; OR: 4.309; 95% CI: 1.019, 18.227), and signal in the portal phase (P &lt; 0.001; OR: 53.486; 95% CI: 10.690, 267.618) were independent discriminative MRI features between non-hypervascular PNETs and PDACs. The discriminative performance of the developed nomogram was optimized compared with single imaging features. The calibration curve, C-index, and DCA validated the superior practicality and usefulness of the MRI-based nomogram. In conclusion, the radiologically discriminative model integrating various MRI features could be preoperatively and easily utilized to differentiate non-hypervascular PNETs from PDACs.

The impact of radiomics in diagnosis and staging of pancreatic cancer

INTRODUCTION

Pancreatic cancer (PC) is one of the most aggressive tumours, and better risk stratification among patients is required to provide tailored treatment. The meaning of radiomics and texture analysis as predictive techniques are not already systematically assessed. The aim of this study is to assess the role of radiomics in PC.

METHODS

A PubMed/MEDLINE and Embase systematic review was conducted to assess the role of radiomics in PC. The search strategy was 'radiomics [All Fields] AND ("pancreas" [MeSH Terms] OR "pancreas" [All Fields] OR "pancreatic" [All Fields])' and only original articles referred to PC in humans in the English language were considered.

RESULTS

A total of 123 studies and 183 studies were obtained using the mentioned search strategy on PubMed and Embase, respectively. After the complete selection process, a total of 56 papers were considered eligible for the analysis of the results. Radiomics methods were applied in PC for assessment technical feasibility and reproducibility aspects analysis, risk stratification, biologic or genomic status prediction and treatment response prediction.

DISCUSSION

Radiomics seems to be a promising approach to evaluate PC from diagnosis to treatment response prediction. Further and larger studies are required to confirm the role and allowed to include radiomics parameter in a comprehensive decision support system.

Non-gaussian models of 3-Tesla diffusion-weighted MRI for the differentiation of pancreatic ductal adenocarcinomas from neuroendocrine tumors and solid pseudopapillary neoplasms

PURPOSE

To assess the MRI performance in differentiating pancreatic ductal adenocarcinomas (PDACs), from solid pseudopapillary neoplasms (SPNs) and pancreatic neuroendocrine tumors (PNETs) using non-gaussian diffusion-weighted imaging models.

METHODS

This was a retrospective study of patients diagnosed with PDACs (01/2015-06/2019) or with PNETs or SPNs diagnosed (01/2011-12/2019) at our hospital. The lesions were randomized 1:1 to the primary and validation cohorts. The regions of interest (ROIs) were manually drawn on each slice at DWI (b = 1500 s/mm²) from 3 T MRI. D (diffusion coefficient), D* (pseudodiffusion coefficient), f (perfusion fraction), distributed diffusion coefficient (DDC), α (diffusion heterogeneity index), mean diffusivity (MD) and mean kurtosis (MK) were obtained. The parameters with largest performance for differentiation were used to establish a diagnostic model.

RESULTS

There were 148, 56, and 60 patients with PDAC, PNET, and SPN, respectively. For differentiating PDACs from SPNs, f and MK values were used to establish a diagnostic model with areas under the receiver operating characteristic curves (AUCs) of 0.92 and 0.89 in the primary and validation groups, respectively. For distinguishing PDACs from PNETs, α and MK values were used to establish a diagnostic model with AUCs of 0.87 and 0.86 in the primary and validation groups, respectively. The accuracy rate of the subjective evaluation with the assistance of non-gaussian DWI models for differentiating PDAC from SPNs and PNETs were higher than that of subjective diagnosis alone (P < 0.05).

CONCLUSIONS

The non-gaussian DWI models could assist radiologists in accurately differentiating PDACs from PNETs and SPNs.

Application of CT-Based Radiomics in Discriminating Pancreatic Cystadenomas From Pancreatic Neuroendocrine Tumors Using Machine Learning Methods

Objectives

The purpose of this study aimed at investigating the reliability of radiomics features extracted from contrast-enhanced CT in differentiating pancreatic cystadenomas from pancreatic neuroendocrine tumors (PNETs) using machine-learning methods.

Methods

In this study, a total number of 120 patients, including 66 pancreatic cystadenomas patients and 54 PNETs patients were enrolled. Forty-eight radiomic features were extracted from contrast-enhanced CT images using LIFEx software. Five feature selection methods were adopted to determine the appropriate features for classifiers. Then, nine machine learning classifiers were employed to build predictive models. The performance of the forty-five models was evaluated with area under the curve (AUC), accuracy, sensitivity, specificity, and F1 score in the testing group.

Results

The predictive models exhibited reliable ability of differentiating pancreatic cystadenomas from PNETs when combined with suitable selection methods. A combination of DC as the selection method and RF as the classifier, as well as Xgboost+RF, demonstrated the best discriminative ability, with the highest AUC of 0.997 in the testing group.

Conclusions

Radiomics-based machine learning methods might be a noninvasive tool to assist in differentiating pancreatic cystadenomas and PNETs.

Radiomics in Oncology, Part 1: Technical Principles and Gastrointestinal Application in CT and MRI

Simple Summary

Part I is an overview aimed to investigate some technical principles and the main fields of radiomic application in gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy in gastrointestinal cancers, describing mostly the results for each pre-eminent tumor. In particular, this paper provides a general description of the main radiomic drawbacks and future challenges, which limit radiomic application in clinical setting as routine. Further investigations need to standardize and validate the Radiomics as a helpful tool in management of oncologic patients. In that context, Radiomics has been playing a relevant role and could be considered as a future imaging landscape.

Abstract

Radiomics has been playing a pivotal role in oncological translational imaging, particularly in cancer diagnosis, prediction prognosis, and therapy response assessment. Recently, promising results were achieved in management of cancer patients by extracting mineable high-dimensional data from medical images, supporting clinicians in decision-making process in the new era of target therapy and personalized medicine. Radiomics could provide quantitative data, extracted from medical images, that could reflect microenvironmental tumor heterogeneity, which might be a useful information for treatment tailoring. Thus, it could be helpful to overcome the main limitations of traditional tumor biopsy, often affected by bias in tumor sampling, lack of repeatability and possible procedure complications. This quantitative approach has been widely investigated as a non-invasive and an objective imaging biomarker in cancer patients; however, it is not applied as a clinical routine due to several limitations related to lack of standardization and validation of images acquisition protocols, features segmentation, extraction, processing, and data analysis. This field is in continuous evolution in each type of cancer, and results support the idea that in the future Radiomics might be a reliable application in oncologic imaging. The first part of this review aimed to describe some radiomic technical principles and clinical applications to gastrointestinal oncologic imaging (CT and MRI) with a focus on diagnosis, prediction prognosis, and assessment of response to therapy.

Radiomics in pancreatic neuroendocrine tumors: methodological issues and clinical significance

PURPOSE

To present the state-of-art of radiomics in the context of pancreatic neuroendocrine tumors (PanNETs), with a focus on the methodological and technical approaches used, to support the search of guidelines for optimal applications. Furthermore, an up-to-date overview of the current clinical applications of radiomics in the field of PanNETs is provided.

METHODS

Original articles were searched on PubMed and Science Direct with specific keywords. Evaluations of the selected studies have been focused mainly on (i) the general radiomic workflow and the assessment of radiomic features robustness/reproducibility, as well as on the major clinical applications and investigations accomplished so far with radiomics in the field of PanNETs: (ii) grade prediction, (iii) differential diagnosis from other neoplasms, (iv) assessment of tumor behavior and aggressiveness, and (v) treatment response prediction.

RESULTS

Thirty-one articles involving PanNETs radiomic-related objectives were selected. In regard to the grade differentiation task, yielded AUCs are currently in the range of 0.7-0.9. For differential diagnosis, the majority of studies are still focused on the preliminary identification of discriminative radiomic features. Limited information is known on the prediction of tumors aggressiveness and of treatment response.

CONCLUSIONS

Radiomics is recently expanding in the setting of PanNETs. From the analysis of the published data, it is emerging how, prior to clinical application, further validations are necessary and methodological implementations require optimization. Nevertheless, this new discipline might have the potential in assisting the current urgent need of improving the management strategies in PanNETs patients.

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.

A Preliminary Study for Distinguish Hormone-Secreting Functional Adrenocortical Adenoma Subtypes Using Multiparametric CT Radiomics-Based Machine Learning Model and Nomogram

Purpose: To explore the application value of multiparametric computed tomography (CT) radiomics in non-invasive differentiation between aldosterone-producing and cortisol-producing functional adrenocortical adenomas. Methods: This retrospective review analyzed 83 patients including 41 patients with aldosterone-producing adenoma and 42 patients with cortisol-producing adenoma. The quantitative radiomics features were extracted from the complete unenhanced, arterial, and venous phase CT images. A comparative study of several frequently used machine learning models (linear discriminant analysis, logistic regression, random forest, and support vector machine) combined with different feature selection methods was implemented in order to determine which was most advantageous for differential diagnosis using radiomics features. Then, the integrated model using the combination of radiomic signature and clinic-radiological features was built, and the associated calibration curve was also presented. The diagnostic performance of these models was estimated and compared using the area under the receiver operating characteristic (ROC) curve (AUC). Result: In the radiomics-based machine learning model, logistic regression model with LASSO (least absolute shrinkage and selection operator) outperformed the other models, which yielded a sensitivity of 0.935, a specificity of 0.823, and an accuracy of 0.887 [AUC = 0.882, 95% confidence interval (CI) = 0.819-0.945]. Moreover, the nomogram representing the integrated model achieved good discrimination performances, which yielded a sensitivity of 0.915, a specificity of 0.928, and an accuracy of 0.922 (AUC = 0.902, 95% CI = 0.822-0.982), and it was better than that of the radiomics model alone. Conclusion: This study found that the combination of multiparametric radiomics signature and clinic-radiological features can non-invasively differentiate the subtypes of hormone-secreting functional adrenocortical adenomas, which may have good potential for facilitating the diagnosis and treatment in clinical practice.

Radiomics Analysis Based on Diffusion Kurtosis Imaging and T2 Weighted Imaging for Differentiation of Pancreatic Neuroendocrine Tumors From Solid Pseudopapillary Tumors

Objective

To develop and validate a radiomics model of diffusion kurtosis imaging (DKI) and T2 weighted imaging for discriminating pancreatic neuroendocrine tumors (PNETs) from solid pseudopapillary tumors (SPTs).

Materials and Methods

Sixty-six patients with histopathological confirmed PNETs (n = 31) and SPTs (n = 35) were enrolled in this study. ROIs of tumors were manually drawn on each slice at T2WI and DWI (b = 1,500 s/mm²) from 3T MRI. Intraclass correlation coefficients were used to evaluate the interobserver agreement. Mean diffusivity (MD) and mean kurtosis (MK) were derived from DKI. The least absolute shrinkage and selection operator regression were used for feature selection.

Results

MD and MK had a moderate diagnostic performancewith the area under curve (AUC) of 0.71 and 0.65, respectively. A radiomics model, which incorporated sex and age of patients and radiomics signature of the tumor, showed excellent discrimination performance with AUC of 0.97 and 0.86 in the primary and validation cohort. Moreover, the new model had better diagnostic performance than that of MD (P = 0.023) and MK (P = 0.004), and showed excellent differentiation with a sensitivity of 95.00% and specificity of 91.67% in primary cohort, and the sensitivity of 90.91% and specificity of 81.82% in the validation cohort. The accuracy of radiomics analysis, radiologist 1, and radiologist 2 for diagnosing SPTs and PNETs were 92.42, 77.27, and 78.79%, respectively. The accuracy of radiomics analysis was significantly higher than that of subjective diagnosis (P < 0.05).

Conclusions

Radiomics model could improve the diagnostic accuracy of SPTs and PNETs and contribute to determining an appropriate treatment strategy for pancreatic tumors.