A Visually Apparent and Quantifiable CT Imaging Feature Identifies Biophysical Subtypes of Pancreatic Ductal Adenocarcinoma

AI-Driven insights in pancreatic cancer imaging: from pre-diagnostic detection to prognostication

Pancreatic ductal adenocarcinoma (PDAC) is the third leading cause of cancer-related deaths in the United States, largely due to its poor five-year survival rate and frequent late-stage diagnosis. A significant barrier to early detection even in high-risk cohorts is that the pancreas often appears morphologically normal during the pre-diagnostic phase. Yet, the disease can progress rapidly from subclinical stages to widespread metastasis, undermining the effectiveness of screening. Recently, artificial intelligence (AI) applied to cross-sectional imaging has shown significant potential in identifying subtle, early-stage changes in pancreatic tissue that are often imperceptible to the human eye. Moreover, AI-driven imaging also aids in the discovery of prognostic and predictive biomarkers, essential for personalized treatment planning. This article uniquely integrates a critical discussion on AI's role in detecting visually occult PDAC on pre-diagnostic imaging, addresses challenges of model generalizability, and emphasizes solutions like standardized datasets and clinical workflows. By focusing on both technical advancements and practical implementation, this article provides a forward-thinking conceptual framework that bridges current gaps in AI-driven PDAC research.

Comparison between pancreatoblastoma (PB) and solid pseudopapillary neoplasm (SPN) in pediatric patients with enhanced CT

RATIONALE AND OBJECTIVES

To investigate whether computed tomography features can differentiate pancreatoblastoma (PB) from solid pseudopapillary tumor (SPN) in children.

MATERIALS AND METHODS

Clinical and imaging data of 18 cases of PB and 61 cases of SPN confirmed by surgery or biopsy were retrospectively analyzed. All enrolled patients underwent 3 phases (non-contrast, arterial, and portal venous phases) of CT scanning. Qualitative CT analysis (location, margin, solid/cystic component proportion, calcification, hemorrhage, peritumoral vascularity, bile duct dilatation, pancreatic duct dilatation, pancreatic atrophy, vascular invasion, peripancreatic invasion, and distant metastases) and quantitative analysis (maximum tumor diameter, interface between tumor and parenchyma [delta], arterial enhancement ratio [AER], and portal enhancement ratio [PER]) were performed. The general CT morphologic features, age and tumor markers were compared also compared between the groups. Univariate analysis and the F test were conducted to identify features of PB. Then logistic Regression classifier was trained using the top five features with the highest F-value. Moreover, we used 5-fold cross-validation techniques for the validation of our model.

RESULTS

PB exhibited a significantly higher frequency of location in the body/tail, larger tumor size, poorly defined margins, calcification, peritumoral vascularity, pancreatic atrophy, and less hemorrhage. In addition, PB had higher AER, PER and lower delta relative to SPN (p < 0.05). PB presented a younger age and higher levels of AFP. Results of the F test indicated that AFP, AER, Age, calcification and pancreatic atrophy were the top five features included in the model that could differentiate pediatric PB from SPN. The combined model of CT and clinical features performed well in differentiating PB from SPN, with an AUC of 0.981 in the training cohort and 0.953 in the validation cohort.

CONCLUSIONS

AFP, AER, age, calcification and pancreatic atrophy are robust CT and clinical features for differentiating pediatric PB from SPN. A combination of qualitative and quantitative CT features may provide good diagnostic accuracy in differentiating PB from SPN in children.

Performance of different CT enhancement quantification methods as predictors of pancreatic cancer recurrence after upfront surgery

The prognosis of pancreatic cancer (PDAC) after tumor resection remains poor, mostly due to a high but variable risk of recurrence. A promising tool for improved prognostication is the quantification of CT tumor enhancement. For this, various enhancement formulas have been used in previous studies. However, a systematic comparison of these formulas is lacking. In the present study, we applied twenty-three previously published CT enhancement formulas to our cohort of 92 PDAC patients who underwent upfront surgery. We identified seven formulas that could reliably predict tumor recurrence. Using these formulas, weak tumor enhancement was associated with tumor recurrence at one and two years after surgery (p ≤ 0.030). Enhancement was inversely associated with adverse clinicopathological features. Low enhancement values were predictive of a high recurrence risk (Hazard Ratio ≥ 1.659, p ≤ 0.028, Cox regression) and a short time to recurrence (TTR) (p ≤ 0.027, log-rank test). Some formulas were independent predictors of TTR in multivariate models. Strikingly, almost all of the best-performing formulas measure solely tumor tissue, suggesting that normalization to non-tumor structures might be unnecessary. Among the top performers were also the absolute arterial/portal venous tumor attenuation values. These can be easily implemented in clinical practice for better recurrence prediction, thus potentially improving patient management.

Blood-Based microRNA Biomarker Signature of Early-Stage Pancreatic Ductal Adenocarcinoma With Lead-Time Trajectory in Prediagnostic Samples

Background and Aims

Clinically validated biomarker of pancreatic ductal adenocarcinoma (PDAC), carbohydrate antigen 19-9 (CA19-9), has limited sensitivity and specificity for early-stage disease. Circulating miRNAs in plasma associated with cancer relevant pathways were developed as early detection biomarkers.

Methods

2083 miRNAs in 15 μl of plasma from multicenter age-matched cohorts (N = 203: healthy controls, n = 46; pancreatitis controls, n = 36; diagnosed cases: n = 121) and a prediagnostic Prostate, Lung, Colorectal, and Ovarian age- and gender-matched cohort (N = 96; controls, n = 48; prediagnosed cases, n = 48) were interrogated. A three-miRNA biomarker signature was developed for early-stage PDAC.

Results

The three-miRNA signature (let-7i-5p, miR-130a-3p and miR-221-3p) detected PDAC from healthy controls independently (area under the curve [AUC] of stage I, II, I-IV = 0.970, 0.975, 0.974) and in combination with CA19-9 (AUC of stage I, II, I-IV = 1.000, 0.992, 0.995). It also discriminated chronic pancreatitis (AUC of stage I, II, I-IV = 0.932, 0.931, 0.929), improving performance of CA19-9 alone (AUC of stage I, II, I-IV = 0.763, 0.701, 0.735) in combination (AUC of stage I, II, I-IV = 0.971, 0.943, 0.951). Blinded validation in prediagnostic Prostate, Lung, Colorectal, and Ovarian cohort revealed lead-time trajectory increase in AUC from 0.702 to 0.729 to 0.757 at twelve-, six-, and three-months before PDAC diagnosis, respectively. The signature also helped stratification of patients with different circulating tumor DNA and imaging subtypes.

Conclusion

Plasma miRNAs associated with oncogenic pathways may serve as PDAC early detection biomarkers.

Important Radiologic and Clinical Factors for Predicting Overall Survival in Pancreatic Adenocarcinoma Patients Who Underwent FOLFIRINOX

BACKGROUND

To predict poor overall survival (OS) in pancreatic adenocarcinoma (PAC) who underwent FOLFIRINOX (5-fluorouracil/leucovorin/irinotecan/oxaliplatin) using clinical and computed tomography (CT) findings.

METHODS

A total of 189 patients with PAC who received FOLFIRINOX were retrospectively included. Two reviewers assessed CT findings and resectability based on National Comprehensive Cancer Network guidelines. They determined tumor size changes according to Response Evaluation Criteria in Solid Tumors (RECIST 1.1). Delta measurements were performed. Clinical results, such as whether to perform surgery, were also investigated. A Cox proportional hazard model was used to identify significant predictors for OS. A CT-based nomogram was constructed to predict OS.

RESULTS

Seventy-four patients (39.2%) underwent surgery. For OS, rim enhancement of PAC on baseline CT (hazard ratio [HR], 1.75; 95% confidence interval [CI], 1.10-2.77; P = 0.018), high delta tumor on baseline CT (HR, 2.46; 95% CI, 1.55-3.91; P < 0.001), progressive disease at follow-up CT (HR, 8.89; 95% CI, 2.94-26.87; P < 0.001), and without surgery (HR, 2.81; 95% CI, 1.49-5.30; P = 0.001) were important features related to poor prognosis. The nomogram showed good predictive ability for the survival.

CONCLUSION

Both clinical and CT findings were useful for predicting OS after FOLFIRINOX in PAC.

Understanding the Conundrum of Pancreatic Cancer in the Omics Sciences Era

Pancreatic cancer (PC) is an increasing cause of cancer-related death, with a dismal prognosis caused by its aggressive biology, the lack of clinical symptoms in the early phases of the disease, and the inefficacy of treatments. PC is characterized by a complex tumor microenvironment. The interaction of its cellular components plays a crucial role in tumor development and progression, contributing to the alteration of metabolism and cellular hyperproliferation, as well as to metastatic evolution and abnormal tumor-associated immunity. Furthermore, in response to intrinsic oncogenic alterations and the influence of the tumor microenvironment, cancer cells undergo a complex oncogene-directed metabolic reprogramming that includes changes in glucose utilization, lipid and amino acid metabolism, redox balance, and activation of recycling and scavenging pathways. The advent of omics sciences is revolutionizing the comprehension of the pathogenetic conundrum of pancreatic carcinogenesis. In particular, metabolomics and genomics has led to a more precise classification of PC into subtypes that show different biological behaviors and responses to treatments. The identification of molecular targets through the pharmacogenomic approach may help to personalize treatments. Novel specific biomarkers have been discovered using proteomics and metabolomics analyses. Radiomics allows for an earlier diagnosis through the computational analysis of imaging. However, the complexity, high expertise required, and costs of the omics approach are the main limitations for its use in clinical practice at present. In addition, the studies of extracellular vesicles (EVs), the use of organoids, the understanding of host-microbiota interactions, and more recently the advent of artificial intelligence are helping to make further steps towards precision and personalized medicine. This present review summarizes the main evidence for the application of omics sciences to the study of PC and the identification of future perspectives.

PanIN or IPMN? Redefining Lesion Size in 3 Dimensions

Pancreatic ductal adenocarcinoma (PDAC) develops from 2 known precursor lesions: a majority (∼85%) develops from pancreatic intraepithelial neoplasia (PanIN), and a minority develops from intraductal papillary mucinous neoplasms (IPMNs). Clinical classification of PanIN and IPMN relies on a combination of low-resolution, 3-dimensional (D) imaging (computed tomography, CT), and high-resolution, 2D imaging (histology). The definitions of PanIN and IPMN currently rely heavily on size. IPMNs are defined as macroscopic: generally >1.0 cm and visible in CT, and PanINs are defined as microscopic: generally <0.5 cm and not identifiable in CT. As 2D evaluation fails to take into account 3D structures, we hypothesized that this classification would fail in evaluation of high-resolution, 3D images. To characterize the size and prevalence of PanINs in 3D, 47 thick slabs of pancreas were harvested from grossly normal areas of pancreatic resections, excluding samples from individuals with a diagnosis of an IPMN. All patients but one underwent preoperative CT scans. Through construction of cellular resolution 3D maps, we identified >1400 ductal precursor lesions that met the 2D histologic size criteria of PanINs. We show that, when 3D space is considered, 25 of these lesions can be digitally sectioned to meet the 2D histologic size criterion of IPMN. Re-evaluation of the preoperative CT images of individuals found to possess these large precursor lesions showed that nearly half are visible on imaging. These findings demonstrate that the clinical classification of PanIN and IPMN fails in evaluation of high-resolution, 3D images, emphasizing the need for re-evaluation of classification guidelines that place significant weight on 2D assessment of 3D structures.

The radiomorphological appearance of the invasive margin in pancreatic cancer is associated with tumor budding

PURPOSE

Pancreatic cancer (PDAC) is characterized by infiltrative, spiculated tumor growth into the surrounding non-neoplastic tissue. Clinically, its diagnosis is often established by magnetic resonance imaging (MRI). At the invasive margin, tumor buds can be detected by histology, an established marker associated with poor prognosis in different types of tumors.

METHODS

We analyzed PDAC by determining the degree of tumor spiculation on T2-weighted MRI using a 3-tier grading system. The grade of spiculation was correlated with the density of tumor buds quantified in histological sections of the respective surgical specimen according to the guidelines of the International Tumor Budding Consensus Conference (n = 28 patients).

RESULTS

64% of tumors revealed intermediate to high spiculation on MRI. In over 90% of cases, tumor buds were detected. We observed a significant positive rank correlation between the grade of radiological tumor spiculation and the histopathological number of tumor buds (rs = 0.745, p < 0.001). The number of tumor buds was not significantly associated with tumor stage, presence of lymph node metastases, or histopathological grading (p ≥ 0.352).

CONCLUSION

Our study identifies a readily available radiological marker for non-invasive estimation of tumor budding, as a correlate for infiltrative tumor growth. This finding could help to identify PDAC patients who might benefit from more extensive peripancreatic soft tissue resection during surgery or stratify patients for personalized therapy concepts.

MR-based radiomics predictive modelling of EGFR mutation and HER2 overexpression in metastatic brain adenocarcinoma: a two-centre study

OBJECTIVES

Magnetic resonance (MR)-based radiomics features of brain metastases are utilised to predict epidermal growth factor receptor (EGFR) mutation and human epidermal growth factor receptor 2 (HER2) overexpression in adenocarcinoma, with the aim to identify the most predictive MR sequence.

METHODS

A retrospective inclusion of 268 individuals with brain metastases from adenocarcinoma across two institutions was conducted. Utilising T1-weighted imaging (T1 contrast-enhanced [T1-CE]) and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequences, 1,409 radiomics features were extracted. These sequences were randomly divided into training and test sets at a 7:3 ratio. The selection of relevant features was done using the least absolute shrinkage selection operator, and the training cohort's support vector classifier model was employed to generate the predictive model. The performance of the radiomics features was evaluated using a separate test set.

RESULTS

For contrast-enhanced T1-CE cohorts, the radiomics features based on 19 selected characteristics exhibited excellent discrimination. No significant differences in age, sex, and time to metastasis were observed between the groups with EGFR mutations or HER2 + and those with wild-type EGFR or HER2 (p > 0.05). Radiomics feature analysis for T1-CE revealed an area under the curve (AUC) of 0.98, classification accuracy of 0.93, sensitivity of 0.92, and specificity of 0.93 in the training cohort. In the test set, the AUC was 0.82. The 19 radiomics features for the T2-FLAIR sequence showed AUCs of 0.86 in the training set and 0.70 in the test set.

CONCLUSIONS

This study developed a T1-CE signature that could serve as a non-invasive adjunctive tool to determine the presence of EGFR mutations and HER2 + status in adenocarcinoma, aiding in the direction of treatment plans.

CLINICAL RELEVANCE STATEMENT

We propose radiomics features based on T1-CE brain MR sequences that are both evidence-based and non-invasive. These can be employed to guide clinical treatment planning in patients with brain metastases from adenocarcinoma.

V, Agianian B, Garcia Chavez M, Vudatha V, Wang R, Vangipurapu R, Chen L, Kennedy P, Subramanian K, Quirke JC, Beato F, Underwood PW, Fleming JB, Trevino J, Hergenrother PJ, Gavathiotis E, Sebti SM. Discovery of KRB-456, a KRAS G12D Switch-I/II Allosteric Pocket Binder That Inhibits the Growth of Pancreatic Cancer Patient-derived Tumors

Currently, there are no clinically approved drugs that directly thwart mutant KRAS G12D, a major driver of human cancer. Here, we report on the discovery of a small molecule, KRB-456, that binds KRAS G12D and inhibits the growth of pancreatic cancer patient-derived tumors. Protein nuclear magnetic resonance studies revealed that KRB-456 binds the GDP-bound and GCP-bound conformation of KRAS G12D by forming interactions with a dynamic allosteric binding pocket within the switch-I/II region. Isothermal titration calorimetry demonstrated that KRB-456 binds potently to KRAS G12D with 1.5-, 2-, and 6-fold higher affinity than to KRAS G12V, KRAS wild-type, and KRAS G12C, respectively. KRB-456 potently inhibits the binding of KRAS G12D to the RAS-binding domain (RBD) of RAF1 as demonstrated by GST-RBD pulldown and AlphaScreen assays. Treatment of KRAS G12D-harboring human pancreatic cancer cells with KRB-456 suppresses the cellular levels of KRAS bound to GTP and inhibits the binding of KRAS to RAF1. Importantly, KRB-456 inhibits P-MEK, P-AKT, and P-S6 levels in vivo and inhibits the growth of subcutaneous and orthotopic xenografts derived from patients with pancreatic cancer whose tumors harbor KRAS G12D and KRAS G12V and who relapsed after chemotherapy and radiotherapy. These results warrant further development of KRB-456 for pancreatic cancer.

SIGNIFICANCE

There are no clinically approved drugs directly abrogating mutant KRAS G12D. Here, we discovered a small molecule, KRB-456, that binds a dynamic allosteric binding pocket within the switch-I/II region of KRAS G12D. KRB-456 inhibits P-MEK, P-AKT, and P-S6 levels in vivo and inhibits the growth of subcutaneous and orthotopic xenografts derived from patients with pancreatic cancer. This discovery warrants further advanced preclinical and clinical studies in pancreatic cancer.

Feasibility and effectiveness of automatic deep learning network and radiomics models for differentiating tumor stroma ratio in pancreatic ductal adenocarcinoma

OBJECTIVE

This study aims to compare the feasibility and effectiveness of automatic deep learning network and radiomics models in differentiating low tumor stroma ratio (TSR) from high TSR in pancreatic ductal adenocarcinoma (PDAC).

METHODS

A retrospective analysis was conducted on a total of 207 PDAC patients from three centers (training cohort: n = 160; test cohort: n = 47). TSR was assessed on hematoxylin and eosin-stained specimens by experienced pathologists and divided as low TSR and high TSR. Deep learning and radiomics models were developed including ShuffulNetV2, Xception, MobileNetV3, ResNet18, support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF), and logistic regression (LR). Additionally, the clinical models were constructed through univariate and multivariate logistic regression. Kaplan-Meier survival analysis and log-rank tests were conducted to compare the overall survival time between different TSR groups.

RESULTS

To differentiate low TSR from high TSR, the deep learning models based on ShuffulNetV2, Xception, MobileNetV3, and ResNet18 achieved AUCs of 0.846, 0.924, 0.930, and 0.941, respectively, outperforming the radiomics models based on SVM, KNN, RF, and LR with AUCs of 0.739, 0.717, 0.763, and 0.756, respectively. Resnet 18 achieved the best predictive performance. The clinical model based on T stage alone performed worse than deep learning models and radiomics models. The survival analysis based on 142 of the 207 patients demonstrated that patients with low TSR had longer overall survival.

CONCLUSIONS

Deep learning models demonstrate feasibility and superiority over radiomics in differentiating TSR in PDAC. The tumor stroma ratio in the PDAC microenvironment plays a significant role in determining prognosis.

CRITICAL RELEVANCE STATEMENT

The objective was to compare the feasibility and effectiveness of automatic deep learning networks and radiomics models in identifying the tumor-stroma ratio in pancreatic ductal adenocarcinoma. Our findings demonstrate deep learning models exhibited superior performance compared to traditional radiomics models.

KEY POINTS

• Deep learning demonstrates better performance than radiomics in differentiating tumor-stroma ratio in pancreatic ductal adenocarcinoma. • The tumor-stroma ratio in the pancreatic ductal adenocarcinoma microenvironment plays a protective role in prognosis. • Preoperative prediction of tumor-stroma ratio contributes to clinical decision-making and guiding precise medicine.

Dual-energy computed tomography-based iodine concentration as a predictor of histopathological response to preoperative chemoradiotherapy for pancreatic cancer

To explore predictors of the histopathological response to preoperative chemoradiotherapy (CRT) in patients with pancreatic cancer (PC) using dual-energy computed tomography-reconstructed images. This retrospective study divided 40 patients who had undergone preoperative CRT (50-60 Gy in 25 fractions) followed by surgical resection into two groups: the response group (Grades II, III and IV, evaluated from surgical specimens) and the nonresponse group (Grades Ia and Ib). The computed tomography number [in Hounsfield units (HUs)] and iodine concentration (IC) were measured at the locations of the aorta, PC and pancreatic parenchyma (PP) in the contrast-enhanced 4D dual-energy computed tomography images. Logistic regression analysis was performed to identify predictors of histopathological response. Univariate analysis did not reveal a significant relation between any parameter and patient characteristics or dosimetric parameters of the treatment plan. The HU and IC values in PP and the differences in HU and IC between the PP and PC (ΔHU and ΔIC, respectively) were significant predictors for distinguishing the response (n = 24) and nonresponse (n = 16) groups (P < 0.05). The IC in PP and ΔIC had a higher area under curve values [0.797 (95% confidence interval, 0.659-0.935) and 0.789 (0.650-0.928), respectively] than HU in PP and ΔHU [0.734 (0.580-0.889) and 0.721 (0.562-0.881), respectively]. The IC value could potentially be used for predicting the histopathological response in patients who have undergone preoperative CRT.

Pan-cancer analyses of senescence-related genes in extracellular matrix characterization in cancer

PURPOSE

The aged microenvironment plays a crucial role in tumor onset and progression. However, it remains unclear whether and how the aging of the extracellular matrix (ECM) influences cancer onset and progression. Furthermore, the mechanisms and implications of extracellular matrix senescence-related genes (ECM-SRGs) in pan-cancer have not been investigated.

METHODS

We collected profiling data from over 10,000 individuals, covering 33 cancer types, 750 small molecule drugs, and 24 immune cell types, for a thorough and systematic analysis of ECM-SRGs in cancer.

RESULTS

We observed a significant correlation between immune cell infiltrates and Gene Set Variation Analysis enrichment scores of ECM-SRGs in 33 cancer types. Moreover, our results revealed significant differences in immune cell infiltration among patients with copy number variations (CNV) and single nucleotide variations (SNV) in ECM-SRGs across various malignancies. Aberrant hypomethylation led to increased ECM-SRGs expression, and in specific malignancies, a connection between ECM-SRGs hypomethylation and adverse patient survival was established. The frequency of CNV and SNV in ECM-SRGs was elevated. We observed a positive correlation between CNV, SNV, and ECM-SRGs expression. Furthermore, a correlation was found between the high frequency of CNV and SNV in ECM-SRGs and poor patient survival in several cancer types. Additionally, the results demonstrated that ECM-SRGs expression could serve as a predictor of patient survival in diverse cancers. Pathway analysis unveiled the role of ECM-SRGs in activating EMT, apoptosis, and the RAS/MAPK signaling pathway while suppressing the cell cycle, hormone AR, and the response to DNA damage signaling pathway. Finally, we conducted searches in the "Genomics of Drug Sensitivity in Cancer" and "Genomics of Therapeutics Response Portal" databases, identifying several drugs that target ECM-SRGs.

CONCLUSIONS

We conducted a comprehensive evaluation of the genomes and immunogenomics of ECM-SRGs, along with their clinical features in 33 solid tumors. This may provide insights into the relationship between ECM-SRGs and tumorigenesis. Consequently, targeting these ECM-SRGs holds promise as a clinical approach for cancer treatment.

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.

Deep Learning for Fully Automated Prediction of Overall Survival in Patients Undergoing Resection for Pancreatic Cancer: A Retrospective Multicenter Study

OBJECTIVE

To develop an imaging-derived biomarker for prediction of overall survival (OS) of pancreatic cancer by analyzing preoperative multiphase contrast-enhanced computed topography (CECT) using deep learning.

BACKGROUND

Exploiting prognostic biomarkers for guiding neoadjuvant and adjuvant treatment decisions may potentially improve outcomes in patients with resectable pancreatic cancer.

METHODS

This multicenter, retrospective study included 1516 patients with resected pancreatic ductal adenocarcinoma (PDAC) from 5 centers located in China. The discovery cohort (n=763), which included preoperative multiphase CECT scans and OS data from 2 centers, was used to construct a fully automated imaging-derived prognostic biomarker-DeepCT-PDAC-by training scalable deep segmentation and prognostic models (via self-learning) to comprehensively model the tumor-anatomy spatial relations and their appearance dynamics in multiphase CECT for OS prediction. The marker was independently tested using internal (n=574) and external validation cohorts (n=179, 3 centers) to evaluate its performance, robustness, and clinical usefulness.

RESULTS

Preoperatively, DeepCT-PDAC was the strongest predictor of OS in both internal and external validation cohorts [hazard ratio (HR) for high versus low risk 2.03, 95% confidence interval (CI): 1.50-2.75; HR: 2.47, CI: 1.35-4.53] in a multivariable analysis. Postoperatively, DeepCT-PDAC remained significant in both cohorts (HR: 2.49, CI: 1.89-3.28; HR: 2.15, CI: 1.14-4.05) after adjustment for potential confounders. For margin-negative patients, adjuvant chemoradiotherapy was associated with improved OS in the subgroup with DeepCT-PDAC low risk (HR: 0.35, CI: 0.19-0.64), but did not affect OS in the subgroup with high risk.

CONCLUSIONS

Deep learning-based CT imaging-derived biomarker enabled the objective and unbiased OS prediction for patients with resectable PDAC. This marker is applicable across hospitals, imaging protocols, and treatments, and has the potential to tailor neoadjuvant and adjuvant treatments at the individual level.

Adjustable extracellular matrix rigidity tumor model for studying stiffness dependent pancreatic ductal adenocarcinomas progression and tumor immunosuppression

Pancreatic ductal adenocarcinomas (PDAC) is one of the stiffest malignancies with strong solid stresses. Increasing stiffness could alter cellular behavior and trigger internal signaling pathways and is strongly associated with a poor prognosis in PDAC. So far, there has been no report on of an experimental model that can rapidly construct and stably maintain a stiffness gradient dimension in both vitro and in vivo. In this study, a gelatin methacryloyl (GelMA)-based hydrogel was designed for in vitro and in vivo PDAC experiments. The GelMA-based hydrogel has porous, adjustable mechanical properties and excellent in vitro and in vivo biocompatibility. The GelMA-based in vitro 3D culture method can effectively form a gradient and stable extracellular matrix stiffness, affecting cell morphology, cytoskeleton remodeling, and malignant biological behaviors such as proliferation and metastasis. This model is suitable for in vivo studies with long-term maintenance of matrix stiffness and no significant toxicity. High matrix stiffness can significantly promote PDAC progression and tumor immunosuppression. This novel adaptive extracellular matrix rigidity tumor model is an excellent candidate for further development as an in vitro and in vivo biomechanical study model of PDAC or other tumors with strong solid stresses.

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

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

CT and MR imaging features of mixed neuroendocrine-non-neuroendocrine neoplasm of the pancreas compared with pancreatic ductal adenocarcinoma and neuroendocrine tumor

OBJECTIVE

This study aimed to assess the computed tomography (CT) and magnetic resonance imaging (MRI) features of pancreatic mixed neuroendocrine-non-neuroendocrine neoplasm (MiNEN) and compare them with those of pancreatic ductal adenocarcinoma (PDAC) and neuroendocrine tumor (NET).

METHODS

Twelve patients with pancreatic MiNEN, 24 patients with PDAC, and 24 patients with NET, who underwent both contrast-enhanced CT and MRI, were included. Clinical data and the key imaging features were retrospectively evaluated by two independent readers and compared between MiNEN and PDAC or NET. Univariate and multivariable logistic regression analyses were performed to obtain predictors for pancreatic MiNEN.

RESULTS

Patients with pancreatic MiNEN more frequently presented with large size and heterogeneous and cystic components compared with PDAC (p < 0.031) and ill-defined irregular margins, progressive enhancement, and adjacent organ involvement compared with NET (p < 0.036). However, vascular invasion was less commonly seen in MiNEN than PDAC (p = 0.010). Moderate enhancement was observed more frequently in MiNEN than in PDAC or NET (p < 0.001). Multivariate logistic analyses demonstrated that moderate enhancement and ill-defined irregular margin were the most valuable features for the prediction of pancreatic MiNEN (p ≤ 0.044). The combination of the two features resulted in a specificity of 93.8%, sensitivity of 83.3%, and accuracy of 91.7%.

CONCLUSIONS

We have mainly described the radiological findings of pancreatic MiNEN with ill-defined irregular margin and moderate enhancement compared with PDAC and NET. The combination of imaging features could improve diagnostic efficiency and help in the selection of the correct treatment method.

Early Diagnosis of Pancreatic Cancer: Clinical Premonitions, Timely Precursor Detection and Increased Curative-Intent Surgery

BACKGROUND

The overall poor prognosis in pancreatic cancer is related to late clinical detection. Early diagnosis remains a considerable challenge in pancreatic cancer. Unfortunately, the onset of clinical symptoms in patients usually indicate advanced disease or presence of metastasis.

ANALYSIS AND RESULTS

Currently, there are no designated diagnostic or screening tests for pancreatic cancer in clinical use. Thus, identifying risk groups, preclinical risk factors or surveillance strategies to facilitate early detection is a target for ongoing research. Hereditary genetic syndromes are a obvious, but small group at risk, and warrants close surveillance as suggested by society guidelines. Screening for pancreatic cancer in asymptomatic individuals is currently associated with the risk of false positive tests and, thus, risk of harms that outweigh benefits. The promise of cancer biomarkers and use of 'omics' technology (genomic, transcriptomics, metabolomics etc.) has yet to see a clinical breakthrough. Several proposed biomarker studies for early cancer detection lack external validation or, when externally validated, have shown considerably lower accuracy than in the original data. Biopsies or tissues are often taken at the time of diagnosis in research studies, hence invalidating the value of a time-dependent lag of the biomarker to detect a pre-clinical, asymptomatic yet operable cancer. New technologies will be essential for early diagnosis, with emerging data from image-based radiomics approaches, artificial intelligence and machine learning suggesting avenues for improved detection.

CONCLUSIONS

Early detection may come from analytics of various body fluids (eg 'liquid biopsies' from blood or urine). In this review we present some the technological platforms that are explored for their ability to detect pancreatic cancer, some of which may eventually change the prospects and outcomes of patients with pancreatic cancer.

Functional biomarkers derived from computed tomography and magnetic resonance imaging differentiate PDAC subgroups and reveal gemcitabine-induced hypo-vascularization

PURPOSE

Pancreatic ductal adenocarcinoma (PDAC) is a molecularly heterogeneous tumor entity with no clinically established imaging biomarkers. We hypothesize that tumor morphology and physiology, including vascularity and perfusion, show variations that can be detected by differences in contrast agent (CA) accumulation measured non-invasively. This work seeks to establish imaging biomarkers for tumor stratification and therapy response monitoring in PDAC, based on this hypothesis.

METHODS AND MATERIALS

Regional CA accumulation in PDAC was correlated with tumor vascularization, stroma content, and tumor cellularity in murine and human subjects. Changes in CA distribution in response to gemcitabine (GEM) were monitored longitudinally with computed tomography (CT) Hounsfield Units ratio (HUr) of tumor to the aorta or with magnetic resonance imaging (MRI) ΔR1 area under the curve at 60 s tumor-to-muscle ratio (AUC60r). Tissue analyses were performed on co-registered samples, including endothelial cell proliferation and cisplatin tissue deposition as a surrogate of chemotherapy delivery.

RESULTS

Tumor cell poor, stroma-rich regions exhibited high CA accumulation both in human (meanHUr 0.64 vs. 0.34, p < 0.001) and mouse PDAC (meanAUC60r 2.0 vs. 1.1, p < 0.001). Compared to the baseline, in vivo CA accumulation decreased specifically in response to GEM treatment in a subset of human (HUr -18%) and mouse (AUC60r -36%) tumors. Ex vivo analyses of mPDAC showed reduced cisplatin delivery (GEM: 0.92 ± 0.5 mg/g, vs. vehicle: 3.1 ± 1.5 mg/g, p = 0.004) and diminished endothelial cell proliferation (GEM: 22.3% vs. vehicle: 30.9%, p = 0.002) upon GEM administration.

CONCLUSION

In PDAC, CA accumulation, which is related to tumor vascularization and perfusion, inversely correlates with tumor cellularity. The standard of care GEM treatment results in decreased CA accumulation, which impedes drug delivery. Further investigation is warranted into potentially detrimental effects of GEM in combinatorial therapy regimens.

The regulatory roles of T helper cells in distinct extracellular matrix characterization in breast cancer

Background

Tumors are characterized by extracellular matrix (ECM) remodeling and stiffening. The ECM has been recognized as an important determinant of breast cancer progression and prognosis. Recent studies have revealed a strong link between ECM remodeling and immune cell infiltration in a variety of tumor types. However, the landscape and specific regulatory mechanisms between ECM and immune microenvironment in breast cancer have not been fully understood.

Methods

Using genomic data and clinical information of breast cancer patients obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases, we conducted an extensive multi-omics analysis to explore the heterogeneity and prognostic significance of the ECM microenvironment. Masson and Sirius red staining were applied to quantify the contents of collagen in the ECM microenvironment. Tissue immunofluorescence (IF) staining was applied to identify T helper (Th) cells.

Results

We classified breast cancer patients into two ECM-clusters and three gene-clusters by consensus clustering. Significant heterogeneity in prognosis and immune cell infiltration have been found in these distinct clusters. Specifically, in the ECM-cluster with better prognosis, the expression levels of Th2 and regulatory T (Treg) cells were reduced, while the Th1, Th17 and T follicular helper (Tfh) cells-associated activities were significantly enhanced. The correlations between ECM characteristics and Th cells infiltration were then validated by clinical tissue samples from our hospital. The ECM-associated prognostic model was then constructed by 10 core prognostic genes and stratified breast cancer patients into two risk groups. Kaplan-Meier analysis showed that the overall survival (OS) of breast cancer patients in the high-risk group was significantly worse than that of the low-risk group. The risk scores for breast cancer patients obtained from our prognostic model were further confirmed to be associated with immune cell infiltration, tumor mutation burden (TMB) and stem cell indexes. Finally, the half-maximal inhibitory concentration (IC50) values of antitumor agents for patients in different risk groups were calculated to provide references for therapy targeting distinct ECM characteristics.

Conclusion

Our findings identify a novel strategy for breast cancer subtyping based on the ECM characterization and reveal the regulatory roles of Th cells in ECM remodeling. Targeting ECM remodeling and Th cells hold potential to be a therapeutic alternative for breast cancer in the future.

Integrated imaging and molecular analysis to decipher tumor microenvironment in the era of immunotherapy

Radiological imaging is an integral component of cancer care, including diagnosis, staging, and treatment response monitoring. It contains rich information about tumor phenotypes that are governed not only by cancer cellintrinsic biological processes but also by the tumor microenvironment, such as the composition and function of tumor-infiltrating immune cells. By analyzing the radiological scans using a quantitative radiomics approach, robust relations between specific imaging and molecular phenotypes can be established. Indeed, a number of studies have demonstrated the feasibility of radiogenomics for predicting intrinsic molecular subtypes and gene expression signatures in breast cancer based on MRI. In parallel, promising results have been shown for inferring the amount of tumor-infiltrating lymphocytes, a key factor for the efficacy of cancer immunotherapy, from standard-of-care radiological images. Compared with the biopsy-based approach, radiogenomics offers a unique avenue to profile the molecular makeup of the tumor and immune microenvironment as well as its evolution in a noninvasive and holistic manner through longitudinal imaging scans. Here, we provide a systematic review of the state of the art radiogenomics studies in the era of immunotherapy and discuss emerging paradigms and opportunities in AI and deep learning approaches. These technical advances are expected to transform the radiogenomics field, leading to the discovery of reliable imaging biomarkers. This will pave the way for their clinical translation to guide precision cancer therapy.

A predictive model for recurrence after upfront surgery in patients with resectable pancreatic ductal adenocarcinoma (PDAC) by using preoperative clinical data and CT characteristics

BACKGROUND

The overall survival for patients with resectable PDAC following curative surgical resection hasn't been improved significantly, as a considerable proportion of patients develop recurrence within a year. The purpose of this study was to develop and validate a predictive model to assess recurrence risk in patients with PDAC after upfront surgery by using preoperative clinical data and CT characteristics.

METHODS

The predictive model was developed based on a retrospective set of 141 pancreatic cancer patients after surgery. A separate set of 77 patients was used to validate model. Between January 2017 and December 2019, all patients underwent multidetector pancreatic CT and upfront surgery. Univariable and multivariate Cox regression was used to determine the risk factors related to recurrence and then establish a nomogram to estimate the 1-year recurrence probability. The Harrell C-index was employed in evaluating the discrimination and calibration of the model.

RESULTS

A total of 218 patients in this retrospective cohort. A recurrence model in nomogram form was developed with predictors including tumor size (hazard ratio [HR], 1.277; 95% CI 1.098, 1.495; P = 0.002), tumor density in the portal vein phase (HR, 0.598; 95% CI 0.424, 0.844; P = 0.003), peripancreatic infiltration (HR, 4.151; 95% CI 2.077, 8.298; P < 0.001), suspicious metastatic lymph node (HR, 2.561; 95% CI 1.653, 3.967; P < 0.001), Neutrophils/Lymphocytes ratio (HR, 1.111; 95% CI 1.016, 1.215; P = 0.020). The predictive nomogram had good discrimination capability with these predictors with an area under curve at 1 year of 0.84 (95%CI 0.77, 0.91) in the development set and 0.82 (95% CI 0.72, 0.92) and 0.84 (95% CI 0.74, 0.94) in the validation set for two radiologists reading respectively.

CONCLUSIONS

The model developed based on preoperative clinical data and CT characteristics of resectable pancreatic ductal adenocarcinoma patients, which can helpfully estimate the recurrence-free survival. It may be a useful tool for clinician to select optimal candidates for upfront surgery or neoadjuvant therapy.

Risk Prediction of Pancreatic Cancer in Patients With Abnormal Morphologic Findings Related to Chronic Pancreatitis: A Machine Learning Approach

BACKGROUND AND AIMS

A significant factor contributing to poor survival in pancreatic cancer is the often late stage at diagnosis. We sought to develop and validate a risk prediction model to facilitate the distinction between chronic pancreatitis-related vs potential early pancreatic ductal adenocarcinoma (PDAC)-associated changes on pancreatic imaging.

METHODS

In this retrospective cohort study, patients aged 18-84 years whose abdominal computed tomography/magnetic resonance imaging reports indicated duct dilatation, atrophy, calcification, cyst, or pseudocyst between January 2008 and November 2019 were identified. The outcome of interest is PDAC in 3 years. More than 100 potential predictors were extracted. Random survival forests approach was used to develop and validate risk models. Multivariable Cox proportional hazard model was applied to estimate the effect of the covariates on the risk of PDAC.

RESULTS

The cohort consisted of 46,041 (mean age 66.4 years). The 3-year incidence rate was 4.0 (95% confidence interval CI 3.6-4.4)/1000 person-years of follow-up. The final models containing age, weight change, duct dilatation, and either alkaline phosphatase or total bilirubin had good discrimination and calibration (c-indices 0.81). Patients with pancreas duct dilatation and at least another morphological feature in the absence of calcification had the highest risk (adjusted hazard ratio [aHR] = 14.15, 95% CI 8.7-22.6), followed by patients with calcification and duct dilatation (aHR = 7.28, 95% CI 4.09-12.96), and patients with duct dilation only (aHR = 6.22, 95% CI 3.86-10.03), compared with patients with calcifications alone as the reference group.

CONCLUSION

The study characterized the risk of pancreatic cancer among patients with 5 abnormal morphologic findings based on radiology reports and demonstrated the ability of prediction algorithms to provide improved risk stratification of pancreatic cancer in these patients.

Imaging Modalities for Early Detection of Pancreatic Cancer: Current State and Future Research Opportunities

Simple Summary

While survival rates for many cancers have improved dramatically over the last 20 years, patients with pancreatic cancer have persistently poor outcomes. The majority of patients with pancreatic cancer are not suitable for potentially curative surgery due to locally advanced or metastatic disease stage at diagnosis. Therefore, early detection would potentially improve survival of pancreatic cancer patients through earlier intervention. Here, we present clinical challenges in the early detection of pancreatic cancer, characterise high risk groups for pancreatic cancer and current screening programs in high-risk individuals. The aim of this scoping review is to investigate the role of both established and novel imaging modalities for early detection of pancreatic cancer. Furthermore, we investigate innovative imaging techniques for early detection of pancreatic cancer, but its widespread application requires further investigation and potentially a combination with other non-invasive biomarkers.

Abstract

Pancreatic cancer, one of the most lethal malignancies, is increasing in incidence. While survival rates for many cancers have improved dramatically over the last 20 years, people with pancreatic cancer have persistently poor outcomes. Potential cure for pancreatic cancer involves surgical resection and adjuvant therapy. However, approximately 85% of patients diagnosed with pancreatic cancer are not suitable for potentially curative therapy due to locally advanced or metastatic disease stage. Because of this stark survival contrast, any improvement in early detection would likely significantly improve survival of patients with pancreatic cancer through earlier intervention. This comprehensive scoping review describes the current evidence on groups at high risk for developing pancreatic cancer, including individuals with inherited predisposition, pancreatic cystic lesions, diabetes, and pancreatitis. We review the current roles of imaging modalities focusing on early detection of pancreatic cancer. Additionally, we propose the use of advanced imaging modalities to identify early, potentially curable pancreatic cancer in high-risk cohorts. We discuss innovative imaging techniques for early detection of pancreatic cancer, but its widespread application requires further investigation and potentially a combination with other non-invasive biomarkers.

Magnetic Resonance Radiomics and Machine-learning Models: An Approach for Evaluating Tumor-stroma Ratio in Patients with Pancreatic Ductal Adenocarcinoma

OBJECTIVE

To develop and validate a magnetic resonance imaging (MRI)-based machine learning classifier for evaluating the tumor-stroma ratio (TSR) in patients with pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

In this retrospective study, 148 patients with PDAC underwent an MR scan and surgical resection. We used hematoxylin and eosin to quantify the TSR. For each patient, we extracted 1,409 radiomics features and reduced them using the least absolute shrinkage and selection operator logistic regression algorithm. The extreme gradient boosting (XGBoost) classifier was developed using a training set comprising 110 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 38 consecutive patients, admitted between January 2018 and April 2018. We determined the performance of the XGBoost classifier based on its discriminative ability, calibration, and clinical utility.

RESULTS

A log-rank test revealed significantly longer survival in the TSR-low group. The prediction model displayed good discrimination in the training (area under the curve [AUC], 0.82) and validation set (AUC, 0.78). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 77.14%, 75.00%, 0.76%, 0.84%, and 0.65%, respectively, those for the validation set were 58.33%, 92.86%, 0.71%, 0.93%, and 0.57%, respectively.

CONCLUSION

We developed an XGBoost classifier based on MRI radiomics features, a non-invasive prediction tool that can evaluate the TSR of patients with PDAC. Moreover, it will provide a basis for interstitial targeted therapy selection and monitoring.

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

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

Inflammation and Myeloid Cells in Cancer Progression and Metastasis

To date, the most immunotherapy drugs act upon T cell surface proteins to promote tumoricidal T cell activity. However, this approach has to date been unsuccessful in certain solid tumor types including pancreatic, prostate cancer and glioblastoma. Myeloid-related innate immunity can promote tumor progression through direct and indirect effects on T cell activity; improved understanding of this field may provide another therapeutic avenue for patients with these tumors. Myeloid cells can differentiate into both pro-inflammatory and anti-inflammatory mature form depending upon the microenvironment. Most cancer type exhibit oncogenic activating point mutations (ex. P53 and KRAS) that trigger cytokines production. In addition, tumor environment (ex. Collagen, Hypoxia, and adenosine) also regulated inflammatory signaling cascade. Both the intrinsic and extrinsic factor driving the tumor immune microenvironment and regulating the differentiation and function of myeloid cells, T cells activity and tumor progression. In this review, we will discuss the relationship between cancer cells and myeloid cells-mediated tumor immune microenvironment to promote cancer progression and immunotherapeutic resistance. Furthermore, we will describe how cytokines and chemokines produced by cancer cells influence myeloid cells within immunosuppressive environment. Finally, we will comment on the development of immunotherapeutic strategies with respect to myeloid-related innate immunity.

NBTXR3, a first-in-class radioenhancer for pancreatic ductal adenocarcinoma: Report of first patient experience

BACKGROUND AND PURPOSE

Pancreatic ductal adenocarcinoma (PDAC) remains one of the leading causes of cancer-related deaths in the world. For patients with PDAC who are not eligible for surgery, radiation therapy improves local disease control, yet safely delivering therapeutic doses of radiation remains challenging due to off-target toxicities in surrounding normal tissues. NBTXR3, a novel radioenhancer composed of functionalized hafnium oxide crystalline nanoparticles, has recently shown clinical activity in soft tissue sarcoma, hepatocellular carcinoma, head and neck squamous cell carcinoma, and advanced solid malignancies with lung or liver metastases. Here we report the first patient with pancreatic cancer treated with NBTXR3.

MATERIALS AND METHODS

A 66-year-old male with unresectable locally advanced PDAC was enrolled on our clinical trial to receive NBTXR3 activated by radiation therapy. Local endoscopic delivery of NBTXR3 was followed by intensity modulated radiation therapy (IMRT). Follow-up assessment consisted of physical examination, laboratory studies including CA19-9, and CT of the chest, abdomen, and pelvis.

RESULTS

The patient received NBTXR3 by local endoscopic delivery without any acute adverse events. Radiation treatment consisted of 45 Gy in 15 daily fractions using IMRT. The patient began radiation twelve days after NBTXR3 injection. Daily CT-on-rails imaging demonstrated retention of NBTXR3 within the tumor for the duration of treatment. At initial follow-up evaluation, the lesion remained radiographically stable and the patient did not demonstrate treatment-related toxicity.

CONCLUSION

This report demonstrates initial feasibility of local endoscopic delivery of NBTXR3 activated by radiation therapy for patients with pancreatic cancer who are not eligible for surgery.

Studying Activated Fibroblast Phenotypes and Fibrosis-Linked Mechanosensing Using 3D Biomimetic Models

Fibrosis and solid tumor progression are closely related, with both involving pathways associated with chronic wound dysregulation. Fibroblasts contribute to extracellular matrix (ECM) remodeling in these processes, a crucial step in scarring, organ failure, and tumor growth, but little is known about the biophysical evolution of remodeling regulation during the development and progression of matrix-related diseases including fibrosis and cancer. A 3D collagen-based scaffold model is employed here to mimic mechanical changes in normal (2 kPa, soft) versus advanced pathological (12 kPa, stiff) tissues. Activated fibroblasts grown on stiff scaffolds show lower migration and increased cell circularity compared to those on soft scaffolds. This is reflected in gene expression profiles, with cells cultured on stiff scaffolds showing upregulated DNA replication, DNA repair, and chromosome organization gene clusters, and a concomitant loss of ability to remodel and deposit ECM. Soft scaffolds can reproduce biophysically meaningful microenvironments to investigate early stage processes in wound healing and tumor niche formation, while stiff scaffolds can mimic advanced fibrotic and cancer stages. These results establish the need for tunable, affordable 3D scaffolds as platforms for aberrant stroma research and reveal the contribution of physiological and pathological microenvironment biomechanics to gene expression changes in the stromal compartment.

PIONEER-Panc: a platform trial for phase II randomized investigations of new and emerging therapies for localized pancreatic cancer

Background

Personalized and effective treatments for pancreatic ductal adenocarcinoma (PDAC) continue to remain elusive. Novel clinical trial designs that enable continual and rapid evaluation of novel therapeutics are needed. Here, we describe a platform clinical trial to address this unmet need.

Methods

This is a phase II study using a Bayesian platform design to evaluate multiple experimental arms against a control arm in patients with PDAC. We first separate patients into three clinical stage groups of localized PDAC (resectable, borderline resectable, and locally advanced disease), and further divide each stage group based on treatment history (treatment naïve or previously treated). The clinical stage and treatment history therefore define 6 different cohorts, and each cohort has one control arm but may have one or more experimental arms running simultaneously. Within each cohort, adaptive randomization rules are applied and patients will be randomized to either an experimental arm or the control arm accordingly. The experimental arm(s) of each cohort are only compared to the applicable cohort specific control arm. Experimental arms may be added independently to one or more cohorts during the study. Multiple correlative studies for tissue, blood, and imaging are also incorporated.

Discussion

To date, PDAC has been treated as a single disease, despite knowledge that there is substantial heterogeneity in disease presentation and biology. It is recognized that the current approach of single arm phase II trials and traditional phase III randomized studies are not well-suited for more personalized treatment strategies in PDAC. The PIONEER Panc platform clinical trial is designed to overcome these challenges and help advance our treatment strategies for this deadly disease.

Trial registration

This study is approved by the Institutional Review Board (IRB) of MD Anderson Cancer Center, IRB-approved protocol 2020-0075. The PIONEER trial is registered at the US National Institutes of Health (ClinicalTrials.gov) NCT04481204.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-09095-7.

Enhancing carrier flux for efficient drug delivery in cancer tissues

Ultrasound focused toward tumors in the presence of circulating microbubbles improves the delivery of drug-loaded nanoparticles and therapeutic outcomes; however, the efficacy varies among the different properties and conditions of the tumors. Therefore, there is a need to optimize the ultrasound parameters and determine the properties of the tumor tissue important for the successful delivery of nanoparticles. Here, we propose a mesoscopic model considering the presence of entropic forces to explain the ultrasound-enhanced transport of nanoparticles across the capillary wall and through the interstitium of tumors. The nanoparticles move through channels of variable shape whose irregularities can be assimilated to barriers of entropic nature that the nanoparticles must overcome to reach their targets. The model assumes that focused ultrasound and circulating microbubbles cause the capillary wall to oscillate, thereby changing the width of transcapillary and interstitial channels. Our analysis provides values for the penetration distances of nanoparticles into the interstitium that are in agreement with experimental results. We found that the penetration increased significantly with increasing acoustic intensity as well as tissue elasticity, which means softer and more deformable tissue (Young modulus lower than 50 kPa), whereas porosity of the tissue and pulse repetition frequency of the ultrasound had less impact on the penetration length. We also considered that nanoparticles can be absorbed into cells and to extracellular matrix constituents, finding that the penetration length is increased when there is a low absorbance coefficient of the nanoparticles compared with their diffusion coefficient (close to 0.2). The model can be used to predict which tumor types, in terms of elasticity, will successfully deliver nanoparticles into the interstitium. It can also be used to predict the penetration distance into the interstitium of nanoparticles with various sizes and the ultrasound intensity needed for the efficient distribution of the nanoparticles.

CT Radiomic Features of Superior Mesenteric Artery Involvement in Pancreatic Ductal Adenocarcinoma: A Pilot Study

Background Current imaging methods for prediction of complete margin resection (R0) in patients with pancreatic ductal adenocarcinoma (PDAC) are not reliable. Purpose To investigate whether tumor-related and perivascular CT radiomic features improve preoperative assessment of arterial involvement in patients with surgically proven PDAC. Materials and Methods This retrospective study included consecutive patients with PDAC who underwent surgery after preoperative CT between 2012 and 2019. A three-dimensional segmentation of PDAC and perivascular tissue surrounding the superior mesenteric artery (SMA) was performed on preoperative CT images with radiomic features extracted to characterize morphology, intensity, texture, and task-based spatial information. The reference standard was the pathologic SMA margin status of the surgical sample: SMA involved (tumor cells ≤1 mm from margin) versus SMA not involved (tumor cells >1 mm from margin). The preoperative assessment of SMA involvement by a fellowship-trained radiologist in multidisciplinary consensus was the comparison. High reproducibility (intraclass correlation coefficient, 0.7) and the Kolmogorov-Smirnov test were used to select features included in the logistic regression model. Results A total of 194 patients (median age, 66 years; interquartile range, 60-71 years; age range, 36-85 years; 99 men) were evaluated. Aside from surgery, 148 patients underwent neoadjuvant therapy. A total of 141 patients' samples did not involve SMA, whereas 53 involved SMA. A total of 1695 CT radiomic features were extracted. The model with five features (maximum hugging angle, maximum diameter, logarithm robust mean absolute deviation, minimum distance, square gray level co-occurrence matrix correlation) showed a better performance compared with the radiologist assessment (model vs radiologist area under the curve, 0.71 [95% CI: 0.62, 0.79] vs 0.54 [95% CI: 0.50, 0.59]; P < .001). The model showed a sensitivity of 62% (33 of 53 patients) (95% CI: 51, 77) and a specificity of 77% (108 of 141 patients) (95% CI: 60, 84). Conclusion A model based on tumor-related and perivascular CT radiomic features improved the detection of superior mesenteric artery involvement in patients with pancreatic ductal adenocarcinoma. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Do and Kambadakone in this issue.

CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma

Purpose

To develop and validate a machine learning classifier based on multidetector computed tomography (MDCT), for the preoperative prediction of tumor-stroma ratio (TSR) expression in patients with pancreatic ductal adenocarcinoma (PDAC).

Materials and Methods

In this retrospective study, 227 patients with PDAC underwent an MDCT scan and surgical resection. We quantified the TSR by using hematoxylin and eosin staining and extracted 1409 arterial and portal venous phase radiomics features for each patient, respectively. Moreover, we used the least absolute shrinkage and selection operator logistic regression algorithm to reduce the features. The extreme gradient boosting (XGBoost) was developed using a training set consisting of 167 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 60 consecutive patients, admitted between January 2018 and April 2018. We determined the XGBoost classifier performance based on its discriminative ability, calibration, and clinical utility.

Results

We observed low and high TSR in 91 (40.09%) and 136 (59.91%) patients, respectively. A log-rank test revealed significantly longer survival for patients in the TSR-low group than those in the TSR-high group. The prediction model revealed good discrimination in the training (area under the curve [AUC]= 0.93) and moderate discrimination in the validation set (AUC= 0.63). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 94.06%, 81.82%, 0.89, 0.89, and 0.90, respectively, those for the validation set were 85.71%, 48.00%, 0.70, 0.70, and 0.71, respectively.

Conclusions

The CT radiomics-based XGBoost classifier provides a potentially valuable noninvasive tool to predict TSR in patients with PDAC and optimize risk stratification.

The PDAC Extracellular Matrix: A Review of the ECM Protein Composition, Tumor Cell Interaction, and Therapeutic Strategies

Pancreatic ductal adenocarcinoma (PDAC) is notorious for a dense fibrotic stroma that is interlaced with a collagen-based extracellular matrix (ECM) that plays an important role in tumor biology. Traditionally thought to only provide a physical barrier from host responses and systemic chemotherapy, new studies have demonstrated that the ECM maintains biomechanical and biochemical properties of the tumor microenvironment (TME) and restrains tumor growth. Recent studies have shown that the ECM augments tumor stiffness, interstitial fluid pressure, cell-to-cell junctions, and microvascularity using a mix of biomechanical and biochemical signals to influence tumor fate for better or worse. In addition, PDAC tumors have been shown to use ECM-derived peptide fragments as a nutrient source in nutrient-poor conditions. While collagens are the most abundant proteins found in the ECM, several studies have identified growth factors, integrins, glycoproteins, and proteoglycans in the ECM. This review focuses on the dichotomous nature of the PDAC ECM, the types of collagens and other proteins found in the ECM, and therapeutic strategies targeting the PDAC ECM.

DeepPrognosis: Preoperative prediction of pancreatic cancer survival and surgical margin via comprehensive understanding of dynamic contrast-enhanced CT imaging and tumor-vascular contact parsing

Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers and carries a dismal prognosis of ∼10% in five year survival rate. Surgery remains the best option of a potential cure for patients who are evaluated to be eligible for initial resection of PDAC. However, outcomes vary significantly even among the resected patients who were the same cancer stage and received similar treatments. Accurate quantitative preoperative prediction of primary resectable PDACs for personalized cancer treatment is thus highly desired. Nevertheless, there are a very few automated methods yet to fully exploit the contrast-enhanced computed tomography (CE-CT) imaging for PDAC prognosis assessment. CE-CT plays a critical role in PDAC staging and resectability evaluation. In this work, we propose a novel deep neural network model for the survival prediction of primary resectable PDAC patients, named as 3D Contrast-Enhanced Convolutional Long Short-Term Memory network (CE-ConvLSTM), which can derive the tumor attenuation signatures or patterns from patient CE-CT imaging studies. Tumor-vascular relationships, which might indicate the resection margin status, have also been proven to hold strong relationships with the overall survival of PDAC patients. To capture such relationships, we propose a self-learning approach for automated pancreas and peripancreatic anatomy segmentation without requiring any annotations on our PDAC datasets. We then employ a multi-task convolutional neural network (CNN) to accomplish both tasks of survival outcome and margin prediction where the network benefits from learning the resection margin related image features to improve the survival prediction. Our presented framework can improve overall survival prediction performances compared with existing state-of-the-art survival analysis approaches. The new staging biomarker integrating both the proposed risk signature and margin prediction has evidently added values to be combined with the current clinical staging system.

Global Phosphoproteomics Reveal CDK Suppression as a Vulnerability to KRas Addiction in Pancreatic Cancer

PURPOSE

Among human cancers that harbor mutant (mt) KRas, some, but not all, are dependent on mt KRas. However, little is known about what drives KRas dependency.

EXPERIMENTAL DESIGN

Global phosphoproteomics, screening of a chemical library of FDA drugs, and genome-wide CRISPR/Cas9 viability database analysis were used to identify vulnerabilities of KRas dependency.

RESULTS

Global phosphoproteomics revealed that KRas dependency is driven by a cyclin-dependent kinase (CDK) network. CRISPR/Cas9 viability database analysis revealed that, in mt KRas-driven pancreatic cancer cells, knocking out the cell-cycle regulators CDK1 or CDK2 or the transcriptional regulators CDK7 or CDK9 was as effective as knocking out KRas. Furthermore, screening of a library of FDA drugs identified AT7519, a CDK1, 2, 7, and 9 inhibitor, as a potent inducer of apoptosis in mt KRas-dependent, but not in mt KRas-independent, human cancer cells. In vivo AT7519 inhibited the phosphorylation of CDK1, 2, 7, and 9 substrates and suppressed growth of xenografts from 5 patients with pancreatic cancer. AT7519 also abrogated mt KRas and mt p53 primary and metastatic pancreatic cancer in three-dimensional (3D) organoids from 2 patients, 3D cocultures from 8 patients, and mouse 3D organoids from pancreatic intraepithelial neoplasia, primary, and metastatic tumors.

CONCLUSIONS

A link between CDK hyperactivation and mt KRas dependency was uncovered and pharmacologically exploited to abrogate mt KRas-driven pancreatic cancer in highly relevant models, warranting clinical investigations of AT7519 in patients with pancreatic cancer.

Artificial intelligence for early detection of pancreatic adenocarcinoma: The future is promising

Pancreatic ductal adenocarcinoma (PDAC) is a worldwide public health concern. Despite extensive research efforts toward improving diagnosis and treatment, the 5-year survival rate at best is approximately 15%. This dismal figure can be attributed to a variety of factors including lack of adequate screening methods, late symptom onset, and treatment resistance. Pancreatic ductal adenocarcinoma remains a grim diagnosis with a high mortality rate and a significant psy-chological burden for patients and their families. In recent years artificial intelligence (AI) has permeated the medical field at an accelerated pace, bringing potential new tools that carry the promise of improving diagnosis and treatment of a variety of diseases. In this review we will summarize the landscape of AI in diagnosis and treatment of PDAC.

The Biological Meaning of Radiomic Features

An earlier incorrect version appeared online. This article was corrected on February 10, 2021.

Radiotherapy for Resectable and Borderline Resectable Pancreas Cancer: When and Why?

The role of (chemo) radiation in the perioperative management of patients with resectable and borderline resectable pancreatic ductal adenocarcinoma is controversial. Herein, we review and interpret existing data relating to the ability of (chemo) radiation to "downstage" pancreatic tumors, delay recurrence, and prolong patients' survival. In sum, the evidence suggests that while neoadjuvant (chemo) radiation may impact pathologic metrics favorably, it rarely converts anatomically unresectable tumors to resectable ones. And while data do support the ability of (chemo)radiation to delay cancer progression, its ability to prolong longevity has not been confirmed. It is possible that (chemo)radiation is effective in prolonging the survival of select patients, but to date, this cohort remains undefined due to heterogeneity in both the populations studied and the regimens used to treat them. Based on our interpretation of existing data, we currently administer neoadjuvant and adjuvant (chemo)radiation selectively to patients with localized pancreatic cancer who we consider at highest risk for local progression. We may also use it as an alternative to pancreatectomy in patients who are poor candidates for surgery. Ultimately, the role of (chemo)radiation in these settings is evolving. Better studies of patients most likely to benefit from its local effects are necessary to clearly define its place within the perioperative treatment algorithms used for patients with localized pancreatic cancer.

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

ABSTRACT

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

A Mathematical Model to Estimate Chemotherapy Concentration at the Tumor-Site and Predict Therapy Response in Colorectal Cancer Patients with Liver Metastases

Simple Summary

It is known that drug transport barriers in the tumor determine drug concentration at the tumor site, causing disparity from the systemic (plasma) drug concentration. However, current clinical standard of care still bases dosage and treatment optimization on the systemic concentration of drugs. Here, we present a proof of concept observational cohort study to accurately estimate drug concentration at the tumor site from mathematical modeling using biologic, clinical, and imaging/perfusion data, and correlate it with outcome in colorectal cancer liver metastases. We demonstrate that drug concentration at the tumor site, not in systemic circulation, can be used as a credible biomarker for predicting chemotherapy outcome, and thus our mathematical modeling approach can be applied prospectively in the clinic to personalize treatment design to optimize outcome.

Abstract

Chemotherapy remains a primary treatment for metastatic cancer, with tumor response being the benchmark outcome marker. However, therapeutic response in cancer is unpredictable due to heterogeneity in drug delivery from systemic circulation to solid tumors. In this proof-of-concept study, we evaluated chemotherapy concentration at the tumor-site and its association with therapy response by applying a mathematical model. By using pre-treatment imaging, clinical and biologic variables, and chemotherapy regimen to inform the model, we estimated tumor-site chemotherapy concentration in patients with colorectal cancer liver metastases, who received treatment prior to surgical hepatic resection with curative-intent. The differential response to therapy in resected specimens, measured with the gold-standard Tumor Regression Grade (TRG; from 1, complete response to 5, no response) was examined, relative to the model predicted systemic and tumor-site chemotherapy concentrations. We found that the average calculated plasma concentration of the cytotoxic drug was essentially equivalent across patients exhibiting different TRGs, while the estimated tumor-site chemotherapeutic concentration (eTSCC) showed a quadratic decline from TRG = 1 to TRG = 5 (p < 0.001). The eTSCC was significantly lower than the observed plasma concentration and dropped by a factor of ~5 between patients with complete response (TRG = 1) and those with no response (TRG = 5), while the plasma concentration remained stable across TRG groups. TRG variations were driven and predicted by differences in tumor perfusion and eTSCC. If confirmed in carefully planned prospective studies, these findings will form the basis of a paradigm shift in the care of patients with potentially curable colorectal cancer and liver metastases.

Radiomics signature of brain metastasis: prediction of EGFR mutation status

OBJECTIVES

To predict epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma using MR-based radiomics signature of brain metastasis and explore the optimal MR sequence for prediction.

METHODS

Data from 52 patients with brain metastasis from lung adenocarcinoma (28 with mutant EGFR, 24 with wild-type EGFR) were retrospectively reviewed. Contrast-enhanced T1-weighted imaging (T1-CE), T2 fluid-attenuated inversion recovery (T2-FLAIR), T2WI, and DWI sequences were selected for radiomics features extraction. A total of 438 radiomics features were extracted from each MR sequence. All sequences were randomly divided into training and validation cohorts. The least absolute shrinkage selection operator was used to select informative features, a radiomics signature was built with the logistic regression model of the training cohort, and the radiomics signature performance was evaluated using the validation cohort and an independent testing data set.

RESULTS

The radiomics signature built on 9 selected features showed good discrimination in both the training and validation cohorts for T2-FLAIR. The radiomics signature of T2-FLAIR yielded an AUC of 0.987, a classification accuracy of 0.991, sensitivity of 1.000, and specificity of 0.980 in the validation cohort. The AUC was 0.871 in the independent testing data set. The AUCs of our radiomics signature to differentiate exon 19 and exon 21 mutations were 0.529, 0.580, 0.645, and 0.406 for T1-CE, T2-FLAIR, T2WI, and DWI, respectively.

CONCLUSIONS

We developed a T2-FLAIR radiomics signature that can be used as a noninvasive auxiliary tool for predicting EGFR mutation status in lung adenocarcinoma, which is helpful to guide therapeutic strategies.

KEY POINTS

• MR-based radiomics signature of brain metastasis may help predict EGFR mutation status in lung adenocarcinoma, especially using T2-FLAIR. • Nine radiomics features extracted from T2-FLAIR sequence strongly correlate with EGFR mutation status. • Radiomics features reflect tumor heterogeneity through potential changes in tissue morphology caused by EGFR mutation.

A mathematical model for the quantification of a patient's sensitivity to checkpoint inhibitors and long-term tumour burden

A large proportion of patients with cancer are unresponsive to treatment with immune checkpoint blockade and other immunotherapies. Here, we report a mathematical model of the time-course of tumour responses to immune-checkpoint inhibitors. The model takes into account intrinsic tumour-growth rates, the rates of immune activation and of tumour–immune-cell interactions, and the efficacy of immune-mediated tumour killing. For 124 patients, four cancer types and two immunotherapy agents, the model reliably described the immune responses and final tumour burden across all different cancers and drug combinations examined. In validation cohorts from four clinical trials of checkpoint inhibitors (with a total of 177 patients), the model accurately stratified the patients according to reduced or increased long-term tumour burden. We also provide model-derived quantitative measures of treatment sensitivity for specific drug–cancer combinations. The model can be used to predict responses to therapy and to quantify specific drug–cancer sensitivities in individual patients.

Clinicopathological correlation of radiologic measurement of post-therapy tumor size and tumor volume for pancreatic ductal adenocarcinoma

OBJECTIVES

Tumor size measurement is critical for accurate tumor staging in patients with pancreatic ductal adenocarcinoma (PDAC). However, accurate tumor size measurement is challenging in patients who received neoadjuvant therapy before resection, due to treatment-induced fibrosis and tumor invasion beyond the grossly identified tumor area. In this study, we evaluated the correlation between the tumor size and tumor volume measured on post-therapy computed tomography (CT) scans and the pathological measurement. Also, we investigated the correlation between these measurements and clinicopathological parameters and survival.

MATERIALS AND METHODS

Retrospectively, we evaluated 343 patients with PDAC who received neoadjuvant therapy, followed by pancreaticoduodenectomy and had pre-operative pancreatic protocol CT imaging. We measured the longest tumor diameter (RadL) and the radiological tumor volume (RadV) on the post-therapy CT scan, then we categorized RadL into four radiologic tumor stages (RTS) based on the current AJCC staging (8th edition) protocol and RadV based on the median. Pearson correlation or Spearman's coefficient (δ), T-test and ANOVA was used to test the correlation between the radiological and pathological measurement. Chi-square analysis was used to test the correlation with the tumor pathological response, lymph-node metastasis and margin status and Kaplan-Meier and Cox-proportional hazard for survival analysis. P-value < 0.05 was considered significant.

RESULTS

As a continuous variable, RadL showed a positive linear correlation with the post-therapy pathologic tumor size in the overall patient population (Pearson correlation coefficient: 0.72, P < 0.001) and RadV (δ: 0.63, p < 0.0001). However, there was no correlation between RadL and pathologic tumor size in patients with ypT0 and those with pathologic tumor size of ≤1.0 cm. Post-therapy RTS and RadV group correlated with ypT stage, tumor response grades using either CAP or MDA grading system, distance of superior mesenteric artery margin and tumor recurrence/metastasis.

CONCLUSION

Although RadL tends to understage ypT in PDAC patients who had no radiologically detectable tumor or small tumors (RTS0 or RTS1), radiologic measurement of post-therapy tumor size may be used as a marker for the pathologic tumor staging and tumor response to neoadjuvant therapy.

Predictive Modeling for Voxel-Based Quantification of Imaging-Based Subtypes of Pancreatic Ductal Adenocarcinoma (PDAC): A Multi-Institutional Study

Previously, we characterized qualitative imaging-based subtypes of pancreatic ductal adenocarcinoma (PDAC) on computed tomography (CT) scans. Conspicuous (high delta) PDAC tumors are more likely to have aggressive biology and poorer clinical outcomes compared to inconspicuous (low delta) tumors. Here, we developed a quantitative classification of this imaging-based subtype (quantitative delta; q-delta). Retrospectively, baseline pancreatic protocol CT scans of three cohorts (cohort#1 = 101, cohort#2 = 90 and cohort#3 = 16 [external validation]) of patients with PDAC were qualitatively classified into high and low delta. We used a voxel-based method to volumetrically quantify tumor enhancement while referencing normal-pancreatic-parenchyma and used machine learning-based analysis to build a predictive model. In addition, we quantified the stromal content using hematoxylin- and eosin-stained treatment-naïve PDAC sections. Analyses revealed that PDAC quantitative enhancement values are predictive of the qualitative delta scoring and were used to build a classification model (q-delta). Compared to high q-delta, low q-delta tumors were associated with improved outcomes, and the q-delta class was an independent prognostic factor for survival. In addition, low q-delta tumors had higher stromal content and lower cellularity compared to high q-delta tumors. Our results suggest that q-delta classification provides a clinically and biologically relevant tool that may be integrated into ongoing and future clinical trials.

Imaging-Based Subtypes of Pancreatic Ductal Adenocarcinoma Exhibit Differential Growth and Metabolic Patterns in the Pre-Diagnostic Period: Implications for Early Detection

BACKGROUND

Previously, we characterized subtypes of pancreatic ductal adenocarcinoma (PDAC) on computed-tomography (CT) scans, whereby conspicuous (high delta) PDAC tumors are more likely to have aggressive biology and poorer clinical outcomes compared to inconspicuous (low delta) tumors. Here, we hypothesized that these imaging-based subtypes would exhibit different growth-rates and distinctive metabolic effects in the period prior to PDAC diagnosis.

MATERIALS AND METHODS

Retrospectively, we evaluated 55 patients who developed PDAC as a second primary cancer and underwent serial pre-diagnostic (T0) and diagnostic (T1) CT-scans. We scored the PDAC tumors into high and low delta on T1 and, serially, obtained the biaxial measurements of the pancreatic lesions (T0-T1). We used the Gompertz-function to model the growth-kinetics and estimate the tumor growth-rate constant (α) which was used for tumor binary classification, followed by cross-validation of the classifier accuracy. We used maximum-likelihood estimation to estimate initiation-time from a single cell (10^-6 mm³) to a 10 mm³ tumor mass. Finally, we serially quantified the subcutaneous-abdominal-fat (SAF), visceral-abdominal-fat (VAF), and muscles volumes (cm³) on CT-scans, and recorded the change in blood glucose (BG) levels. T-test, likelihood-ratio, Cox proportional-hazards, and Kaplan-Meier were used for statistical analysis and p-value <0.05 was considered significant.

RESULTS

Compared to high delta tumors, low delta tumors had significantly slower average growth-rate constants (0.024 month^-1 vs. 0.088 month^-1, p<0.0001) and longer average initiation-times (14 years vs. 5 years, p<0.0001). α demonstrated high accuracy (area under the curve (AUC)=0.85) in classifying the tumors into high and low delta, with an optimal cut-off of 0.034 month^-1. Leave-one-out-cross-validation showed 80% accuracy in predicting the delta-class (AUC=0.84). High delta tumors exhibited accelerated SAF, VAF, and muscle wasting (p <0.001), and BG disturbance (p<0.01) compared to low delta tumors. Patients with low delta tumors had better PDAC-specific progression-free survival (log-rank, p<0.0001), earlier stage tumors (p=0.005), and higher likelihood to receive resection after PDAC diagnosis (p=0.008), compared to those with high delta tumors.

CONCLUSION

Imaging-based subtypes of PDAC exhibit distinct growth, metabolic, and clinical profiles during the pre-diagnostic period. Our results suggest that heterogeneous disease biology may be an important consideration in early detection strategies for PDAC.

Therapeutic response assessment in pancreatic ductal adenocarcinoma: society of abdominal radiology review paper on the role of morphological and functional imaging techniques

Pancreatic ductal adenocarcinoma (PDA) is the third leading cause of cancer-related death in the United States and is projected to be the second by 2030. Systemic combination chemotherapy is considered an essential first-line treatment for the majority of patients with PDA, in both the neoadjuvant and palliative settings. In addition, a number of novel therapies are being tested in clinical trials for patients with advanced PDA. In all cases, accurate and timely assessment of treatment response is critical to guide therapy, reduce drug toxicities and cost from a failing therapy, and aid adaptive clinical trials. Conventional morphological imaging has significant limitations, especially in the context of determining primary tumor response and resectability following neoadjuvant therapies. In this article, we provide an overview of current therapy options for PDA, highlight several morphological imaging findings that may be helpful to reduce over-staging following neoadjuvant therapy, and discuss a number of emerging imaging, and non-imaging, tools that have shown promise in providing a more precise quantification of disease burden and treatment response in PDA.

Radiomics Improves Cancer Screening and Early Detection

Imaging is a key technology in the early detection of cancers, including X-ray mammography, low-dose CT for lung cancer, or optical imaging for skin, esophageal, or colorectal cancers. Historically, imaging information in early detection schema was assessed qualitatively. However, the last decade has seen increased development of computerized tools that convert images into quantitative mineable data (radiomics), and their subsequent analyses with artificial intelligence (AI). These tools are improving diagnostic accuracy of early lesions to define risk and classify malignant/aggressive from benign/indolent disease. The first section of this review will briefly describe the various imaging modalities and their use as primary or secondary screens in an early detection pipeline. The second section will describe specific use cases to illustrate the breadth of imaging modalities as well as the benefits of quantitative image analytics. These will include optical (skin cancer), X-ray CT (pancreatic and lung cancer), X-ray mammography (breast cancer), multiparametric MRI (breast and prostate cancer), PET (pancreatic cancer), and ultrasound elastography (liver cancer). Finally, we will discuss the inexorable improvements in radiomics to build more robust classifier models and the significant limitations to this development, including access to well-annotated databases, and biological descriptors of the imaged feature data.See all articles in this CEBP Focus section, "NCI Early Detection Research Network: Making Cancer Detection Possible."