scholarly journals Multiparametric Modelling of Survival in Pancreatic Ductal Adenocarcinoma Using Clinical, Histomorphological, Genetic and Image-Derived Parameters

2020 ◽  
Vol 9 (5) ◽  
pp. 1250
Author(s):  
Georgios A. Kaissis ◽  
Friederike Jungmann ◽  
Sebastian Ziegelmayer ◽  
Fabian K. Lohöfer ◽  
Felix N. Harder ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Molecular Subtype ◽  
Cox Proportional Hazards ◽  
Ductal Adenocarcinoma ◽  
Imaging Biomarkers ◽  
Lymph Node Status ◽  
Survival Prediction ◽  
Imaging Features ◽  
True Value

Rationale: Pancreatic ductal adenocarcinoma (PDAC) remains a tumor entity of exceptionally poor prognosis, and several biomarkers are under current investigation for the prediction of patient prognosis. Many studies focus on promoting newly developed imaging biomarkers without a rigorous comparison to other established parameters. To assess the true value and leverage the potential of all efforts in this field, a multi-parametric evaluation of the available biomarkers for PDAC survival prediction is warranted. Here we present a multiparametric analysis to assess the predictive value of established parameters and the added contribution of newly developed imaging features such as biomarkers for overall PDAC patient survival. Methods: 103 patients with resectable PDAC were retrospectively enrolled. Clinical and histopathological data (age, sex, chemotherapy regimens, tumor size, lymph node status, grading and resection status), morpho-molecular and genetic data (tumor morphology, molecular subtype, tp53, kras, smad4 and p16 genetics), image-derived features and the combination of all parameters were tested for their prognostic strength based on the concordance index (CI) of multivariate Cox proportional hazards survival modelling after unsupervised machine learning preprocessing. Results: The average CIs of the out-of-sample data were: 0.63 for the clinical and histopathological features, 0.53 for the morpho-molecular and genetic features, 0.65 for the imaging features and 0.65 for the combined model including all parameters. Conclusions: Imaging-derived features represent an independent survival predictor in PDAC and enable the multiparametric, machine learning-assisted modelling of postoperative overall survival with a high performance compared to clinical and morpho-molecular/genetic parameters. We propose that future studies systematically include imaging-derived features to benchmark their additive value when evaluating biomarker-based model performance.

scholarly journals Image-Based Molecular Phenotyping of Pancreatic Ductal Adenocarcinoma

2020 ◽  
Vol 9 (3) ◽  
pp. 724 ◽  
Author(s):  
Georgios A. Kaissis ◽  
Sebastian Ziegelmayer ◽  
Fabian K. Lohöfer ◽  
Felix N. Harder ◽  
Friederike Jungmann ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Learning Algorithm ◽  
Molecular Subtype ◽  
Characteristic Curve ◽  
Ductal Adenocarcinoma ◽  
Rank Test ◽  
Learning Approaches ◽  
Imaging Data ◽  
Log Rank Test

To bridge the translational gap between recent discoveries of distinct molecular phenotypes of pancreatic cancer and tangible improvements in patient outcome, there is an urgent need to develop strategies and tools informing and improving the clinical decision process. Radiomics and machine learning approaches can offer non-invasive whole tumor analytics for clinical imaging data-based classification. The retrospective study assessed baseline computed tomography (CT) from 207 patients with proven pancreatic ductal adenocarcinoma (PDAC). Following expert level manual annotation, Pyradiomics was used for the extraction of 1474 radiomic features. The molecular tumor subtype was defined by immunohistochemical staining for KRT81 and HNF1a as quasi-mesenchymal (QM) vs. non-quasi-mesenchymal (non-QM). A Random Forest machine learning algorithm was developed to predict the molecular subtype from the radiomic features. The algorithm was then applied to an independent cohort of histopathologically unclassifiable tumors with distinct clinical outcomes. The classification algorithm achieved a sensitivity, specificity and ROC-AUC (area under the receiver operating characteristic curve) of 0.84 ± 0.05, 0.92 ± 0.01 and 0.93 ± 0.01, respectively. The median overall survival for predicted QM and non-QM tumors was 16.1 and 20.9 months, respectively, log-rank-test p = 0.02, harzard ratio (HR) 1.59. The application of the algorithm to histopathologically unclassifiable tumors revealed two groups with significantly different survival (8.9 and 39.8 months, log-rank-test p < 0.001, HR 4.33). The machine learning-based analysis of preoperative (CT) imaging allows the prediction of molecular PDAC subtypes highly relevant for patient survival, allowing advanced pre-operative patient stratification for precision medicine applications.

Characterization of undiagnosed pancreatic ductal adenocarcinoma on CT scans.

2021 ◽  
Vol 39 (3_suppl) ◽  
pp. 380-380
Author(s):  
John Chang ◽  
Madelyn Bartels ◽  
Kelsey Beyer ◽  
Ashley Maitland ◽  
Richard Taft Peterson ◽  
...  
Keyword(s):  
Pancreatic Ductal Adenocarcinoma ◽  
The Body ◽  
Ct Scans ◽  
Ductal Adenocarcinoma ◽  
Imaging Features ◽  
Cognitive Errors ◽  
Radiologic Findings ◽  
Stage 1 ◽  
Improved Technology ◽  
Radiologic Features

380 Background: Pancreatic ductal adenocarcinoma (PDAC) is the third leading cause of cancer-related deaths. At present, the best 5-year survival is 25% for resectable PDAC. For small (1 cm) stage 1 PDAC, resection has resulted in much better survival. The goal of this study was to evaluate the appearance and location of early undiagnosed PDAC on computed tomography scans (CT) prior to diagnosis with the goal of minimizing missing early PDAC. We also categorize the errors as either perceptive or cognitive. Methods: PDAC cases were retrospectively reviewed from 1/1/2012 through 12/31/2018 from our tumor registry, identifying 81 cases with paired CT scans both at the time of and prior to diagnosis. Among these, 31 contained imaging features considered diagnostic or suspicious for early PDAC(38%). These “errors” were classified by radiologic features and as well as by location. In addition, errors were classified into “perceptive errors" when the first study was read as normal, and as “cognitive errors” when the report noted an abnormality but failed to note suspicion for malignancy. Results: Among the 31 undiagnosed PDAC, 18 had features of an identifiable mass (58%), 9 had pancreatic ductal dilatation (29%), and 4 had evidence of perivascular soft tissue (13%). 44% of undiagnosed tumors were located in the head-neck, 39% in the body, and 17% in the tail. Perceptive errors were found in 58% and 42% were cognitive. No significant differences were seen between perceptive and cognitive errors based on suspicious features. Conclusions: Radiologic findings of early PDAC was retrospectively evident in more than one third of cases in which prior imaging was performed. These findings are most often masses or ductal dilatation. Location of these undiagnosed tumors were distributed throughout the gland. This study identifies the radiologic features of undiagnosed PDAC which may provide an opportunity for future prospective studies and improved technology which may improve early detection of pancreatic cancer.

Discovery and validation of a quantitative, stromal-associated imaging biomarker of pancreatic ductal adenocarcinoma (PDAC).

2018 ◽  
Vol 36 (4_suppl) ◽  
pp. 228-228 ◽  
Author(s):  
Mohamed Zaid ◽  
Baishali Chaudhury ◽  
Gauri R. Varadhachary ◽  
Matthew H. G. Katz ◽  
Joseph M. Herman ◽  
...  
Keyword(s):  
Pancreatic Ductal Adenocarcinoma ◽  
Proportional Hazards ◽  
Quantitative Imaging ◽  
Tumor Biology ◽  
Continuous Variable ◽  
Cox Proportional Hazards ◽  
Imaging Biomarker ◽  
Ductal Adenocarcinoma ◽  
Arterial Phase ◽  
Treatment Naïve

228 Background: As pancreatic ductal adenocarcinoma (PDAC) remains highly lethal, biomarkers are needed to identify patients who may benefit from specific therapeutic strategies. We previously described a qualitative computed tomography (CT) based biomarker - delta classification, whereby high delta tumors showed lower stromal content, more aggressive biology and poorer outcomes, than their counterparts. Here, we describe a quantitative method to differentiate these patients and predict outcomes. Methods: We retrospectively identified 101 treatment naïve patients who underwent pancreatectomy as a discovery cohort and 90 patients who underwent preoperative gemcitabine-based chemoradiation for validation. All patients underwent a pre-therapy pancreatic protocol CT and were classified as high or low delta, as described before. We semi-automatically segmented the tumors, chose normal pancreatic (NP) tissue and abdominal fat as references, then measured relative enhancement values using Philips IntelliSpace8 multimodality tumor tracking. We then analyzed the arterial and portal-venous phases separately using ROC and cox proportional hazards. Results: Delta class significantly associated with normalized enhancement values (NEV) in the arterial phase referenced to NP (P<0.0001, AUC =90%). A cutoff of 0.72 was identified that also distinguished high and low delta groups in the validation cohort (P<0.0001). As a continuous variable, the NEV was associated with distant metastasis free survival (DMFS) and overall survival (OS) on uni and multivariate analyses, accounting for traditional survival covariates. Using cutoff of 0.72, patients with high NEV had longer median OS (39 and 35.9 months) compared to those with low NEV (17.5 and 17.6 months, P=<0.0001) in discovery and validation cohorts, respectively. Similarly, patients with high NEV had longer median DMFS (46.6 and 62.2 months) compared to those with low NEV (15.6 and 13.1 months, P=0.005) in discovery and validation cohorts, respectively. Conclusions: The NEV measurement on baseline CT scans may serve as a quantitative imaging biomarker that can objectively reflect tumor biology and provide prognostic insight.

Quantitative PET-MRI for early treatment response assessment in pancreatic ductal adenocarcinoma.

2018 ◽  
Vol 36 (4_suppl) ◽  
pp. 520-520
Author(s):  
Martin Valera Consunji ◽  
Spencer Behr ◽  
Andrew H. Ko ◽  
Margaret A. Tempero ◽  
Pelin Cinar ◽  
...  
Keyword(s):  
Pancreatic Ductal Adenocarcinoma ◽  
Treatment Response ◽  
Early Treatment ◽  
Tumor Size ◽  
Treatment Initiation ◽  
Post Treatment ◽  
Ductal Adenocarcinoma ◽  
Imaging Biomarkers ◽  
Early Assessment ◽  
Early Treatment Response

520 Background: There is an unmet need for improved non-invasive markers to assess early treatment response in pancreatic ductal adenocarcinoma (PDAC). Assessing early treatment response using tumor size on anatomic imaging or serum carbohydrate antigen 19-9 (CA19-9) level is unreliable. In contrast, metabolic and functional imaging is a promising new tool that may differentiate responders from non-responders early on during therapy. Therefore, the objective of this pilot study was to explore the potential of integrated positron emission tomography-magnetic resonance imaging (PET-MRI) to provide imaging biomarkers of early (4 weeks post treatment initiation) response in patients with advanced PDAC. Methods: 13 patients with biopsy-proven locally advanced or metastatic PDAC underwent integrated 18F-fluorodeoxyglucose PET-MRI through the abdomen prior to, and again at 4 weeks post, treatment initiation. Patients also had computed tomography (CT) imaging of the chest, abdomen, and pelvis and serum CA19-9 levels measured, as per standard of care. Patients were classified as responders or non-responders according to RECIST (Response Evaluation Criteria In Solid Tumors) on delayed CT, at 8-12 weeks interval post treatment initiation. Changes in metabolic tumor volume (MTV) and total lesion glycolysis (TLG) from PET, and apparent diffusion coefficient (ADC) from diffusion-weighted MRI at 4 weeks were compared between responders and non-responders. Results: Of the 13 patients, there were 7 responders (partial response by RECIST) and 6 non-responders (progressive or stable disease by RECIST). After 4 weeks of therapy, responders had a significantly greater decrease in MTV (p = 0.003) and TLG (p = 0.006) compared to non-responders. Responders also had a significantly greater increase in mean and minimum ADC (p = 0.004 and p = 0.024, respectively) compared to non-responders. Change in tumor size at 4 weeks was not significantly different between responders and non-responders (p = 0.11). Conclusions: Integrated PET-MRI can provide early assessment of treatment response in patients with advanced PDAC.

Sign in / Sign up

Export Citation Format

Share Document