Baseline Characteristics and Utility of Pretherapeutic Fluorodeoxyglucose-PET for Pancreatic Cancer.

INTRODUCTION: Pancreatic ductal adenocarcinoma (PDAC) is an aggressive and lethal malignancy. Surgical resection is the only curative modality combined with neoadjuvant chemotherapy to improve survival. Given the limitations of traditional responses like cross-sectional imaging (CT/MRI) or tumor markers, carbohydrate antigen 19-9 (CA19-9), the 2023 National Comprehensive Cancer Network (NCCN) guidelines included fluorodeoxyglucose-positron emission tomography (FDG-PET) as an adjunct to assess response to neoadjuvant chemotherapy. There are common misconceptions on the metabolic activity (tumor avidity) in PDAC, so we aimed to describe the baseline characteristics and utility of FDG-PET in a cohort of treatment naïve PDAC patients. METHODS: A single center retrospective study was conducted capturing all biopsy proven, treatment naïve PDAC patients that underwent either baseline FDG-PET/CT or FDG-PET/MRI imaging between (2008-2023). Baseline FDG-PET characteristics were collected, including primary tumors' maximum standardized uptake value (SUVmax) defined as metabolic activity (FDG uptake) of tumor compared to surrounding pancreatic parenchymal background, and the identification of extra-pancreatic metastatic disease. RESULTS: We identified 1095 treatment naïve PDAC patients that underwent baseline FDG-PET imaging at diagnosis. CA19-9 was elevated in 76% of patients. Overall, 96.3% (n=1054) of patients had FDG-avid tumors with a median SUVmax of 6.4. FDG-PET also identified suspicious extrapancreatic metastatic lesions in 50% of patients, with a higher proportion (p < 0.001) in PET/MRI (59.9%) vs. PET/CT (44.3%). After controlling for CA19-9 elevation, PET/MRI was superior in detection of extrapancreatic lesions compared to PET/CT. CONCLUSION: FDG-PET has significant utility in PDAC as a baseline imaging modality prior neoadjuvant therapy given the majority of tumors are FDG avid. Furthermore, FDG-PET can identify additional extrapancreatic suspicious lesions allowing for optimal initial staging, with PET/MRI having increased sensitivity over PET/CT.

Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods.

PURPOSE: To evaluate robustness of a radiomics-based support vector machine (SVM) model for detection of visually occult PDA on pre-diagnostic CTs by simulating common variations in image acquisition and radiomics workflow using image perturbation methods. METHODS: Eighteen algorithmically generated-perturbations, which simulated variations in image noise levels (σ, 2σ, 3σ, 5σ), image rotation [both CT image and the corresponding pancreas segmentation mask by 45° and 90° in axial plane], voxel resampling (isotropic and anisotropic), gray-level discretization [bin width (BW) 32 and 64)], and pancreas segmentation (sequential erosions by 3, 4, 6, and 8 pixels and dilations by 3, 4, and 6 pixels from the boundary), were introduced to the original (unperturbed) test subset (n = 128; 45 pre-diagnostic CTs, 83 control CTs with normal pancreas). Radiomic features were extracted from pancreas masks of these additional test subsets, and the model's performance was compared vis-a-vis the unperturbed test subset. RESULTS: The model correctly classified 43 out of 45 pre-diagnostic CTs and 75 out of 83 control CTs in the unperturbed test subset, achieving 92.2% accuracy and 0.98 AUC. Model's performance was unaffected by a three-fold increase in noise level except for sensitivity declining to 80% at 3σ (p = 0.02). Performance remained comparable vis-a-vis the unperturbed test subset despite variations in image rotation (p = 0.99), voxel resampling (p = 0.25-0.31), change in gray-level BW to 32 (p = 0.31-0.99), and erosions/dilations up to 4 pixels from the pancreas boundary (p = 0.12-0.34). CONCLUSION: The model's high performance for detection of visually occult PDA was robust within a broad range of clinically relevant variations in image acquisition and radiomics workflow.

Gallium-68-labeled fibroblast activation protein inhibitor-46 PET in patients with resectable or borderline resectable pancreatic ductal adenocarcinoma: A phase 2, multicenter, single arm, open label non-randomized study protocol.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a lethal disease prone to widespread metastatic dissemination and characterized by a desmoplastic stroma that contributes to poor outcomes. Fibroblast activation protein (FAP)-expressing Cancer-Associated Fibroblasts (CAFs) are crucial components of the tumor stroma, influencing carcinogenesis, fibrosis, tumor growth, metastases, and treatment resistance. Non-invasive tools to profile CAF identity and function are essential for overcoming CAF-mediated therapy resistance, developing innovative targeted therapies, and improved patient outcomes. We present the design of a multicenter phase 2 study (clinicaltrials.gov identifier NCT05262855) of [68Ga]FAPI-46 PET to image FAP-expressing CAFs in resectable or borderline resectable PDAC. METHODS: We will enroll up to 60 adult treatment-naïve patients with confirmed PDAC. These patients will be eligible for curative surgical resection, either without prior treatment (Cohort 1) or after neoadjuvant therapy (NAT) (Cohort 2). A baseline PET scan will be conducted from the vertex to mid-thighs approximately 15 minutes after administering 5 mCi (±2) of [68Ga]FAPI-46 intravenously. Cohort 2 patients will undergo an additional PET after completing NAT but before surgery. Histopathology and FAP immunohistochemistry (IHC) of initial diagnostic biopsy and resected tumor samples will serve as the truth standards. Primary objective is to assess the sensitivity, specificity, and accuracy of [68Ga]FAPI-46 PET for detecting FAP-expressing CAFs. Secondary objectives will assess predictive values and safety profile validation. Exploratory objectives are comparison of diagnostic performance of [68Ga]FAPI-46 PET to standard-of-care imaging, and comparison of pre- versus post-NAT [68Ga]FAPI-46 PET in Cohort 2. CONCLUSION: To facilitate the clinical translation of [68Ga]FAPI-46 in PDAC, the current study seeks to implement a coherent strategy to mitigate risks and increase the probability of meeting FDA requirements and stakeholder expectations. The findings from this study could potentially serve as a foundation for a New Drug Application to the FDA. TRIAL REGISTRATION: @ClinicalTrials.gov identifier NCT05262855.

Automated Artificial Intelligence Model Trained on a Large Data Set Can Detect Pancreas Cancer on Diagnostic Computed Tomography Scans As Well As Visually Occult Preinvasive Cancer on Prediagnostic Computed Tomography Scans.

BACKGROUND & AIMS: The aims of our case-control study were (1) to develop an automated 3-dimensional (3D) Convolutional Neural Network (CNN) for detection of pancreatic ductal adenocarcinoma (PDA) on diagnostic computed tomography scans (CTs), (2) evaluate its generalizability on multi-institutional public data sets, (3) its utility as a potential screening tool using a simulated cohort with high pretest probability, and (4) its ability to detect visually occult preinvasive cancer on prediagnostic CTs. METHODS: A 3D-CNN classification system was trained using algorithmically generated bounding boxes and pancreatic masks on a curated data set of 696 portal phase diagnostic CTs with PDA and 1080 control images with a nonneoplastic pancreas. The model was evaluated on (1) an intramural hold-out test subset (409 CTs with PDA, 829 controls); (2) a simulated cohort with a case-control distribution that matched the risk of PDA in glycemically defined new-onset diabetes, and Enriching New-Onset Diabetes for Pancreatic Cancer score ≥3; (3) multi-institutional public data sets (194 CTs with PDA, 80 controls), and (4) a cohort of 100 prediagnostic CTs (i.e., CTs incidentally acquired 3-36 months before clinical diagnosis of PDA) without a focal mass, and 134 controls. RESULTS: Of the CTs in the intramural test subset, 798 (64%) were from other hospitals. The model correctly classified 360 CTs (88%) with PDA and 783 control CTs (94%), with a mean accuracy 0.92 (95% CI, 0.91-0.94), area under the receiver operating characteristic (AUROC) curve of 0.97 (95% CI, 0.96-0.98), sensitivity of 0.88 (95% CI, 0.85-0.91), and specificity of 0.95 (95% CI, 0.93-0.96). Activation areas on heat maps overlapped with the tumor in 350 of 360 CTs (97%). Performance was high across tumor stages (sensitivity of 0.80, 0.87, 0.95, and 1.0 on T1 through T4 stages, respectively), comparable for hypodense vs isodense tumors (sensitivity: 0.90 vs 0.82), different age, sex, CT slice thicknesses, and vendors (all P > .05), and generalizable on both the simulated cohort (accuracy, 0.95 [95% 0.94-0.95]; AUROC curve, 0.97 [95% CI, 0.94-0.99]) and public data sets (accuracy, 0.86 [95% CI, 0.82-0.90]; AUROC curve, 0.90 [95% CI, 0.86-0.95]). Despite being exclusively trained on diagnostic CTs with larger tumors, the model could detect occult PDA on prediagnostic CTs (accuracy, 0.84 [95% CI, 0.79-0.88]; AUROC curve, 0.91 [95% CI, 0.86-0.94]; sensitivity, 0.75 [95% CI, 0.67-0.84]; and specificity, 0.90 [95% CI, 0.85-0.95]) at a median 475 days (range, 93-1082 days) before clinical diagnosis. CONCLUSIONS: This automated artificial intelligence model trained on a large and diverse data set shows high accuracy and generalizable performance for detection of PDA on diagnostic CTs as well as for visually occult PDA on prediagnostic CTs. Prospective validation with blood-based biomarkers is warranted to assess the potential for early detection of sporadic PDA in high-risk individuals.

Bounding box-based 3D AI model for user-guided volumetric segmentation of pancreatic ductal adenocarcinoma on standard-of-care CTs.

OBJECTIVES: To develop a bounding-box-based 3D convolutional neural network (CNN) for user-guided volumetric pancreas ductal adenocarcinoma (PDA) segmentation. METHODS: Reference segmentations were obtained on CTs (2006-2020) of treatment-naïve PDA. Images were algorithmically cropped using a tumor-centered bounding box for training a 3D nnUNet-based-CNN. Three radiologists independently segmented tumors on test subset, which were combined with reference segmentations using STAPLE to derive composite segmentations. Generalizability was evaluated on Cancer Imaging Archive (TCIA) (n = 41) and Medical Segmentation Decathlon (MSD) (n = 152) datasets. RESULTS: Total 1151 patients [667 males; age:65.3 ± 10.2 years; T1:34, T2:477, T3:237, T4:403; mean (range) tumor diameter:4.34 (1.1-12.6)-cm] were randomly divided between training/validation (n = 921) and test subsets (n = 230; 75% from other institutions). Model had a high DSC (mean ± SD) against reference segmentations (0.84 ± 0.06), which was comparable to its DSC against composite segmentations (0.84 ± 0.11, p = 0.52). Model-predicted versus reference tumor volumes were comparable (mean ± SD) (29.1 ± 42.2-cc versus 27.1 ± 32.9-cc, p = 0.69, CCC = 0.93). Inter-reader variability was high (mean DSC 0.69 ± 0.16), especially for smaller and isodense tumors. Conversely, model's high performance was comparable between tumor stages, volumes and densities (p > 0.05). Model was resilient to different tumor locations, status of pancreatic/biliary ducts, pancreatic atrophy, CT vendors and slice thicknesses, as well as to the epicenter and dimensions of the bounding-box (p > 0.05). Performance was generalizable on MSD (DSC:0.82 ± 0.06) and TCIA datasets (DSC:0.84 ± 0.08). CONCLUSION: A computationally efficient bounding box-based AI model developed on a large and diverse dataset shows high accuracy, generalizability, and robustness to clinically encountered variations for user-guided volumetric PDA segmentation including for small and isodense tumors. CLINICAL RELEVANCE: AI-driven bounding box-based user-guided PDA segmentation offers a discovery tool for image-based multi-omics models for applications such as risk-stratification, treatment response assessment, and prognostication, which are urgently needed to customize treatment strategies to the unique biological profile of each patient's tumor.

Artificial intelligence assisted whole organ pancreatic fat estimation on magnetic resonance imaging and correlation with pancreas attenuation on computed tomography.

BACKGROUND: Fatty pancreas is associated with inflammatory and neoplastic pancreatic diseases. Magnetic resonance imaging (MRI) is the diagnostic modality of choice for measuring pancreatic fat. Measurements typically use regions of interest limited by sampling and variability. We have previously described an artificial intelligence (AI)-aided approach for whole pancreas fat estimation on computed tomography (CT). In this study, we aimed to assess the correlation between whole pancreas MRI proton-density fat fraction (MR-PDFF) and CT attenuation. METHODS: We identified patients without pancreatic disease who underwent both MRI and CT between January 1, 2015 and June 1, 2020. 158 paired MRI and CT scans were available for pancreas segmentation using an iteratively trained convolutional neural network (CNN) with manual correction. Boxplots were generated to visualize slice-by-slice variability in 2D-axial slice MR-PDFF. Correlation between whole pancreas MR-PDFF and age, BMI, hepatic fat and pancreas CT-Hounsfield Unit (CT-HU) was assessed. RESULTS: Mean pancreatic MR-PDFF showed a strong inverse correlation (Spearman -0.755) with mean CT-HU. MR-PDFF was higher in males (25.22 vs 20.87; p = 0.0015) and in subjects with diabetes mellitus (25.95 vs 22.17; p = 0.0324), and was positively correlated with age and BMI. The pancreatic 2D-axial slice-to-slice MR-PDFF variability increased with increasing mean whole pancreas MR-PDFF (Spearman 0.51; p < 0.0001). CONCLUSION: Our study demonstrates a strong inverse correlation between whole pancreas MR-PDFF and CT-HU, indicating that both imaging modalities can be used to assess pancreatic fat. 2D-axial pancreas MR-PDFF is variable across slices, underscoring the need for AI-aided whole-organ measurements for objective and reproducible estimation of pancreatic fat.

Rectal cancer pelvic recurrence: imaging patterns and key concepts to guide treatment planning.

For rectal cancer, MRI plays an important role in assessing extramural tumor spread and informs surgical planning. The contemporary standardized management of rectal cancer with total mesorectal excision guided by imaging-based risk stratification has dramatically improved patient outcomes. Colonoscopy and CT are utilized in surveillance after surgery to detect intraluminal and extramural recurrence, respectively; however, local recurrence of rectal cancer remains a challenge because postoperative changes such as fat necrosis and fibrosis can resemble tumor recurrence; additionally, mucinous adenocarcinoma recurrence may mimic fluid collection or abscess on CT. MRI and 18F-FDG PET are problem-resolving modalities for equivocal imaging findings on CT. Treatment options for recurrent rectal cancer include pelvic exenteration to achieve radical (R0 resection) resection and intraoperative radiation therapy. After pathologic diagnosis of recurrence, imaging plays an essential role for evaluating the feasibility and approach of salvage surgery. Patterns of recurrence can be divided into axial/central, anterior, lateral, and posterior. Some lateral and posterior recurrence patterns especially in patients with neurogenic pain are associated with perineural invasion. Cross-sectional imaging, especially MRI and 18F-FDG PET, permit direct visualization of perineural spread, and contribute to determining the extent of resection. Multidisciplinary discussion is essential for treatment planning of locally recurrent rectal cancer. This review article illustrates surveillance strategy after initial surgery, imaging patterns of rectal cancer recurrence based on anatomic classification, highlights imaging findings of perineural spread on each modality, and discusses how resectability and contemporary surgical approaches are determined based on imaging findings.

Postoperative surveillance of pancreatic ductal adenocarcinoma (PDAC) recurrence: practice pattern on standardized imaging and reporting from the society of abdominal radiology disease focus panel on PDAC.

PURPOSE: Surgical resection is the only potential curative treatment for patients with pancreatic ductal adenocarcinoma (PDAC), but unfortunately most patients recur within 5 years of surgery. This article aims to assess the practice patterns across major academic institutions and develop consensus recommendations for postoperative imaging and interpretation in patients with PDAC. METHODS: The consensus recommendations for postoperative imaging surveillance following PDAC resection were developed using the Delphi method. Members of the Society of Abdominal Radiology (SAR) PDAC Disease Focused Panel (DFP) underwent three rounds of surveys followed by live webinar group discussions to develop consensus recommendations. RESULTS: Significant variations currently exist in the postoperative surveillance of PDAC, even among academic institutions. Differentiating common postoperative inflammatory and fibrotic changes from tumor recurrence remains a diagnostic challenge, and there is no reliable size threshold or growth rate of imaging findings that can provide differentiation. A new liver lesion or peritoneal nodule should be considered suspicious for tumor recurrence, and the imaging features should be interpreted in the appropriate clinical context (e.g., CA 19-9, clinical presentation, pathologic staging). CONCLUSION: Postoperative imaging following PDAC resection is challenging to interpret due to the presence of confounding postoperative inflammatory changes. A standardized reporting template for locoregional findings and report impression may improve communication of relaying risk of recurrence with referring providers, which merits validation in future studies.

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

PURPOSE: To determine if pancreas radiomics-based AI model can detect the CT imaging signature of type 2 diabetes (T2D). METHODS: Total 107 radiomic features were extracted from volumetrically segmented normal pancreas in 422 T2D patients and 456 age-matched controls. Dataset was randomly split into training (300 T2D, 300 control CTs) and test subsets (122 T2D, 156 control CTs). An XGBoost model trained on 10 features selected through top-K-based selection method and optimized through threefold cross-validation on training subset was evaluated on test subset. RESULTS: Model correctly classified 73 (60%) T2D patients and 96 (62%) controls yielding F1-score, sensitivity, specificity, precision, and AUC of 0.57, 0.62, 0.61, 0.55, and 0.65, respectively. Model's performance was equivalent across gender, CT slice thicknesses, and CT vendors (p values > 0.05). There was no difference between correctly classified versus misclassified patients in the mean (range) T2D duration [4.5 (0-15.4) versus 4.8 (0-15.7) years, p = 0.8], antidiabetic treatment [insulin (22% versus 18%), oral antidiabetics (10% versus 18%), both (41% versus 39%) (p > 0.05)], and treatment duration [5.4 (0-15) versus 5 (0-13) years, p = 0.4]. CONCLUSION: Pancreas radiomics-based AI model can detect the imaging signature of T2D. Further refinement and validation are needed to evaluate its potential for opportunistic T2D detection on millions of CTs that are performed annually.

FDG-PET Predicts Neoadjuvant Therapy Response and Survival in Borderline Resectable/Locally Advanced Pancreatic Adenocarcinoma.

BACKGROUND: Neoadjuvant therapy (NAT) is used in borderline resectable/locally advanced (BR/LA) pancreatic ductal adenocarcinoma (PDAC). Anatomic imaging (CT/MRI) poorly predicts response, and biochemical (CA 19-9) markers are not useful (nonsecretors/nonelevated) in many patients. Pathologic response highly predicts survival post-NAT, but is only known postoperatively. Because metabolic imaging (FDG-PET) reveals primary tumor viability, this study aimed to evaluate our experience with preoperative FDG-PET in patients with BR/LA PDAC in predicting NAT response and survival. METHODS: We reviewed all patients with resected BR/LA PDAC who underwent NAT with FDG-PET within 60 days of resection. Pre- and post-NAT metabolic (FDG-PET) and biochemical (CA 19-9) responses were dichotomized in addition to pathologic responses. We compared post-NAT metabolic and biochemical responses as preoperative predictors of pathologic responses and recurrence-free survival (RFS) and overall survival (OS). RESULTS: We identified 202 eligible patients. Post-NAT, 58% of patients had optimization of CA 19-9 levels. Major metabolic and pathologic responses were present in 51% and 38% of patients, respectively. Median RFS and OS times were 21 and 48.7 months, respectively. Metabolic response was superior to biochemical response in predicting pathologic response (area under the curve, 0.86 vs 0.75; P<.001). Metabolic response was the only univariate preoperative predictor of OS (odds ratio, 0.25; 95% CI, 0.13-0.40), and was highly correlated (P=.001) with pathologic response as opposed to biochemical response alone. After multivariate adjustment, metabolic response was the single largest independent preoperative predictor (P<.001) for pathologic response (odds ratio, 43.2; 95% CI, 16.9-153.2), RFS (hazard ratio, 0.37; 95% CI, 0.2-0.6), and OS (hazard ratio, 0.21; 95% CI, 0.1-0.4). CONCLUSIONS: Among patients with post-NAT resected BR/LA PDAC, FDG-PET highly predicts pathologic response and survival, superior to biochemical responses alone. Given the poor ability of anatomic imaging or biochemical markers to assess NAT responses in these patients, FDG-PET is a preoperative metric of NAT efficacy, thereby allowing potential therapeutic alterations and surgical treatment decisions. We suggest that FDG-PET should be an adjunct and recommended modality during the NAT phase of care for these patients.

Radiomics-based Machine-learning Models Can Detect Pancreatic Cancer on Prediagnostic Computed Tomography Scans at a Substantial Lead Time Before Clinical Diagnosis.

BACKGROUND & AIMS: Our purpose was to detect pancreatic ductal adenocarcinoma (PDAC) at the prediagnostic stage (3-36 months before clinical diagnosis) using radiomics-based machine-learning (ML) models, and to compare performance against radiologists in a case-control study. METHODS: Volumetric pancreas segmentation was performed on prediagnostic computed tomography scans (CTs) (median interval between CT and PDAC diagnosis: 398 days) of 155 patients and an age-matched cohort of 265 subjects with normal pancreas. A total of 88 first-order and gray-level radiomic features were extracted and 34 features were selected through the least absolute shrinkage and selection operator-based feature selection method. The dataset was randomly divided into training (292 CTs: 110 prediagnostic and 182 controls) and test subsets (128 CTs: 45 prediagnostic and 83 controls). Four ML classifiers, k-nearest neighbor (KNN), support vector machine (SVM), random forest (RM), and extreme gradient boosting (XGBoost), were evaluated. Specificity of model with highest accuracy was further validated on an independent internal dataset (n = 176) and the public National Institutes of Health dataset (n = 80). Two radiologists (R4 and R5) independently evaluated the pancreas on a 5-point diagnostic scale. RESULTS: Median (range) time between prediagnostic CTs of the test subset and PDAC diagnosis was 386 (97-1092) days. SVM had the highest sensitivity (mean; 95% confidence interval) (95.5; 85.5-100.0), specificity (90.3; 84.3-91.5), F1-score (89.5; 82.3-91.7), area under the curve (AUC) (0.98; 0.94-0.98), and accuracy (92.2%; 86.7-93.7) for classification of CTs into prediagnostic versus normal. All 3 other ML models, KNN, RF, and XGBoost, had comparable AUCs (0.95, 0.95, and 0.96, respectively). The high specificity of SVM was generalizable to both the independent internal (92.6%) and the National Institutes of Health dataset (96.2%). In contrast, interreader radiologist agreement was only fair (Cohen's kappa 0.3) and their mean AUC (0.66; 0.46-0.86) was lower than each of the 4 ML models (AUCs: 0.95-0.98) (P < .001). Radiologists also recorded false positive indirect findings of PDAC in control subjects (n = 83) (7% R4, 18% R5). CONCLUSIONS: Radiomics-based ML models can detect PDAC from normal pancreas when it is beyond human interrogation capability at a substantial lead time before clinical diagnosis. Prospective validation and integration of such models with complementary fluid-based biomarkers has the potential for PDAC detection at a stage when surgical cure is a possibility.

PET/CT and PET/MRI in neuroendocrine neoplasms.

Advanced molecular imaging has come to play an integral role in the management of gastro-entero-pancreatic neuroendocrine neoplasms (GEP-NENs). Somatostatin receptor (SSTR) PET has now emerged as the reference standard for the evaluation of NENs and is particularly critical in the context of peptide receptor radionuclide therapy (PRRT) eligibility. SSTR PET/MRI with liver-specific contrast agent has a strong potential for one-stop-shop multiparametric evaluation of GEP-NENs. 18F-FDG is a complementary radiotracer to SSTR, especially in the context of high-grade neuroendocrine neoplasms. Knowledge gaps in quantitative evaluation of molecular imaging studies and their role in assessment of response to PRRT and combination therapies are active research areas. Novel radiotracers have the potential to overcome existing limitations in the molecular imaging of GEP-NENs. The purpose of this article is to provide an overview of the current trends, pitfalls, and recent advancements of molecular imaging for GEP-NENs.

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.

Atypical Metastases in the Abdomen and Pelvis From Biochemically Recurrent Prostate Cancer: 11C-Choline PET/CT With Multimodality Correlation.

PET with targeted radiotracers has become integral to mapping the location and burden of recurrent disease in patients with biochemical recurrence (BCR) of prostate cancer (PCa). PET with 11C-choline is part of the National Comprehensive Cancer Network and European Association of Urology guidelines for evaluation of BCR. With advances in PET technology, increasing use of targeted radiotracers, and improved survival of patients with BCR because of novel therapeutics, atypical sites of metastases are being increasingly encountered, challenging the conventional view that prostate cancer rarely metastasizes beyond bones or lymph nodes. The purpose of this article is to describe such atypical metastases in the abdomen and pelvis on 11C-choline PET (including metastases to the liver, pancreas, genital tract, urinary tract, peritoneum, abdominal wall, and perineural spread) and to present multimodality imaging features and relevant imaging pitfalls. Given atypical metastases' inconsistent relationship with the serum PSA level and the nonspecific presenting symptoms, atypical metastases are often first detected on imaging. Awareness of their imaging features is important because their detection affects clinical management, patient counseling, prognosis, and clinical trial eligibility. Such awareness is particularly critical because the role of radiologists in the imaging and management of BCR will continue to increase given the expanding regulatory approvals of other targeted and theranostic radiotracers.

PSMA as a Theranostic Target in Hepatocellular Carcinoma: Immunohistochemistry and 68 Ga-PSMA-11 PET Using Cyclotron-Produced 68 Ga.

Prostate-specific membrane antigen (PSMA) is a validated target for molecular diagnostics and targeted radionuclide therapy. Our purpose was to evaluate PSMA expression in hepatocellular carcinoma (HCC), cholangiocarcinoma (CCA), and hepatic adenoma (HCA); investigate the genetic pathways in HCC associated with PSMA expression; and evaluate HCC detection rate with 68 Ga-PSMA-11 positron emission tomography (PET). In phase 1, PSMA immunohistochemistry (IHC) on HCC (n = 148), CCA (n = 111), and HCA (n = 78) was scored. In a subset (n = 30), messenger RNA (mRNA) data from the Cancer Genome Atlas HCC RNA sequencing were correlated with PSMA expression. In phase 2, 68 Ga-PSMA-11 PET was prospectively performed in patients with treatment-naïve HCC on a digital PET scanner using cyclotron-produced 68 Ga. Uptake was graded qualitatively and semi-quantitatively using standard metrics. On IHC, PSMA expression was significantly higher in HCC compared with CCA and HCA (P < 0.0001); 91% of HCCs (n = 134) expressed PSMA, which principally localized to tumor-associated neovasculature. Higher tumor grade was associated with PSMA expression (P = 0.012) but there was no association with tumor size (P = 0.14), fibrosis (P = 0.35), cirrhosis (P = 0.74), hepatitis B virus (P = 0.31), or hepatitis C virus (P = 0.15). Overall survival tended to be longer in patients without versus with PSMA expression (median overall survival: 4.2 vs. 1.9 years; P = 0.273). FGF14 (fibroblast growth factor 14) mRNA expression correlated positively (rho = 0.70; P = 1.70 × 10-5 ) and MAD1L1 (Mitotic spindle assembly checkpoint protein MAD1) correlated negatively with PSMA expression (rho = -0.753; P = 1.58 × 10-6 ). Of the 190 patients who met the eligibility criteria, 31 patients with 39 HCC lesions completed PET; 64% (n = 25) lesions had pronounced 68 Ga-PSMA-11 standardized uptake value: SUVmax (median [range] 9.2 [4.9-28.4]), SUVmean 4.7 (2.4-12.7), and tumor-to-liver background ratio 2 (1.1-11). Conclusion: Ex vivo expression of PSMA in neovasculature of HCC translates to marked tumor avidity on 68 Ga-PSMA-11 PET, which suggests that PSMA has the potential as a theranostic target in patients with HCC.

Learning to Generate Missing Pulse Sequence in MRI using Deep Convolution Neural Network Trained with Visual Turing Test.

Magnetic resonance imaging (MRI) is widely used in clinical applications due to its ability to acquire a wide variety of soft tissues using multiple pulse sequences. Each sequence provides information that generally complements the other. However, factors like an increase in scan time or contrast allergies impede imaging with numerous sequences. Synthesizing images of such non acquired sequences is a challenging proposition that can suffice for corrupted acquisition, fast reconstruction prior, super-resolution, etc. This manuscript employed a deep convolution neural network (CNN) to synthesize multiple missing pulse sequences of brain MRI with tumors. The CNN is an encoder-decoder-like network trained to minimize reconstruction mean square error (MSE) loss while maximizing the adversarial attack. It inflicts on a relativistic Visual Turing Test discriminator (rVTT). The approach is evaluated through experiments performed with the Brats2018 dataset, quantitative metrics viz. MSE, Structural Similarity Measure (SSIM), and Peak Signal to Noise Ratio (PSNR). The Radiologist and MR physicist performed the Turing test with 76% accuracy, demonstrating our approach's performance superiority over the prior art. We can synthesize MR images of missing pulse sequences at an inference cost of 350.71 GFlops/voxel through this approach.

Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications.

OBJECTIVE: Quality gaps in medical imaging datasets lead to profound errors in experiments. Our objective was to characterize such quality gaps in public pancreas imaging datasets (PPIDs), to evaluate their impact on previously published studies, and to provide post-hoc labels and segmentations as a value-add for these PPIDs. METHODS: We scored the available PPIDs on the medical imaging data readiness (MIDaR) scale, and evaluated for associated metadata, image quality, acquisition phase, etiology of pancreas lesion, sources of confounders, and biases. Studies utilizing these PPIDs were evaluated for awareness of and any impact of quality gaps on their results. Volumetric pancreatic adenocarcinoma (PDA) segmentations were performed for non-annotated CTs by a junior radiologist (R1) and reviewed by a senior radiologist (R3). RESULTS: We found three PPIDs with 560 CTs and six MRIs. NIH dataset of normal pancreas CTs (PCT) (n = 80 CTs) had optimal image quality and met MIDaR A criteria but parts of pancreas have been excluded in the provided segmentations. TCIA-PDA (n = 60 CTs; 6 MRIs) and MSD(n = 420 CTs) datasets categorized to MIDaR B due to incomplete annotations, limited metadata, and insufficient documentation. Substantial proportion of CTs from TCIA-PDA and MSD datasets were found unsuitable for AI due to biliary stents [TCIA-PDA:10 (17%); MSD:112 (27%)] or other factors (non-portal venous phase, suboptimal image quality, non-PDA etiology, or post-treatment status) [TCIA-PDA:5 (8.5%); MSD:156 (37.1%)]. These quality gaps were not accounted for in any of the 25 studies that have used these PPIDs (NIH-PCT:20; MSD:1; both: 4). PDA segmentations were done by R1 in 91 eligible CTs (TCIA-PDA:42; MSD:49). Of these, corrections were made by R3 in 16 CTs (18%) (TCIA-PDA:4; MSD:12) [mean (standard deviation) Dice: 0.72(0.21) and 0.63(0.23) respectively]. CONCLUSION: Substantial quality gaps, sources of bias, and high proportion of CTs unsuitable for AI characterize the available limited PPIDs. Published studies on these PPIDs do not account for these quality gaps. We complement these PPIDs through post-hoc labels and segmentations for public release on the TCIA portal. Collaborative efforts leading to large, well-curated PPIDs supported by adequate documentation are critically needed to translate the promise of AI to clinical practice.

Two-stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra-reader and inter-reader reliability at full and reduced radiation dose on an external dataset.

PURPOSE: To develop a two-stage three-dimensional (3D) convolutional neural networks (CNNs) for fully automated volumetric segmentation of pancreas on computed tomography (CT) and to further evaluate its performance in the context of intra-reader and inter-reader reliability at full dose and reduced radiation dose CTs on a public dataset. METHODS: A dataset of 1994 abdomen CT scans (portal venous phase, slice thickness ≤ 3.75-mm, multiple CT vendors) was curated by two radiologists (R1 and R2) to exclude cases with pancreatic pathology, suboptimal image quality, and image artifacts (n = 77). Remaining 1917 CTs were equally allocated between R1 and R2 for volumetric pancreas segmentation [ground truth (GT)]. This internal dataset was randomly divided into training (n = 1380), validation (n = 248), and test (n = 289) sets for the development of a two-stage 3D CNN model based on a modified U-net architecture for automated volumetric pancreas segmentation. Model's performance for pancreas segmentation and the differences in model-predicted pancreatic volumes vs GT volumes were compared on the test set. Subsequently, an external dataset from The Cancer Imaging Archive (TCIA) that had CT scans acquired at standard radiation dose and same scans reconstructed at a simulated 25% radiation dose was curated (n = 41). Volumetric pancreas segmentation was done on this TCIA dataset by R1 and R2 independently on the full dose and then at the reduced radiation dose CT images. Intra-reader and inter-reader reliability, model's segmentation performance, and reliability between model-predicted pancreatic volumes at full vs reduced dose were measured. Finally, model's performance was tested on the benchmarking National Institute of Health (NIH)-Pancreas CT (PCT) dataset. RESULTS: Three-dimensional CNN had mean (SD) Dice similarity coefficient (DSC): 0.91 (0.03) and average Hausdorff distance of 0.15 (0.09) mm on the test set. Model's performance was equivalent between males and females (P = 0.08) and across different CT slice thicknesses (P > 0.05) based on noninferiority statistical testing. There was no difference in model-predicted and GT pancreatic volumes [mean predicted volume 99 cc (31cc); GT volume 101 cc (33 cc), P = 0.33]. Mean pancreatic volume difference was -2.7 cc (percent difference: -2.4% of GT volume) with excellent correlation between model-predicted and GT volumes [concordance correlation coefficient (CCC)=0.97]. In the external TCIA dataset, the model had higher reliability than R1 and R2 on full vs reduced dose CT scans [model mean (SD) DSC: 0.96 (0.02), CCC = 0.995 vs R1 DSC: 0.83 (0.07), CCC = 0.89, and R2 DSC:0.87 (0.04), CCC = 0.97]. The DSC and volume concordance correlations for R1 vs R2 (inter-reader reliability) were 0.85 (0.07), CCC = 0.90 at full dose and 0.83 (0.07), CCC = 0.96 at reduced dose datasets. There was good reliability between model and R1 at both full and reduced dose CT [full dose: DSC: 0.81 (0.07), CCC = 0.83 and reduced dose DSC:0.81 (0.08), CCC = 0.87]. Likewise, there was good reliability between model and R2 at both full and reduced dose CT [full dose: DSC: 0.84 (0.05), CCC = 0.89 and reduced dose DSC:0.83(0.06), CCC = 0.89]. There was no difference in model-predicted and GT pancreatic volume in TCIA dataset (mean predicted volume 96 cc (33); GT pancreatic volume 89 cc (30), p = 0.31). Model had mean (SD) DSC: 0.89 (0.04) (minimum-maximum DSC: 0.79 -0.96) on the NIH-PCT dataset. CONCLUSION: A 3D CNN developed on the largest dataset of CTs is accurate for fully automated volumetric pancreas segmentation and is generalizable across a wide range of CT slice thicknesses, radiation dose, and patient gender. This 3D CNN offers a scalable tool to leverage biomarkers from pancreas morphometrics and radiomics for pancreatic diseases including for early pancreatic cancer detection.