Pancreatic neuroendocrine tumor: prediction of the tumor grade using magnetic resonance imaging findings and texture analysis with 3-T magnetic resonance

A novel endoscopic ultrasomics-based machine learning model and nomogram to predict the pathological grading of pancreatic neuroendocrine tumors

Objectives

This research aimed to retrospectively construct and authenticate ultrasomics models using endoscopic ultrasonography (EUS) images for forecasting the pathological grading of pancreatic neuroendocrine tumors (PNETs).

Methods

After confirmation through pathological examination, a retrospective analysis of 79 patients was conducted, including 49 with grade 1 PNETs and 30 with grade 2/3 PNETs. These patients were randomized to the training or test cohort in a 6:4 proportion. The least absolute shrinkage and selection operator (LASSO) algorithm was used to reduce the dimensionality of ultrasomics features derived from standard EUS images. These nonzero coefficient features were retained and applied to construct prediction models via eight machine-learning algorithms. The optimum ulstrasomics model was determined, followed by creating and evaluating a nomogram.

Results

Ultrasomics features of 107 were extracted, and only those with coefficients greater than zero were retained. The XGboost ultrasomics model performed exceptionally well, achieving AUCs of 0.987 and 0.781 in the training and test cohorts, respectively. Furthermore, an effective nomogram was developed and visually represented. Finally, the calibration curves, decision curve analysis (DCA) plots, and clinical impact curve (CIC) displayed in the ulstrasomics model and nomogram demonstrated high accuracy. They provided significant net benefits for clinical decision-making.

Conclusions

A novel ulstrasomics model and nomogram were created and certified to predict the pathological grading of PNETs using EUS images. This study has the potential to provide valuable insights that improve the clinical applicability and efficacy of EUS in predicting the grading of PNETs.

Recent advances and future challenges in the diagnosis of neuroendocrine neoplasms

Neuroendocrine neoplasms (NEN) are a heterogeneous group of malignancies with increasing incidence, whose diagnosis is usually delayed, negatively impacting on patients' prognosis. The latest advances in pathological classifications, biomarker identification and imaging techniques may provide early detection, leading to personalized treatment strategies. In this narrative review the recent developments in diagnosis of NEN are discussed including progresses in pathological classifications, biomarker and imaging. Furthermore, the challenges that lie ahead are investigated. By discussing the limitations of current approaches and addressing potential roadblocks, we hope to guide future research directions in this field. This article is proposed as a valuable resource for clinicians and researchers involved in the management of NEN. Update of pathological classifications and the availability of standardized templates in pathology and radiology represent a substantially improvement in diagnosis and communication among clinicians. Additional immunohistochemistry markers may now enrich pathological classifications, as well as miRNA profiling. New and multi-analytical circulating biomarkers, as liquid biopsy and NETest, are being proposed for diagnosis but their validation and availability should be improved. Radiological imaging strives for precise, non-invasive and less harmful technique to improve safety and quality of life in NEN patient. Nuclear medicine may benefit of somatostatin receptors' antagonists and membrane receptor analogues. Diagnosis in NEN still represents a challenge due to their complex biology and variable presentation. Further advancements are necessary to obtain early and minimally invasive diagnosis to improve patients' outcomes.

Predicting histologic grades for pancreatic neuroendocrine tumors by radiologic image-based artificial intelligence: a systematic review and meta-analysis

Background

Accurate detection of the histological grade of pancreatic neuroendocrine tumors (PNETs) is important for patients' prognoses and treatment. Here, we investigated the performance of radiological image-based artificial intelligence (AI) models in predicting histological grades using meta-analysis.

Method

A systematic literature search was performed for studies published before September 2023. Study characteristics and diagnostic measures were extracted. Estimates were pooled using random-effects meta-analysis. Evaluation of risk of bias was performed by the QUADAS-2 tool.

Results

A total of 26 studies were included, 20 of which met the meta-analysis criteria. We found that the AI-based models had high area under the curve (AUC) values and showed moderate predictive value. The pooled distinguishing abilities between different grades of PNETs were 0.89 [0.84-0.90]. By performing subgroup analysis, we found that the radiomics feature-only models had a predictive value of 0.90 [0.87-0.92] with I2 = 89.91%, while the pooled AUC value of the combined group was 0.81 [0.77-0.84] with I2 = 41.54%. The validation group had a pooled AUC of 0.84 [0.81-0.87] without heterogenicity, whereas the validation-free group had high heterogenicity (I2 = 91.65%, P=0.000). The machine learning group had a pooled AUC of 0.83 [0.80-0.86] with I2 = 82.28%.

Conclusion

AI can be considered as a potential tool to detect histological PNETs grades. Sample diversity, lack of external validation, imaging modalities, inconsistent radiomics feature extraction across platforms, different modeling algorithms and software choices were sources of heterogeneity. Standardized imaging, transparent statistical methodologies for feature selection and model development are still needed in the future to achieve the transformation of radiomics results into clinical applications.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42022341852.

Recent developments in the diagnosis of pancreatic neuroendocrine neoplasms

INTRODUCTION

Pancreatic Neuroendocrine Neoplasms (PanNENs) are characterized by a highly heterogeneous clinical and biological behavior, making their diagnosis challenging. PanNENs diagnostic work-up mainly relies on biochemical markers, pathological examination, and imaging evaluation. The latter includes radiological imaging (i.e. computed tomography [CT] and magnetic resonance imaging [MRI]), functional imaging (i.e. 68Gallium [68 Ga]Ga-DOTA-peptide PET/CT and Fluorine-18 fluorodeoxyglucose [18F]FDG PET/CT), and endoscopic ultrasound (EUS) with its associated procedures.

AREAS COVERED

This review provides a comprehensive assessment of the recent advancements in the PanNENs diagnostic field. PubMed and Embase databases were used for the research, performed from inception to October 2023.

EXPERT OPINION

A deeper understanding of PanNENs biology, recent technological improvements in imaging modalities, as well as progresses achieved in molecular and cytological assays, are fundamental players for the achievement of early diagnosis and enhanced preoperative characterization of PanNENs. A multimodal diagnostic approach is required for a thorough disease assessment.

A novel method for detection of pancreatic Ductal Adenocarcinoma using explainable machine learning

BACKGROUND AND OBJECTIVE

Pancreatic Ductal Adenocarcinoma (PDAC) is a form of pancreatic cancer that is one of the primary causes of cancer-related deaths globally, with less than 10 % of the five years survival rate. The prognosis of pancreatic cancer has remained poor in the last four decades, mainly due to the lack of early diagnostic mechanisms. This study proposes a novel method for detecting PDAC using explainable and supervised machine learning from Raman spectroscopic signals.

METHODS

An insightful feature set consisting of statistical, peak, and extended empirical mode decomposition features is selected using the support vector machine recursive feature elimination method integrated with a correlation bias reduction. Explicable features successfully identified mutations in Kirsten rat sarcoma viral oncogene homolog (KRAS) and tumor suppressor protein53 (TP53) in the fingerprint region for the first time in the literature. PDAC and normal pancreas are classified using K-nearest neighbor, linear discriminant analysis, and support vector machine classifiers.

RESULTS

This study achieved a classification accuracy of 98.5% using a nonlinear support vector machine. Our proposed method reduced test time by 28.5 % and saved 85.6 % memory utilization, which reduces complexity significantly and is more accurate than the state-of-the-art method. The generalization of the proposed method is assessed by fifteen-fold cross-validation, and its performance is evaluated using accuracy, specificity, sensitivity, and receiver operating characteristic curves.

CONCLUSIONS

In this study, we proposed a method to detect and define the fingerprint region for PDAC using explainable machine learning. This simple, accurate, and efficient method for PDAC detection in mice could be generalized to examine human pancreatic cancer and provide a basis for precise chemotherapy for early cancer treatment.

Accurate non-invasive grading of nonfunctional pancreatic neuroendocrine tumors with a CT derived radiomics signature

PURPOSE

The purpose of this study was to develop a radiomics-signature using computed tomography (CT) data for the preoperative prediction of grade of nonfunctional pancreatic neuroendocrine tumors (NF-PNETs).

MATERIALS AND METHODS

A retrospective study was performed on patients undergoing resection for NF-PNETs between 2010 and 2019. A total of 2436 radiomic features were extracted from arterial and venous phases of pancreas-protocol CT examinations. Radiomic features that were associated with final pathologic grade observed in the surgical specimens were subjected to joint mutual information maximization for hierarchical feature selection and the development of the radiomic-signature. Youden-index was used to identify optimal cutoff for determining tumor grade. A random forest prediction model was trained and validated internally. The performance of this tool in predicting tumor grade was compared to that of EUS-FNA sampling that was used as the standard of reference.

RESULTS

A total of 270 patients were included and a fusion radiomic-signature based on 10 selected features was developed using the development cohort (n = 201). There were 149 men and 121 women with a mean age of 59.4 ± 12.3 (standard deviation) years (range: 23.3-85.0 years). Upon internal validation in a new set of 69 patients, a strong discrimination was observed with an area under the curve (AUC) of 0.80 (95% confidence interval [CI]: 0.71-0.90) with corresponding sensitivity and specificity of 87.5% (95% CI: 79.7-95.3) and 73.3% (95% CI: 62.9-83.8) respectively. Of the study population, 143 patients (52.9%) underwent EUS-FNA. Biopsies were non-diagnostic in 26 patients (18.2%) and could not be graded due to insufficient sample in 42 patients (29.4%). In the cohort of 75 patients (52.4%) in whom biopsies were graded the radiomic-signature demonstrated not different AUC as compared to EUS-FNA (AUC: 0.69 vs. 0.67; P = 0.723), however greater sensitivity (i.e., ability to accurately identify G2/3 lesion was observed (80.8% vs. 42.3%; P < 0.001).

CONCLUSION

Non-invasive assessment of tumor grade in patients with PNETs using the proposed radiomic-signature demonstrated high accuracy. Prospective validation and optimization could overcome the commonly experienced diagnostic uncertainty in the assessment of tumor grade in patients with PNETs and could facilitate clinical decision-making.

A Machine Learning Approach Using [18F]FDG PET-Based Radiomics for Prediction of Tumor Grade and Prognosis in Pancreatic Neuroendocrine Tumor

PURPOSE

We sought to develop and validate machine learning (ML) models for predicting tumor grade and prognosis using 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) positron emission tomography (PET)-based radiomics and clinical features in patients with pancreatic neuroendocrine tumors (PNETs).

PROCEDURES

A total of 58 patients with PNETs who underwent pretherapeutic [18F]FDG PET/computed tomography (CT) were retrospectively enrolled. PET-based radiomics extracted from segmented tumor and clinical features were selected to develop prediction models by the least absolute shrinkage and selection operator feature selection method. The predictive performances of ML models using neural network (NN) and random forest algorithms were compared by the areas under the receiver operating characteristic curves (AUROCs) and validated by stratified five-fold cross validation.

RESULTS

We developed two separate ML models for predicting high-grade tumors (Grade 3) and tumors with poor prognosis (disease progression within two years). The integrated models consisting of clinical and radiomic features with NN algorithm showed the best performances than the other models (stand-alone clinical or radiomics models). The performance metrics of the integrated model by NN algorithm were AUROC of 0.864 in the tumor grade prediction model and AUROC of 0.830 in the prognosis prediction model. In addition, AUROC of the integrated clinico-radiomics model with NN was significantly higher than that of tumor maximum standardized uptake model in predicting prognosis (P < 0.001).

CONCLUSIONS

Integration of clinical features and [18F]FDG PET-based radiomics using ML algorithms improved the prediction of high-grade PNET and poor prognosis in a non-invasive manner.

A Novel Observational Strategy for Nonfunctional Pancreatic Neuroendocrine Neoplasms With Texture Analysis: A Multicenter Retrospective Study

Background/Aim

Surgical resection is recommended for nonfunctional pancreatic neuroendocrine neoplasms (NF-pNENs). However, metastasis is rare in patients with small lesions with histological grade 1 (G1); thus, observation is an optional treatment approach for small NF-pNENs. Texture analysis (TA) is an imaging analysis mode for quantification of heterogeneity by extracting quantitative parameters from images. We retrospectively evaluated the utility of TA in predicting histological grade of resected NF-pNENs in a multicenter retrospective study.

Patients and Methods

The utility of TA in preoperative prediction of grade were evaluated with 29 patients treated by pancreatectomy for NF-pNEN who underwent preoperative dynamic computed tomography scan between January 1, 2013 and December 31, 2020 at three hospitals affiliated with the Jikei University School of Medicine. TA was performed with dedicated software for medical imaging processing for determining histological tumor grade using dynamic computed tomography images.

Results

Histological tumor grades based on the 2017 World Health Organization Classification for Pancreatic Neuroendocrine Neoplasms were grade 1, 2 and 3 in 18, 10 and one patient, respectively. Preoperative grades by TA were 1 and 2/3 in 15 and 14 patients, respectively. The sensitivity, specificity and area under the curve for TA-oriented grade 1 lesions were 1.00, 0.889 and 0.965 (95% confidence interval=0.901-1.000), respectively.

Conclusion

TA is useful for predicting grade 2/3 NF-pNEN and can provide a safe option for observation for patients with small grade 1 lesions.

Diagnostic accuracy of apparent diffusion coefficient to differentiate intrapancreatic accessory spleen from pancreatic neuroendocrine tumors

BACKGROUND

Intrapancreatic accessory spleen (IPAS) shares similar imaging findings with hypervascular pancreatic neuroendocrine tumors (PNETs), which may lead to unnecessary surgery.

AIM

To investigate and compare the diagnostic performance of absolute apparent diffusion coefficient (ADC) and normalized ADC (lesion-to-spleen ADC ratios) in the differential diagnosis of IPAS from PNETs.

METHODS

A retrospective study consisting of 29 patients (16 PNET patients vs 13 IPAS patients) who underwent preoperative contrast-enhanced magnetic resonance imaging together with diffusion-weighted imaging/ADC maps between January 2017 and July 2020 was performed. Two independent reviewers measured ADC on all lesions and spleens, and normalized ADC was calculated for further analysis. The receiver operating characteristics analysis was carried out for evaluating the diagnostic performance of both absolute ADC and normalized ADC values in the differential diagnosis between IPAS and PNETs by clarifying sensitivity, specificity, and accuracy. Inter-reader reliability for the two methods was evaluated.

RESULTS

IPAS had a significantly lower absolute ADC (0.931 ± 0.773 × 10^-3 mm²/s vs 1.254 ± 0.219 × 10^-3 mm²/s) and normalized ADC value (1.154 ± 0.167 vs 1.591 ± 0.364) compared to PNET. A cutoff value of 1.046 × 10^-3 mm²/s for absolute ADC was associated with 81.25% sensitivity, 100% specificity, and 89.66% accuracy with an area under the curve of 0.94 (95% confidence interval: 0.8536-1.000) for the differential diagnosis of IPAS from PNET. Similarly, a cutoff value of 1.342 for normalized ADC was associated with 81.25% sensitivity, 92.31% specificity, and 86.21% accuracy with an area under the curve of 0.91 (95% confidence interval: 0.8080-1.000) for the differential diagnosis of IPAS from PNET. Both methods showed excellent inter-reader reliability with intraclass correlation coefficients for absolute ADC and ADC ratio being 0.968 and 0.976, respectively.

CONCLUSION

Both absolute ADC and normalized ADC values can facilitate the differentiation between IPAS and PNET.

Diagnostic performance of texture analysis in the differential diagnosis of perianal fistulising Crohn’s disease and glandular anal fistula

BACKGROUND

Perianal fistulising Crohn's disease (PFCD) and glandular anal fistula have many similarities on conventional magnetic resonance imaging. However, many patients with PFCD show concomitant active proctitis, but only few patients with glandular anal fistula have active proctitis.

AIM

To explore the value of differential diagnosis of PFCD and glandular anal fistula by comparing the textural feature parameters of the rectum and anal canal in fat suppression T2-weighted imaging (FS-T2WI).

METHODS

Patients with rectal water sac implantation were screened from the first part of this study (48 patients with PFCD and 22 patients with glandular anal fistula). Open-source software ITK-SNAP (Version 3.6.0, http://www.itksnap.org/) was used to delineate the region of interest (ROI) of the entire rectum and anal canal wall on every axial section, and then the ROIs were input in the Analysis Kit software (version V3.0.0.R, GE Healthcare) to calculate the textural feature parameters. Textural feature parameter differences of the rectum and anal canal wall between the PFCD group vs the glandular anal fistula group were analyzed using Mann-Whitney U test. The redundant textural parameters were screened by bivariate Spearman correlation analysis, and binary logistic regression analysis was used to establish the model of textural feature parameters. Finally, diagnostic accuracy was assessed by receiver operating characteristic-area under the curve (AUC) analysis.

RESULTS

In all, 385 textural parameters were obtained, including 37 parameters with statistically significant differences between the PFCD and glandular anal fistula groups. Then, 16 texture feature parameters remained after bivariate Spearman correlation analysis, including one histogram parameter (Histogram energy); four grey level co-occurrence matrix (GLCM) parameters (GLCM energy_all direction_offset1_SD, GLCM entropy_all direction_ offset4_SD, GLCM entropy_all direction_offset7_SD, and Haralick correlation_all direction_ offset7_SD); four texture parameters (Correlation_all direction_offset1_SD, cluster prominence _angle 90_offset4, Inertia_all direction_offset7_SD, and cluster shade_angle 45_offset7); five grey level run-length matrix parameters (grey level nonuniformity_angle 90_offset1, grey level nonuniformity_all direction_offset4_SD, long run high grey level emphasis_all direction_offset1_SD, long run emphasis_all direction_ offset4_ SD, and long run high grey level emphasis_all direction_offset4_SD); and two form factor parameters (surface area and maximum 3D diameter). The AUC, sensitivity, and specificity of the model of textural feature parameters were 0.917, 85.42%, and 86.36%, respectively.

CONCLUSION

The model of textural feature parameters showed good diagnostic performance for PFCD. The texture feature parameters of the rectum and anal canal in FS-T2WI are helpful to distinguish PFCD from glandular anal fistula.

Spectral Computed Tomography-Derived Iodine Content and Tumor Response in the Follow-Up of Neuroendocrine Tumors-A Single-Center Experience

Spectral computed tomography (SCT) allows iodine content (IC) calculation for characterization of hypervascularized neoplasms and thus might help in the staging of neuroendocrine tumors (NETs). This single-center prospective study analyzed the association between SCT-derived IC and tumor response in the follow-up of metastasized NETs. Twenty-six patients with a median age of 70 years (range 51-85) with histologically proven NETs and a total of 78 lesions underwent SCT for staging. Because NETS are rare, no primary NET types were excluded. Lesions and intralesional hotspots were measured in virtual images and iodine maps. Tumor response was classified as progressive or nonprogressive at study endpoint. Generalized estimating equations served to estimate associations between IC and tumor response, additionally stratified by lesion location. Most commonly affected sites were the lymph nodes, liver, pancreas, and bones. Median time between SCT and endpoint was 64 weeks (range 5-260). Despite statistical imprecision in the estimate, patients with higher IC in lymphonodular metastases had lower odds for disease progression (adjusted OR = 0.21, 95% CI: 0.02-2.02). Opposite tendencies were observed in hepatic and pancreatic metastases in unadjusted analyses, which vanished after adjusting for therapy and primary tumor grade.

Differential Diagnosis of Pancreatic Cancer and Chronic Pancreatitis According to Endoscopic Ultrasonography Based on the Analysis of the Nature of the Contours of Focal Formations Based on Fuzzy Mathematical Models

One of the key echographic signs of focal pathology of the pancreas is the presence of formation contours and their nature. Endoscopic ultrasonography has a unique ability to visualize the echographic texture of the pancreatic parenchyma, and also allows you to assess in detail the boundaries and nature of the contours of the tumor formations of the organ due to the proximity of the ultrasound sensor. However, the differential diagnosis of focal pancreatic lesions remains a difficult clinical task due to the similarity of their echosemiotics. One of the ways to objectify and improve the accuracy of ultrasound data is the use of artificial intelligence methods for interpreting images. Improving the quality of differential diagnosis of focal pathology of the pancreas according to endoscopic ultrasonography based on the analysis of the nature of the contours of focal formations using fuzzy mathematical models.

Pancreatic neuroendocrine neoplasms: a 2022 update for radiologists

Pancreatic neuroendocrine neoplasms (PaNENs) are a unique group of pancreatic neoplasms with a wide range of clinical presentations and behaviors. Given their heterogeneous appearance and increasing detection on cross-sectional imaging, it is essential that radiologists understand the variable presentation and distinctions PaNENs display compared to other pancreatic neoplasms. Additionally, some of these neoplasms may be hormonally functional, and it is imperative that radiologists be aware of the common clinical presentations of hormonally active PaNENs. Knowledge of PaNEN pathology and treatments may influence which imaging modality is optimal for each patient. Each imaging modality used for PaNENs has distinct advantages and disadvantages, particularly in different treatment settings. Thus, the focus of this manuscript is to provide an update for the radiologist on PaNEN pathology, imaging, and treatments.

Maximum Value on Arterial Phase Computed Tomography Predicts Prognosis and Treatment Efficacy of Sunitinib for Pancreatic Neuroendocrine Tumours

PURPOSE

This study was designed to assess the computed tomography maximum (CTmax) value on pretherapeutic arterial phase computed tomography (APCT) images to predict pancreatic neuroendocrine tumours (pNETs) recurrence and clarify its role in predicting the outcome of tumour therapy.

METHODS

This retrospective study enrolled 250 surgical patients and 24 nonsurgical patients with sunitinib-based treatment in our hospital from 2008 to 2019. CT images were assessed, the maximum value was defined as "CTmax," and recurrence-free survival (RFS) or progression-free survival (PFS) was compared between a high-CTmax group and a low-CTmax group among patients who underwent surgical resection or nonsurgical, sunitinib-based treatment according to the CTmax cutoff value.

RESULTS

In ROC curve analysis, a CTmax of 108 Hounsfield units, as the cutoff value, achieved an AUC of 0.796 in predicting recurrence. Compared with the low-CTmax group, the high-CTmax group had a longer RFS (p < 0.001). Low CTmax was identified as an independent factor for RFS (p < 0.001) in multivariate analysis; these results were confirmed using the internal validation set. The CTmax value was significantly correlated with the microvascular density (MVD) value (p < 0.001) and the vascular endothelial growth factor receptor 2 (VEGFR2) score (p < 0.001). Furthermore, the high-CTmax group had a better PFS than the low-CTmax group among the sunitinib treatment group (p = 0.007).

CONCLUSIONS

The tumour CTmax on APCT might be a potential and independent indicator for predicting recurrence in patients who have undergone surgical resection and assessing the efficacy of sunitinib for patients with advanced metastatic pNETs.

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.

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.

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.

Preoperative Prediction of G1 and G2/3 Grades in Patients With Nonfunctional Pancreatic Neuroendocrine Tumors Using Multimodality Imaging

OBJECTIVES

We aimed to develop and validate a multimodality radiomics model for the preoperative prediction of nonfunctional pancreatic neuroendocrine tumor (NF-pNET) grade (G).

METHODS

This retrospective study assessed 123 patients with surgically resected, pathologically confirmed NF-pNETs who underwent multidetector computed tomography and MRI scans between December 2012 and May 2020. Radiomic features were extracted from multidetector computed tomography and MRI. Wilcoxon rank-sum test and Max-Relevance and Min-Redundancy tests were used to select the features. The linear discriminative analysis (LDA) was used to construct the four models including a clinical model, MRI radiomics model, computed tomography radiomics model, and mixed radiomics model. The performance of the models was assessed using a training cohort (82 patients) and a validation cohort (41 patients), and decision curve analysis was applied for clinical use.

RESULTS

We successfully constructed 4 models to predict the tumor grade of NF- pNETs. Model 4 combined 6 features of T2-weighted imaging radiomics features and 1 arterial-phase computed tomography radiomics feature, and showed better discrimination in the training cohort (AUC = 0.92) and validation cohort (AUC = 0.85) relative to the other models. In the decision curves, if the threshold probability was 0.07-0.87, the use of the radiomics score to distinguish NF-pNET G1 and G2/3 offered more benefit than did the use of a "treat all patients" or a "treat none" scheme in the training cohort of the MRI radiomics model.

CONCLUSION

The LDA classifier combining multimodality images may be a valuable noninvasive tool for distinguishing NF-pNET grades and avoid unnecessary surgery.

Two-dimensional and three-dimensional T2 weighted imaging-based radiomic signatures for the preoperative discrimination of ovarian borderline tumors and malignant tumors

BACKGROUND

Ovarian cancer is the most women malignancy in the whole world. It is difficult to differentiate ovarian cancers from ovarian borderline tumors because of some similar imaging findings.Radiomics study may help clinicians to make a proper diagnosis before invasive surgery.

PURPOSE

To evaluate the ability of T2-weighted imaging (T2WI)-based radiomics to discriminate ovarian borderline tumors (BOTs) from malignancies based on two-dimensional (2D) and three-dimensional (3D) lesion segmentation methods.

METHODS

A total of 95 patients with pathologically proven ovarian BOTs and 101 patients with malignancies were retrospectively included in this study. We evaluated the diagnostic performance of the signatures derived from T2WI-based radiomics in their ability to differentiate between BOTs and malignancies and compared the performance differences in the 2D and 3D segmentation models. The least absolute shrinkage and selection operator method (Lasso) was used for radiomics feature selection and machine learning processing.

RESULTS

The radiomics score between BOTs and malignancies in four types of selected T2WI-based radiomics models differed significantly at the statistical level (p < 0.0001). For the classification between BOTs and malignant masses, the 2D and 3D coronal T2WI-based radiomics models yielded accuracy values of 0.79 and 0.83 in the testing group, respectively; the 2D and 3D sagittal fat-suppressed (fs) T2WI-based radiomics models yielded an accuracy of 0.78 and 0.99, respectively.

CONCLUSIONS

Our results suggest that T2WI-based radiomic features were highly correlated with ovarian tumor subtype classification. 3D-sagittal MRI radiomics features may help clinicians differentiate ovarian BOTs from malignancies with high ACC.

Gd-EOB-DTPA-enhanced MRI radiomic features for predicting histological grade of hepatocellular carcinoma

Background

Prediction models for the histological grade of hepatocellular carcinoma (HCC) remain unsatisfactory. The purpose of this study is to develop preoperative models to predict histological grade of HCC based on gadolinium-ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) radiomics. And to compare the performance between artificial neural network (ANN) and logistic regression model.

Methods

A total of 122 HCCs were randomly assigned to the training set (n=85) and the test set (n=37). There were 242 radiomic features extracted from volumetric of interest (VOI) of arterial and hepatobiliary phases images. The radiomic features and clinical parameters [gender, age, alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen 19-9 (CA19-9), alanine aminotransferase (ALT), aspartate transaminase (AST)] were selected by permutation test and decision tree. ANN of arterial phase (ANN-AP), logistic regression model of arterial phase (LR-AP), ANN of hepatobiliary phase (ANN-HBP), logistic regression mode of hepatobiliary phase (LR-HBP), ANN of combined arterial and hepatobiliary phases (ANN-AP + HBP), and logistic regression model of combined arterial and hepatobiliary phases (LR-AP + HBP) were built to predict HCC histological grade. Those prediction models were assessed and compared.

Results

ANN-AP and LR-AP were composed by AST and radiomic features based on arterial phase. ANN-HBP and LR-HBP were composed by AFP and radiomic features based on hepatobiliary phase. ANN-AP + HBP and LR-AP + HBP were composed by AST and radiomic features based on arterial and hepatobiliary phases. The prediction models could distinguish between high-grade tumors [Edmondson-Steiner (E-S) grade III and IV] and low-grade tumors (E-S grade I and II) in both training set and test set. In the test set, the AUCs of ANN-AP, LR-AP, ANN-HBP, LR-HBP, ANN-AP + HBP and LR-AP + HBP were 0.889, 0.777, 0.941, 0.819, 0.944 and 0.792 respectively. The ANN-HBP was significantly superior to LR-HBP (P=0.001). And the ANN-AP + HBP was significantly superior to LR-AP + HBP (P=0.007).

Conclusions

Prediction models consisting of clinical parameters and Gd-EOB-DTPA-enhanced MRI radiomic features (based on arterial phase, hepatobiliary phase, and combined arterial and hepatobiliary phases) could distinguish between high-grade HCCs and low-grade HCCs. And the ANN was superior to logistic regression model in predicting histological grade of HCC.

Pancreatic Serous Cystic Neoplasms and Mucinous Cystic Neoplasms: Differential Diagnosis by Combining Imaging Features and Enhanced CT Texture Analysis

Objective

To establish a diagnostic model by combining imaging features with enhanced CT texture analysis to differentiate pancreatic serous cystadenomas (SCNs) from pancreatic mucinous cystadenomas (MCNs).

Materials and Methods

Fifty-seven and 43 patients with pathology-confirmed SCNs and MCNs, respectively, from one center were analyzed and divided into a training cohort (n = 72) and an internal validation cohort (n = 28). An external validation cohort (n = 28) from another center was allocated. Demographic and radiological information were collected. The least absolute shrinkage and selection operator (LASSO) and recursive feature elimination linear support vector machine (RFE_LinearSVC) were implemented to select significant features. Multivariable logistic regression algorithms were conducted for model construction. Receiver operating characteristic (ROC) curves for the models were evaluated, and their prediction efficiency was quantified by the area under the curve (AUC), 95% confidence interval (95% CI), sensitivity and specificity.

Results

Following multivariable logistic regression analysis, the AUC was 0.932 and 0.887, the sensitivity was 87.5% and 90%, and the specificity was 82.4% and 84.6% with the training and validation cohorts, respectively, for the model combining radiological features and CT texture features. For the model based on radiological features alone, the AUC was 0.84 and 0.91, the sensitivity was 75% and 66.7%, and the specificity was 82.4% and 77% with the training and validation cohorts, respectively.

Conclusion

This study showed that a logistic model combining radiological features and CT texture features is more effective in distinguishing SCNs from MCNs of the pancreas than a model based on radiological features alone.

Trends in Incidence and Survival of Patients with Pancreatic Neuroendocrine Neoplasm, 1987-2016

Background

Pancreatic neuroendocrine neoplasm (pNEN), with the lowest 5-year survival rates in neuroendocrine tumors (NETs), exerts great threat to human health. Because large-scale population research aimed at pNEN is rare, we aimed to explore the tendencies and differences of changes in incidences and survival rates of pNEN in each decade from 1987 to 2016 and evaluate the impacts of age, sex, race, socioeconomic status (SES), and grade.

Methods

Data on pNEN cases from 1987 to 2016 were extracted from the Surveillance, Epidemiology, and End Results Program (SEER) database. Kaplan-Meier, Cox proportional hazards regression analyses, and relative survival rates (RSRs) were used to identify risk factors for pNEN.

Results

The incidence and survival duration of pNEN increase every decade due to medical developments. The disparities of long-term survival in different age, sex, and grade groups expanded over time while that in race and SES groups narrowed. Older age and higher grade are independent risk factors for poorer survival. Females have lower incidence and longer survival than males. Prognosis of Black patients and poor (medium and high poverty) patients improved.

Conclusions

This study depicted changes in incidence and survival rates of pNEN over the past three decades and evaluated potential risk factors related to pNEN, benefiting future prediction of vulnerable and clinical options.

Diagnostic Value of CT- and MRI-Based Texture Analysis and Imaging Findings for Grading Cartilaginous Tumors in Long Bones

Objective

To confirm the diagnostic performance of computed tomography (CT)-based texture analysis (CTTA) and magnetic resonance imaging (MRI)-based texture analysis for grading cartilaginous tumors in long bones and to compare these findings to radiological features.

Materials and Methods

Twenty-nine patients with enchondromas, 20 with low-grade chondrosarcomas and 16 with high-grade chondrosarcomas were included retrospectively. Clinical and radiological information and 9 histogram features extracted from CT, T1WI, and T2WI were evaluated. Binary logistic regression analysis was performed to determine predictive factors for grading cartilaginous tumors and to establish diagnostic models. Another 26 patients were included to validate each model. Receiver operating characteristic (ROC) curves were generated, and accuracy rate, sensitivity, specificity and positive/negative predictive values (PPV/NPV) were calculated.

Results

On imaging, endosteal scalloping, cortical destruction and calcification shape were predictive for grading cartilaginous tumors. For texture analysis, variance, mean, perc.01%, perc.10%, perc.99% and kurtosis were extracted after multivariate analysis. To differentiate benign cartilaginous tumors from low-grade chondrosarcomas, the imaging features model reached the highest accuracy rate (83.7%) and AUC (0.841), with a sensitivity of 75% and specificity of 93.1%. The CTTA feature model best distinguished low-grade and high-grade chondrosarcomas, with accuracies of 71.9%, and 80% in the training and validation groups, respectively; T1-TA and T2-TA could not distinguish them well. We found that the imaging feature model best differentiated benign and malignant cartilaginous tumors, with an accuracy rate of 89.2%, followed by the T1-TA feature model (80.4%).

Conclusions

The imaging feature model and CTTA- or MRI-based texture analysis have the potential to differentiate cartilaginous tumors in long bones by grade. MRI-based texture analysis failed to grade chondrosarcomas.

Imaging of Pancreatic Neuroendocrine Neoplasms

Pancreatic neuroendocrine neoplasms (panNENs) represent the second most common pancreatic tumors. They are a heterogeneous group of neoplasms with varying clinical expression and biological behavior, from indolent to aggressive ones. PanNENs can be functioning or non-functioning in accordance with their ability or not to produce metabolically active hormones. They are histopathologically classified according to the 2017 World Health Organization (WHO) classification system. Although the final diagnosis of neuroendocrine tumor relies on histologic examination of biopsy or surgical specimens, both morphologic and functional imaging are crucial for patient care. Morphologic imaging with ultrasonography (US), computed tomography (CT) and magnetic resonance imaging (MRI) is used for initial evaluation and staging of disease, as well as surveillance and therapy monitoring. Functional imaging techniques with somatostatin receptor scintigraphy (SRS) and positron emission tomography (PET) are used for functional and metabolic assessment that is helpful for therapy management and post-therapeutic re-staging. This article reviews the morphological and functional imaging modalities now available and the imaging features of panNENs. Finally, future imaging challenges, such as radiomics analysis, are illustrated.

Contrast-Enhanced Ultrasonography Findings Correlate with Pathologic Grades of Pancreatic Neuroendocrine Tumors

The correlation of sonographic findings with pathologic grades of pancreatic neuroendocrine tumors (PNETs) remains unclear. This study aimed to evaluate the usefulness of sonographic features in diagnosing the pathologic grade of PNETs. Conventional and contrast-enhanced ultrasonography findings of PNETs diagnosed by surgical pathology from July 2010 to June 2020 were retrospectively reviewed. Sonographic features were compared among three pathologic grades of PNETs according to the World Health Organization 2010 classification. Ordinal regression models were constructed to evaluate the usefulness of the sonographic features in diagnosing the pathologic grade of PNETs. This study enrolled 93 participants with PNETs: 50 grade 1, 31 grade 2 and 12 grade 3. Multivariate ordinal regression analysis suggested that tumor size ≥2 cm (odds ratio [OR], 0.110; 95% confidence interval [CI], 0.020-0.606; p = 0.011), dilation of the main pancreatic duct (OR, 0.103; 95% CI, 0.025-0.430; p = 0.002), hepatic metastases (OR, 0.250; 95% CI, 0.072-0.869; p = 0.029) and hyper-enhancement in arterial phase (OR, 4.676; 95% CI, 1.656-13.206; p = 0.004) were significantly associated with the pathologic grades of PNETs. The accuracy of the ordinal logistic regression model in identifying grade 1, 2 and 3 PNETs was 77.4%, 67.7% and 90.3%, respectively. The findings suggest that sonographic features, including tumor size, pancreatic duct dilation and hepatic metastasis, as well as the enhancement level in arterial phase, may help identify different pathologic grades of PNETs.

Target Heterogeneity in Oncology: The Best Predictor for Differential Response to Radioligand Therapy in Neuroendocrine Tumors and Prostate Cancer

Simple Summary

In the era of precision medicine, novel targets have emerged on the surface of cancer cells, which have been exploited for the purpose of radioligand therapy. However, there have been variations in the way these receptors are expressed, especially in prostate cancers and neuroendocrine tumors. This variable expression of receptors across the grades of cancers led to the concept of ‘target heterogeneity’, which has not just impacted therapeutic decisions but also their outcomes. Radiopharmaceuticals targeting receptors need to be used when there are specific indicators—either clinical, radiological, or at molecular level—warranting their use. In addition, response to these radioligands can be assessed using different techniques, whereby we can prognosticate further outcomes. We shall also discuss, in this review, the conventional as well as novel approaches of detecting heterogeneity in prostate cancers and neuroendocrine tumors.

Abstract

Tumor or target heterogeneity (TH) implies presence of variable cellular populations having different genomic characteristics within the same tumor, or in different tumor sites of the same patient. The challenge is to identify this heterogeneity, as it has emerged as the most common cause of ‘treatment resistance’, to current therapeutic agents. We have focused our discussion on ‘Prostate Cancer’ and ‘Neuroendocrine Tumors’, and looked at the established methods for demonstrating heterogeneity, each with its advantages and drawbacks. Also, the available theranostic radiotracers targeting PSMA and somatostatin receptors combined with targeted systemic agents, have been described. Lu-177 labeled PSMA and DOTATATE are the ‘standard of care’ radionuclide therapeutic tracers for management of progressive treatment-resistant prostate cancer and NET. These approved therapies have shown reasonable benefit in treatment outcome, with improvement in quality of life parameters. Various biomarkers and predictors of response to radionuclide therapies targeting TH which are currently available and those which can be explored have been elaborated in details. Imaging-based features using artificial intelligence (AI) need to be developed to further predict the presence of TH. Also, novel theranostic tools binding to newer targets on surface of cancer cell should be explored to overcome the treatment resistance to current treatment regimens.

A [68Ga]Ga-DOTANOC PET/CT Radiomic Model for Non-Invasive Prediction of Tumour Grade in Pancreatic Neuroendocrine Tumours

Predicting grade 1 (G1) and 2 (G2) primary pancreatic neuroendocrine tumour (panNET) is crucial to foresee panNET clinical behaviour. Fifty-one patients with G1-G2 primary panNET demonstrated by pre-surgical [68Ga]Ga-DOTANOC PET/CT and diagnostic conventional imaging were grouped according to the tumour grade assessment method: histology on the whole excised primary lesion (HS) or biopsy (BS). First-order and second-order radiomic features (RFs) were computed from SUV maps for the whole tumour volume on HS. The RFs showing the lowest p-values and the highest area under the curve (AUC) were selected. Three radiomic models were assessed: A (trained on HS, validated on BS), B (trained on BS, validated on HS), and C (using the cross-validation on the whole dataset). The second-order normalized homogeneity and entropy was the most effective RFs couple predicting G2 and G1. The best performance was achieved by model A (test AUC = 0.90, sensitivity = 0.88, specificity = 0.89), followed by model C (median test AUC = 0.87, sensitivity = 0.83, specificity = 0.82). Model B performed worse. Using HS to train a radiomic model leads to the best prediction, although a “hybrid” (HS+BS) population performs better than biopsy-only. The non-invasive prediction of panNET grading may be especially useful in lesions not amenable to biopsy while [68Ga]Ga-DOTANOC heterogeneity might recommend FDG PET/CT.

Hypovascular pancreatic neuroendocrine tumor with hepatic metastases: A case report and literature review

Hypovascular pancreatic neuroendocrine tumors are uncommon pancreatic tumors and commonly misdiagnosed as pancreatic ductal adenocarcinoma or chronic mass-forming pancreatitis. The liver is the organ most commonly affected by neuroendocrine tumor metastases but hepatic neuroendocrine tumor metastases are quite difficult to discriminate from other hepatic metastases and primary hepatic tumors. We describe a case of a 47-year-old man with incidentally detected multiple hepatic lesions on ultrasound. On further imaging technique including computed tomography and magnetic resonance imaging, the patient had an abnormal hypoenhancing lesion at the pancreatic tail and multiple hyperenhancing hepatic metastases that were diagnosed as hypovascular pancreatic well-differentiated neuroendocrine tumor Grade 2 with multiple hypervascular hepatic metastases after liver biopsy and surgery. Neuroendocrine tumor is a rare etiology among hypoenhancing pancreatic tumors, and must be considered to discriminate from pancreatic adenocarcinomas in cases there are multiple hyperenhancing hepatic metastases on the arterial phase without typical washout on the portal venous phase.

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.

Prediction of the World Health Organization Grade of rectal neuroendocrine tumors based on CT histogram analysis

OBJECTIVES

To investigate the diagnostic value of contrast-enhanced computed tomography (CECT) histogram analysis in predicting the World Health Organization (WHO) grade of rectal neuroendocrine tumors (R-NETs).

MATERIALS AND METHODS

A total of 61 (35 G1, 12 G2, 10 G3, and 4 NECs) patients who underwent preoperative CECT and treated with surgery to be confirmed as R-NETs were included in this study from January 2014 to May 2019. We depicted ROIs and measured the CECT texture parameters (mean, median, 10th, 25th, 75th, 90th percentiles, skewness, kurtosis, and entropy) from arterial phase (AP) and venous phase (VP) images by two radiologists. We calculated intraclass correlation coefficient (ICC) and compared the histogram parameters between low-grade (G1) and higher grade (HG) (G2/G3/NECs) by applying appropriate statistical method. We obtained the optimal parameters to identify G1 from HG using receiver operating characteristic (ROC) curves.

RESULTS

The capability of AP and VP histogram parameters for differentiating G1 from HG was similar in several histogram parameters (mean, median, 10th, 25th, 75th, and 90th percentiles) (all p < 0.001). Skewness, kurtosis, and entropy on AP images showed no significant differences between G1 and HG (p = 0.853, 0.512, 0.557, respectively). Entropy on VP images was significantly different (p = 0.017) between G1 and HG, however, skewness and kurtosis showed no significant differences (p = 0.654, 0.172, respectively). ROC analysis showed a good predictive performance between G1 and HG, and the 75th (AP) generated the highest area under the curve (AUC = 0.871), followed by the 25th (AP), mean (VP), and median (VP) (AUC = 0.864). Combined the size of tumor and the 75th (AP) generated the highest AUC.

CONCLUSIONS

CECT histogram parameters, including arterial and venous phases, can be used as excellent indicators for predicting G1 and HG of rectal neuroendocrine tumors, and the size of the tumor is also an important independent predictor.

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.

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.

Usefulness of texture analysis for grading pancreatic neuroendocrine tumors on contrast-enhanced computed tomography and apparent diffusion coefficient maps

PURPOSE

To determine whether texture analysis of contrast-enhanced computed tomography (CECT) and apparent diffusion coefficient (ADC) maps could predict tumor grade (G1 vs G2-3) in patients with pancreatic neuroendocrine tumor (PNET).

MATERIALS AND METHODS

Thirty-three PNETs (22 G1 and 11 G2-3) were retrospectively reviewed. Fifty features were individually extracted from the arterial and portal venous phases of CECT and ADC maps by two radiologists. Diagnostic performance was assessed by receiver operating characteristic curves while inter-observer agreement was determined by calculating intraclass correlation coefficients (ICCs).

RESULTS

G2-G3 tumors were significantly larger than G1. Seventeen features significantly differed among the two readers on univariate analysis, with ICCs > 0.6; the largest area under the curve (AUC) for features of each CECT phase and ADC map was log-sigma 1.0 joint-energy = 0.855 for the arterial phase, log-sigma 1.5 kurtosis = 0.860 for the portal venous phase, and log-sigma 1.0 correlation = 0.847 for the ADC map. The log-sigma 1.5 kurtosis of the portal venous phase showed the largest AUC in the CECT and ADC map, and its sensitivity, specificity, and accuracy were 95.5%, 72.7%, and 87.9%, respectively.

CONCLUSION

Texture analysis may aid in differentiating between G1 and G2-3 PNET.

Morphological imaging and CT histogram analysis to differentiate pancreatic neuroendocrine tumor grade 3 from neuroendocrine carcinoma

PURPOSE

To compare morphological imaging features and CT texture histogram parameters between grade 3 pancreatic neuroendocrine tumors (G3-NET) and neuroendocrine carcinomas (NEC).

MATERIALS AND METHODS

Patients with pathologically proven G3-NET and NEC, according to the 2017 World Health Organization classification who had CT and MRI examinations between 2006-2017 were retrospectively included. CT and MRI examinations were reviewed by two radiologists in consensus and analyzed with respect to tumor size, enhancement patterns, hemorrhagic content, liver metastases and lymphadenopathies. Texture histogram analysis of tumors was performed on arterial and portal phase CT images. images. Morphological imaging features and CT texture histogram parameters of G3-NETs and NECs were compared.

RESULTS

Thirty-seven patients (21 men, 16 women; mean age, 56±13 [SD] years [range: 28-82 years]) with 37 tumors (mean diameter, 60±46 [SD] mm) were included (CT available for all, MRI for 16/37, 43%). Twenty-three patients (23/37; 62%) had NEC and 14 patients (14/37; 38%) had G3-NET. NECs were larger than G3-NETs (mean, 70±51 [SD] mm [range: 18 - 196mm] vs. 42±24 [SD] mm [range: 8 - 94mm], respectively; P=0.039), with more tumor necrosis (75% vs. 33%, respectively; P=0.030) and lower attenuation on precontrast (30±4 [SD] HU [range: 25-39 HU] vs. 37±6 [SD] [range: 25-45 HU], respectively; P=0.002) and on portal venous phase CT images (75±18 [SD] HU [range: 43 - 108 HU] vs. 92±19 [SD] HU [range: 46 - 117 HU], respectively; P=0.014). Hemorrhagic content on MRI was only observed in NEC (P=0.007). The mean ADC value was lower in NEC ([1.1±0.1 (SD)]×10^-3 mm²/s [range: (0.91 - 1.3)×10^-3 mm²/s] vs. [1.4±0.2 (SD)]×10^-3 mm²/s [range: (1.1 - 1.6)×10^-3 mm²/s]; P=0.005). CT histogram analysis showed that NEC were more heterogeneous on portal venous phase images (Entropy-0: 4.7±0.2 [SD] [range: 4.2-5.1] vs. 4.5±0.4 [SD] [range: 3.7-4.9]; P=0.023).

CONCLUSION

Pancreatic NECs are larger, more frequently hypoattenuating and more heterogeneous with hemorrhagic content than G3-NET on CT and MRI.

MRI texture analysis in acromegaly and its role in predicting response to somatostatin receptor ligands

PURPOSE

Given the paucity of reliable predictors of tumor recurrence, progression, or response to somatostatin receptor ligand (SRL) therapy in acromegaly, we attempted to determine whether preoperative MR image texture was predictive of these clinical outcomes. We also determined whether image texture could differentiate somatotroph adenomas from non-functioning pituitary adenomas (NFPAs).

METHODS

We performed a retrospective study of patients with acromegaly due to a macroadenoma who underwent transsphenoidal surgery at our institution between 2007 and 2015. Clinical data were extracted from electronic medical records. MRI texture analysis was performed on preoperative non-enhanced T1-weighted images using ImageJ (NIH). Logistic and Cox models were used to determine if image texture parameters predicted outcomes.

RESULTS

Eighty-nine patients had texture parameters measured, which were compared to that of NFPAs, while 64 of these patients had follow-up and were included in the remainder of analyses. Minimum pixel intensity, skewness, and kurtosis were significantly different in somatotroph adenomas versus NFPAs (area under the receiver operating characteristic curve, 0.7771, for kurtosis). Furthermore, those with a maximum pixel intensity above the median had an increased odds of IGF-I normalization on SRL therapy (OR 5.96, 95% CI 1.33-26.66), which persisted after adjusting for several potential predictors of response. Image texture did not predict tumor recurrence or progression.

CONCLUSION

Our data suggest that MRI texture analysis can distinguish NFPAs from somatotroph macroadenomas with good diagnostic accuracy and can predict normalization of IGF-I with SRL therapy.

Complementary role of computed tomography texture analysis for differentiation of pancreatic ductal adenocarcinoma from pancreatic neuroendocrine tumors in the portal-venous enhancement phase

Purpose

To assess the role of CT-texture analysis (CTTA) for differentiation of pancreatic ductal adenocarcinoma (PDAC) from pancreatic neuroendocrine neoplasm (PNEN) in the portal-venous phase as compared with visual assessment and tumor-to-pancreas attenuation ratios.

Methods

53 patients (66.1 ± 8.6y) with PDAC and 42 patients (65.5 ± 12.2y) with PNEN who underwent contrast-enhanced CT for primary staging were evaluated. Volumes of interests (VOIs) were set in the tumor tissue at the portal-venous phase excluding adjacent structures. Based on pyradiomics library, 92 textural features were extracted including 1st, 2nd, and higher order features, and then compared between PNEN and PDAC. The visual assessment classified tumors into hypo-, iso-, or hyperdense to pancreas parenchyma or into homogeneous/heterogeneous. Additionally, attenuation ratios between the tumors and the non-involved pancreas were calculated.

Results

8/92 (8.6%) highly significant (p < 0.005) discriminatory textural features between PDAC and PNEN were identified including the 1st order features “median,” “total energy,” “energy,” “10th percentile,” “90th percentile,” “minimum,” “maximum,” and the 2nd order feature “Gray-Level co-occurrence Matrix (GLCM) Informational Measure of Correlation (Imc2).” In PNEN, the higher order feature “GLSZM Small Area High Gray-Level Emphasis” proved significantly higher in G1 compared to G2/3 tumors (p < 0.05). The tumor/parenchyma ratios as well as the visual assessment into hypo-/iso-/hyperdense or homogeneous/heterogeneous did not significantly differ between PDAC and PNEN.

Conclusions

Our data indicate that CTTA is a feasible tool for differentiation of PNEN from PDAC and also of G1 from G2/3 PNEN in the portal-venous phase. Visual assessment and tumor-to-parenchyma ratios were not useful for discrimination.

Electronic supplementary material

The online version of this article (10.1007/s00261-020-02406-9) contains supplementary material, which is available to authorized users.