A primer on artificial intelligence in pancreatic imaging

Detection and characterization of pancreatic lesion with artificial intelligence: The SFR 2023 artificial intelligence data challenge

PURPOSE

The purpose of the 2023 SFR data challenge was to invite researchers to develop artificial intelligence (AI) models to identify the presence of a pancreatic mass and distinguish between benign and malignant pancreatic masses on abdominal computed tomography (CT) examinations.

MATERIALS AND METHODS

Anonymized abdominal CT examinations acquired during the portal venous phase were collected from 18 French centers. Abdominal CT examinations were divided into three groups including CT examinations with no lesion, CT examinations with benign pancreatic mass, or CT examinations with malignant pancreatic mass. Each team included at least one radiologist, one data scientist, and one engineer. Pancreatic lesions were annotated by expert radiologists. CT examinations were distributed in balanced batches via a Health Data Hosting certified platform. Data were distributed into four batches, two for training, one for internal evaluation, and one for the external evaluation. Training used 83 % of the data from 14 centers and external evaluation used data from the other four centers. The metric (i.e., final score) used to rank the participants was a weighted average of mean sensitivity, mean precision and mean area under the curve.

RESULTS

A total of 1037 abdominal CT examinations were divided into two training sets (including 500 and 232 CT examinations), an internal evaluation set (including 139 CT examinations), and an external evaluation set (including 166 CT examinations). The training sets were distributed on September 7 and October 13, 2023, and evaluation sets on October 15, 2023. Ten teams with a total of 93 members participated to the data challenge, with the best final score being 0.72.

CONCLUSION

This SFR 2023 data challenge based on multicenter CT data suggests that the use of AI for pancreatic lesions detection is possible on real data, but the distinction between benign and malignant pancreatic lesions remains challenging.

Artificial Intelligence in Pancreatic Image Analysis: A Review

Pancreatic cancer is a highly lethal disease with a poor prognosis. Its early diagnosis and accurate treatment mainly rely on medical imaging, so accurate medical image analysis is especially vital for pancreatic cancer patients. However, medical image analysis of pancreatic cancer is facing challenges due to ambiguous symptoms, high misdiagnosis rates, and significant financial costs. Artificial intelligence (AI) offers a promising solution by relieving medical personnel's workload, improving clinical decision-making, and reducing patient costs. This study focuses on AI applications such as segmentation, classification, object detection, and prognosis prediction across five types of medical imaging: CT, MRI, EUS, PET, and pathological images, as well as integrating these imaging modalities to boost diagnostic accuracy and treatment efficiency. In addition, this study discusses current hot topics and future directions aimed at overcoming the challenges in AI-enabled automated pancreatic cancer diagnosis algorithms.

Groove pancreatitis: From enigma to future directions-A comprehensive review

Groove pancreatitis (GP) is a rare and clinically distinct form of chronic pancreatitis affecting the pancreaticoduodenal groove comprising the head of the pancreas, duodenum, and the common bile duct. It is more prevalent in individuals in their 4-5th decade of life and disproportionately affects men compared with women. Excessive alcohol consumption, tobacco smoking, pancreatic ductal stones, pancreatic divisum, annular pancreas, ectopic pancreas, duodenal wall thickening, and peptic ulcers are significant risk factors implicated in the development of GP. The usual presenting symptoms include severe abdominal pain, nausea, vomiting, diarrhea, weight loss, and jaundice. Establishing a diagnosis of GP is often challenging due to significant clinical and radiological overlap with numerous benign and malignant conditions affecting the same anatomical location. This can lead to a delay in initiation of treatment leading to increasing morbidity, mortality, and complication rates. Promising research in artificial intelligence (AI) has garnered immense interest in recent years. Due to its widespread application in diagnostic imaging with a high degree of sensitivity and specificity, AI has the potential of becoming a vital tool in differentiating GP from pancreatic malignancies, thereby preventing a missed or delayed diagnosis. In this article, we provide a comprehensive review of GP, covering the etiology, pathogenesis, clinical presentation, radiological and endoscopic evaluation, management strategies, and future directions. This article also aims to increase awareness about this lesser known and often-misdiagnosed clinical entity amongst clinicians to ultimately improve patient outcomes.

Prognostic Significance of 18F-FDG PET/CT Radiomics in Patients With Resectable Pancreatic Ductal Adenocarcinoma Undergoing Curative Surgery

PURPOSE

This study aimed to investigate the prognostic significance of PET/CT radiomics to predict overall survival (OS) in patients with resectable pancreatic ductal adenocarcinoma (PDAC).

METHODS

We enrolled 627 patients with resectable PDAC who underwent preoperative 18F-FDG PET/CT and subsequent curative surgery. Radiomics analysis of the PET/CT images for the primary tumor was performed using the Chang-Gung Image Texture Analysis toolbox. Radiomics features were subjected to least absolute shrinkage and selection operator (LASSO) regression to select the most valuable imaging features of OS. The prognostic significance was evaluated by Cox proportional hazards regression analysis. Conventional PET parameters and LASSO score were assessed as predictive factors for OS by time-dependent receiver operating characteristic curve analysis.

RESULTS

During a mean follow-up of 28.8 months, 378 patients (60.3%) died. In the multivariable Cox regression analysis, tumor differentiation, resection margin status, tumor stage, and LASSO score were independent prognostic factors for OS (HR, 1.753, 1.669, 2.655, and 2.946; all P < 0.001, respectively). The time-dependent receiver operating characteristic curve analysis showed that the LASSO score had better predictive performance for OS than conventional PET parameters.

CONCLUSION

The LASSO score using the 18F-FDG PET/CT radiomics of the primary tumor was the independent prognostic factor for predicting OS in patients with resectable PDAC and may be helpful in determining therapeutic and follow-up plans for these patients.

Artificial intelligence in radiotherapy: Current applications and future trends

Radiation therapy has dramatically changed with the advent of computed tomography and intensity modulation. This added complexity to the workflow but allowed for more precise and reproducible treatment. As a result, these advances required the accurate delineation of many more volumes, raising questions about how to delineate them, in a uniform manner across centers. Then, as computing power improved, reverse planning became possible and three-dimensional dose distributions could be generated. Artificial intelligence offers the opportunity to make such workflow more efficient while increasing practice homogeneity. Many artificial intelligence-based tools are being implemented in routine practice to increase efficiency, reduce workload and improve homogeneity of treatments. Data retrieved from this workflow could be combined with clinical data and omic data to develop predictive tools to support clinical decision-making process. Such predictive tools are at the stage of proof-of-concept and need to be explainatory, prospectively validated, and based on large and multicenter cohorts. Nevertheless, they could bridge the gap to personalized radiation oncology, by personalizing oncologic strategies, dose prescriptions to tumor volumes and dose constraints to organs at risk.

Application of artificial intelligence in pancreas endoscopic ultrasound imaging- A systematic review

The pancreas is a vital organ in digestive system which has significant health implications. It is imperative to evaluate and identify malignant pancreatic lesions promptly in light of the high mortality rate linked to such malignancies. Endoscopic Ultrasound (EUS) is a non-invasive precise technique to detect pancreas disorders, but it is highly operator dependent. Artificial intelligence (AI), including traditional machine learning (ML) and deep learning (DL) techniques can play a pivotal role to enhancing the performance of EUS regardless of operator. AI performs a critical function in the detection, classification, and segmentation of medical images. The utilization of AI-assisted systems has improved the accuracy and productivity of pancreatic analysis, including the detection of diverse pancreatic disorders (e.g., pancreatitis, masses, and cysts) as well as landmarks and parenchyma. This systematic review examines the rapidly developing domain of AI-assisted system in EUS of the pancreas. Its objective is to present a thorough study of the present research status and developments in this area. This paper explores the significant challenges of AI-assisted system in pancreas EUS imaging, highlights the potential of AI techniques in addressing these challenges, and suggests the scope for future research in domain of AI-assisted EUS systems.

Early detection of pancreatic cancer in the era of precision medicine

Pancreatic ductal adenocarcinoma (PDAC) is the third leading cause of cancer-related mortality and it is often diagnosed at advanced stages due to non-specific clinical presentation. Disease detection at localized disease stage followed by surgical resection remains the only potentially curative treatment. In this era of precision medicine, a multifaceted approach to early detection of PDAC includes targeted screening in high-risk populations, serum biomarkers and "liquid biopsies", and artificial intelligence augmented tumor detection from radiologic examinations. In this review, we will review these emerging techniques in the early detection of PDAC.

Development of Clinical Radiomics-Based Models to Predict Survival Outcome in Pancreatic Ductal Adenocarcinoma: A Multicenter Retrospective Study

PURPOSE

This multicenter retrospective study aims to identify reliable clinical and radiomic features to build machine learning models that predict progression-free survival (PFS) and overall survival (OS) in pancreatic ductal adenocarcinoma (PDAC) patients.

METHODS

Between 2010 and 2020 pre-treatment contrast-enhanced CT scans of 287 pathology-confirmed PDAC patients from two sites of the Hopital Universitaire de Bruxelles (HUB) and from 47 hospitals within the HUB network were retrospectively analysed. Demographic, clinical, and survival data were also collected. Gross tumour volume (GTV) and non-tumoral pancreas (RPV) were semi-manually segmented and radiomics features were extracted. Patients from two HUB sites comprised the training dataset, while those from the remaining 47 hospitals of the HUB network constituted the testing dataset. A three-step method was used for feature selection. Based on the GradientBoostingSurvivalAnalysis classifier, different machine learning models were trained and tested to predict OS and PFS. Model performances were assessed using the C-index and Kaplan-Meier curves. SHAP analysis was applied to allow for post hoc interpretability.

RESULTS

A total of 107 radiomics features were extracted from each of the GTV and RPV. Fourteen subgroups of features were selected: clinical, GTV, RPV, clinical & GTV, clinical & GTV & RPV, GTV-volume and RPV-volume both for OS and PFS. Subsequently, 14 Gradient Boosting Survival Analysis models were trained and tested. In the testing dataset, the clinical & GTV model demonstrated the highest performance for OS (C-index: 0.72) among all other models, while for PFS, the clinical model exhibited a superior performance (C-index: 0.70).

CONCLUSIONS

An integrated approach, combining clinical and radiomics features, excels in predicting OS, whereas clinical features demonstrate strong performance in PFS prediction.

Feasibility of deep learning-reconstructed thin-slice single-breath-hold HASTE for detecting pancreatic lesions: A comparison with two conventional T2-weighted imaging sequences

Objective

The objective of this study was to evaluate the clinical feasibility of deep learning reconstruction-accelerated thin-slice single-breath-hold half-Fourier single-shot turbo spin echo imaging (HASTEDL) for detecting pancreatic lesions, in comparison with two conventional T2-weighted imaging sequences: compressed-sensing HASTE (HASTECS) and BLADE.

Methods

From March 2022 to January 2023, a total of 63 patients with suspected pancreatic-related disease underwent the HASTEDL, HASTECS, and BLADE sequences were enrolled in this retrospectively study. The acquisition time, the pancreatic lesion conspicuity (LCP), respiratory motion artifact (RMA), main pancreatic duct conspicuity (MPDC), overall image quality (OIQ), signal-to-noise ratio (SNR), and contrast-noise-ratio (CNR) of the pancreatic lesions were compared among the three sequences by two readers.

Results

The acquisition time of both HASTEDL and HASTECS was 16 s, which was significantly shorter than that of 102 s for BLADE. In terms of qualitative parameters, Reader 1 and Reader 2 assigned significantly higher scores to the LCP, RMA, MPDC, and OIQ for HASTEDL compared to HASTECS and BLADE sequences; As for the quantitative parameters, the SNR values of the pancreatic head, body, tail, and lesions, the CNR of the pancreatic lesion measured by the two readers were also significantly higher for HASTEDL than for HASTECS and BLADE sequences.

Conclusions

Compared to conventional T2WI sequences (HASTECS and BLADE), deep-learning reconstructed HASTE enables thin slice and single-breath-hold acquisition with clinical acceptable image quality for detection of pancreatic lesions.

A preoperative computed tomography radiomics model to predict disease-free survival in patients with pancreatic neuroendocrine tumors

IMPORTANCE

Imaging has demonstrated capabilities in the diagnosis of pancreatic neuroendocrine tumors (pNETs), but its utility for prognostic prediction has not been elucidated yet.

OBJECTIVE

The aim of this study was to build a radiomics model using preoperative computed tomography (CT) data that may help predict recurrence-free survival (RFS) or OS in patients with pNET.

DESIGN

We performed a retrospective observational study in a cohort of French patients with pNETs.

PARTICIPANTS

Patients with surgically resected pNET and available CT examinations were included.

INTERVENTIONS

Radiomics features of preoperative CT data were extracted using 3D-Slicer® software with manual segmentation. Discriminant features were selected with penalized regression using least absolute shrinkage and selection operator method with training on the tumor Ki67 rate (≤2 or >2). Selected features were used to build a radiomics index ranging from 0 to 1.

OUTCOME AND MEASURE

A receiving operator curve was built to select an optimal cutoff value of the radiomics index to predict patient RFS and OS. Recurrence-free survival and OS were assessed using Kaplan-Meier analysis.

RESULTS

Thirty-seven patients (median age, 61 years; 20 men) with 37 pNETs (grade 1, 21/37 [57%]; grade 2, 12/37 [32%]; grade 3, 4/37 [11%]) were included. Patients with a radiomics index >0.4 had a shorter median RFS (36 months; range: 1-133) than those with a radiomics index ≤0.4 (84 months; range: 9-148; P = .013). No associations were found between the radiomics index and OS (P = .86).

Modified Appleby procedure for locally advanced pancreatic carcinoma: A primer for the radiologist

Pancreatic ductal adenocarcinoma (PDAC) is the most prevalent pancreatic neoplasm accounting for more than 90% of pancreatic malignancies. Surgical resection with adequate lymphadenectomy remains the only available curative strategy for patients with PDAC. Despite improvements in both chemotherapy regimen and surgical care, body/neck PDAC still conveys a poor prognosis because of the vicinity of major vascular structures, including celiac trunk, which favors insidious disease spread at the time of diagnosis. Body/neck PDAC involving the celiac trunk is considered locally advanced PDAC in most guidelines and therefore not eligible for upfront resection. However, a more aggressive surgical approach (i.e., distal pancreatectomy with splenectomy and en-bloc celiac trunk resection [DP-CAR]) was recently proposed to offer hope for cure in selected patients with locally advanced body/neck PDAC responsive to induction therapy at the cost of higher morbidity. The so-called "modified Appleby procedure" is highly demanding and requires optimal preoperative staging as well as appropriate patient preparation for surgery (i.e., preoperative arterial embolization). Herein, we review current evidence regarding DP-CAR indications and outcomes as well as the critical role of diagnostic and interventional radiology in patient preparation before DP-CAR, and early identification and management of DP-CAR complications.

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.