scholarly journals A machine learning algorithm predicts molecular subtypes in pancreatic ductal adenocarcinoma with differential response to gemcitabine-based versus FOLFIRINOX chemotherapy

2019 ◽  
Author(s):  
Georgios Kaissis ◽  
Sebastian Ziegelmayer ◽  
Fabian Lohöfer ◽  
Katja Steiger ◽  
Hana Algül ◽  
...  
Keyword(s):  
Machine Learning ◽  
Overall Survival ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Median Overall Survival ◽  
Molecular Subtypes ◽  
Supervised Machine Learning ◽  
Ductal Adenocarcinoma ◽  
Chemotherapy Response ◽  
Response To Chemotherapy ◽  
Sensitivity Specificity

AbstractPurposeDevelopment of a supervised machine-learning model capable of predicting clinically relevant molecular subtypes of pancreatic ductal adenocarcinoma (PDAC) from diffusion-weighted-imaging-derived radiomic features.MethodsThe retrospective observational study assessed 55 surgical PDAC patients. Molecular subtypes were defined by immunohistochemical staining of KRT81. Tumors were manually segmented and 1606 radiomic features were extracted withPyRadiomics. A gradient-boosted-tree algorithm (XGBoost) was trained on 70% of the patients (N=28) and tested on 30% (N=17) to predict KRT81+ vs. KRT81-tumor subtypes. The average sensitivity, specificity and ROC-AUC value were calculated. Chemotherapy response was assessed stratified by subtype. Radiomic feature importance was ranked.ResultsThe mean±STDEV sensitivity, specificity and ROC-AUC were 0.90±0.07, 0.92±0.11, and 0.93±0.07, respectively. Patients with a KRT81+ subtype experienced significantly diminished median overall survival compared to KRT81-patients (7.0 vs. 22.6 months, HR 1.44, log-rank-test P=<0.001) and a significantly improved response to gemcitabine-based chemotherapy over FOLFIRINOX (10.14 vs. 3.8 months median overall survival, HR 0.85, P=0.037) compared to KRT81-patients, who responded significantly better to FOLFIRINOX over gemcitabine-based treatment (30.8 vs. 13.4 months median overall survival, HR 0.88, P=0.027).ConclusionsThe machine-learning based analysis of radiomic features enables the prediction of subtypes of PDAC, which are highly relevant for overall patient survival and response to chemotherapy.

The Role of Nanoliposomal Irinotecan Plus Fluorouracil and Folinic Acid as Second-Line Treatment Option in Patients With Metastatic Pancreatic Ductal Adenocarcinoma

2021 ◽  
Author(s):  
Se Jun Park ◽  
Hyunho Kim ◽  
Kabsoo Shin ◽  
Tae Ho Hong ◽  
Ja Hee Suh ◽  
...  
Keyword(s):  
Pancreatic Cancer ◽  
Overall Survival ◽  
Adverse Events ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Real World ◽  
Median Overall Survival ◽  
Ductal Adenocarcinoma ◽  
Nanoliposomal Irinotecan ◽  
Previously Treated ◽  
Grade 3

Abstract BackgroundAccording to the NAPOLI-1 trial, nanoliposomal irinotecan (nal-IRI) plus 5-fluorouracil/leucovorin (5-FU/LV) showed improved overall survival compared to fluorouracil alone for patients with metastatic pancreatic cancer who previously treated gemcitabine-based therapy. In that trial, Asian patients had frequent dose modification due to hematological toxicity. There has been limited information on the clinical benefit and toxicity of this regimen in a real-world setting. Herein, we assessed real-world experience of nal-IRI plus 5-FU/LV in patients with advanced pancreatic cancer after gemcitabine failure.MethodsWe conducted a single institution retrospective analysis of response, survival and safety in patients who had been treated with nal-IRI with 5-FU/LV. Patients with metastatic pancreatic ductal adenocarcinoma previously treated with gemcitabine-based therapy received nal-IRI (80mg/m2) with 5-FU/LV every 2 weeks. ResultsFifty-one patients received nal-IRI plus 5-FU/LV between January 2015 and December 2020. The median age was 67 years, and males were 58.8%. A total of 40 (78.4%) and 11 (21.6%) patients had received one and two lines of prior chemotherapy before enrollment, respectively. Median progression-free survival was 2.8 months (95% confidence interval [CI] 1.8-3.7) and median overall survival was 7.0 months (95% CI 6.0-7.9). Chemotherapy doses were reduced or delayed in 33 (64.7%) patients during the first 6 weeks and median relative dose intensity was 0.87. Thirty-six (70.6%) patients experienced any grade 3 or 4 adverse events. Most common grade 3 or 4 adverse event was neutropenia (58.8%) and most non-hematologic adverse events were under grade 2. Since the start of first-line chemotherapy, median overall survival was 16.3 months (95% CI 14.1-18.4).ConclusionsNal-IRI plus 5-FU/LV seems to be effective, with manageable toxicities, after gemcitabine-based treatment in patients with metastatic pancreatic ductal adenocarcinoma. Trial registration Retrospectively registered

scholarly journals Identification and Validation of Immune Molecular Subtypes in Pancreatic Ductal Adenocarcinoma: Implications for Prognosis and Immunotherapy

2021 ◽  
Vol 12 ◽  
Author(s):  
Ruiyu Li ◽  
Yangzhige He ◽  
Hui Zhang ◽  
Jing Wang ◽  
Xiaoding Liu ◽  
...  
Keyword(s):  
Overall Survival ◽  
Prognostic Factor ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Immune Cell ◽  
Molecular Subtypes ◽  
Molecular Subtype ◽  
The Cancer Genome Atlas ◽  
Ductal Adenocarcinoma ◽  
Expression Data ◽  
Favorable Prognostic Factor

BackgroundPancreatic ductal adenocarcinoma (PDAC) remains treatment refractory. Immunotherapy has achieved success in the treatment of multiple malignancies. However, the efficacy of immunotherapy in PDAC is limited by a lack of promising biomarkers. In this research, we aimed to identify robust immune molecular subtypes of PDAC to facilitate prognosis prediction and patient selection for immunotherapy.MethodsA training cohort of 149 PDAC samples from The Cancer Genome Atlas (TCGA) with mRNA expression data was analyzed. By means of non-negative matrix factorization (NMF), we virtually dissected the immune-related signals from bulk gene expression data. Detailed immunogenomic and survival analyses of the immune molecular subtypes were conducted to determine their biological and clinical relevance. Validation was performed in five independent datasets on a total of 615 samples.ResultsApproximately 31% of PDAC samples (46/149) had higher immune cell infiltration, more active immune cytolytic activity, higher activation of the interferon pathway, a higher tumor mutational burden (TMB), and fewer copy number alterations (CNAs) than the other samples (all P &lt; 0.001). This new molecular subtype was named Immune Class, which served as an independent favorable prognostic factor for overall survival (hazard ratio, 0.56; 95% confidence interval, 0.33-0.97). Immune Class in cooperation with previously reported tumor and stroma classifications had a cumulative effect on PDAC prognostic stratification. Moreover, programmed cell death-1 (PD-1) inhibitors showed potential efficacy for Immune Class (P = 0.04). The robustness of our immune molecular subtypes was further verified in the validation cohort.ConclusionsBy capturing immune-related signals in the PDAC tumor microenvironment, we reveal a novel molecular subtype, Immune Class. Immune Class serves as an independent favorable prognostic factor for overall survival in PDAC patients.

scholarly journals Nanoliposomal irinotecan plus fluorouracil and folinic acid as a second-line treatment option in patients with metastatic pancreatic ductal adenocarcinoma: a retrospective cohort study

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Se Jun Park ◽  
Hyunho Kim ◽  
Kabsoo Shin ◽  
Tae Ho Hong ◽  
Ja Hee Suh ◽  
...  
Keyword(s):  
Pancreatic Cancer ◽  
Overall Survival ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Median Overall Survival ◽  
Progression Free Survival ◽  
Ductal Adenocarcinoma ◽  
Free Survival ◽  
Median Progression Free Survival ◽  
Nanoliposomal Irinotecan ◽  
Previously Treated

Abstract Background According to the NAPOLI-1 trial, nanoliposomal irinotecan (nal-IRI) plus fluorouracil/folinic acid (5-FU/LV) showed improved overall survival compared to fluorouracil alone for patients with metastatic pancreatic cancer who were previously treated with gemcitabine-based therapy. In that trial, Asian patients had frequent dose modification due to haematological toxicity. There has been limited information on the clinical benefits and toxicity of this regimen in real-world settings. In this study, we assessed real-world experience of nal-IRI plus 5-FU/LV in patients with advanced pancreatic cancer after gemcitabine failure. Methods We conducted a single institution, retrospective analysis of response, survival and safety in patients who had been treated with nal-IRI with 5-FU/LV. Patients with metastatic pancreatic ductal adenocarcinoma previously treated with gemcitabine-based therapy received nal-IRI (80 mg/m2) with 5-FU/LV every 2 weeks. Kaplan-Meier analysis was performed to obtain median progression free survival and median overall survival. The hazard ratio and 95% confidence interval (CI) were estimated using a stratified Cox regression model. A multivariate Cox proportional hazards regression model was used to identify the effects of clinical factors. Results Fifty-one patients received nal-IRI plus 5-FU/LV between January 2015 and December 2020. The median age was 67 years, and males were 58.8%. A total of 40 (78.4%) and 11 (21.6%) patients had received one and two lines of prior chemotherapy before enrollment, respectively. Median progression-free survival was 2.8 months (95% CI 1.8–3.7) and median overall survival was 7.0 months (95% CI 6.0–7.9). Chemotherapy doses were reduced or delayed in 33 (64.7%) patients during the first 6 weeks and median relative dose intensity was 0.87. Thirty-six (70.6%) patients experienced grade 3 or 4 adverse events, most commonly neutropenia (58.8%). Most non-haematologic adverse events were under grade 2. Since the start of first-line chemotherapy, median overall survival was 16.3 months (95% CI 14.1–18.4). Conclusions Nal-IRI plus 5-FU/LV seems to be effective, with manageable toxicities, following gemcitabine-based treatment in patients with metastatic pancreatic ductal adenocarcinoma. Nal-IRI plus 5-FU/LV following gemcitabine with nab-paclitaxel is a feasible sequential treatment option in patients with metastatic pancreatic cancer. Trial registration Retrospectively registered.

scholarly journals A machine learning model for the prediction of survival and tumor subtype in pancreatic ductal adenocarcinoma from preoperative diffusion-weighted imaging

2019 ◽  
Vol 3 (1) ◽  
Author(s):  
Georgios Kaissis ◽  
Sebastian Ziegelmayer ◽  
Fabian Lohöfer ◽  
Hana Algül ◽  
Matthias Eiber ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Diffusion Weighted Imaging ◽  
Area Under The Curve ◽  
Supervised Machine Learning ◽  
Ductal Adenocarcinoma ◽  
Recursive Feature Elimination ◽  
Training Cohort ◽  
Diffusion Weighted ◽  
Histopathological Subtype

Abstract Background To develop a supervised machine learning (ML) algorithm predicting above- versus below-median overall survival (OS) from diffusion-weighted imaging-derived radiomic features in patients with pancreatic ductal adenocarcinoma (PDAC). Methods One hundred two patients with histopathologically proven PDAC were retrospectively assessed as training cohort, and 30 prospectively accrued and retrospectively enrolled patients served as independent validation cohort (IVC). Tumors were segmented on preoperative apparent diffusion coefficient (ADC) maps, and radiomic features were extracted. A random forest ML algorithm was fit to the training cohort and tested in the IVC. Histopathological subtype of tumor samples was assessed by immunohistochemistry in 21 IVC patients. Individual radiomic feature importance was evaluated by assessment of tree node Gini impurity decrease and recursive feature elimination. Fisher’s exact test, 95% confidence intervals (CI), and receiver operating characteristic area under the curve (ROC-AUC) were used. Results The ML algorithm achieved 87% sensitivity (95% IC 67.3–92.7), 80% specificity (95% CI 74.0–86.7), and ROC-AUC 90% for the prediction of above- versus below-median OS in the IVC. Heterogeneity-related features were highly ranked by the model. Of the 21 patients with determined histopathological subtype, 8/9 patients predicted to experience below-median OS exhibited the quasi-mesenchymal subtype, whilst 11/12 patients predicted to experience above-median OS exhibited a non-quasi-mesenchymal subtype (p < 0.001). Conclusion ML application to ADC radiomics allowed OS prediction with a high diagnostic accuracy in an IVC. The high overlap of clinically relevant histopathological subtypes with model predictions underlines the potential of quantitative imaging in PDAC pre-operative subtyping and prognosis.

scholarly journals A prospectively validated machine learning model for the prediction of survival and tumor subtype in pancreatic ductal adenocarcinoma

2019 ◽  
Author(s):  
Georgios Kaissis ◽  
Sebastian Ziegelmayer ◽  
Fabian Lohöfer ◽  
Hana Algül ◽  
Matthias Eiber ◽  
...  
Keyword(s):  
Machine Learning ◽  
Overall Survival ◽  
Median Overall Survival ◽  
Validation Cohort ◽  
Learning Algorithm ◽  
External Validation ◽  
Ductal Adenocarcinoma ◽  
Machine Learning Algorithm ◽  
Training Cohort ◽  
Histopathological Subtype

AbstractPurposeTo develop a supervised machine learning algorithm capable of predicting above vs. below-median overall survival from medical imaging-derived radiomic features in a cohort of patients with pancreatic ductal adenocarcinoma (PDAC).Materials and Methods102 patients with histopathologically proven PDAC were retrospectively assessed as the training cohort and 30 prospectively enrolled patients served as the external validation cohort. Tumors were segmented in pre-operative diffusion weighted-(DW)-MRI derived ADC maps and radiomic features were extracted. A Random Forest machine learning algorithm was fit to the training cohort and tested in the external validation cohort. The histopathological subtype of the tumor samples was assessed by immunohistochemistry in 21/30 patients of the external validation cohort. Individual radiomic feature importance was evaluated.ResultsThe machine learning algorithm achieved a sensitivity of 87% and a specificity of 80% (ROC-AUC 90%) for the prediction of above- vs. below-median survival on the unseen data of the external validation cohort. Heterogeneity-related features were highly ranked by the model. Of the 21 patients for whom the histopathological subtype was determined, 8/9 patients predicted by the model to experience below-median overall survival exhibited the quasi-mesenchymal subtype, while 11/12 patients predicted to experience above-median survival exhibited a non-quasi-mesenchymal subtype (Fisher’s exact test P<0.001).ConclusionThe application of machine-learning to the radiomic analysis of DW-MRI-derived ADC maps allowed the prediction of overall survival with high diagnostic accuracy in a prospectively collected cohort. The high overlap of clinically relevant histopathological subtypes with model predictions underlines the potential of quantitative imaging workflows in pre-operative subtyping and risk assessment in PDAC.

scholarly journals Increased dose primary thromboprophylaxis in ambulatory patients with advanced pancreatic ductal adenocarcinoma, a single centre cohort study.

2020 ◽  
Author(s):  
Anthony Maraveyas ◽  
Farzana Haque ◽  
Iqtedar Ahmed Muazzam ◽  
Waqas Ilyas ◽  
George Bozas
Keyword(s):  
Overall Survival ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Median Time ◽  
Major Bleeding ◽  
Thromboembolic Event ◽  
Median Overall Survival ◽  
Ductal Adenocarcinoma ◽  
First Line ◽  
Single Centre ◽  
Ambulatory Patients

Abstract Background: Advanced pancreatic ductal adenocarcinoma (aPDAC) patients have a lifetime all type thromboembolic event (ATTE) rate of 25- 35%. Efficacy and safety of increased dose primary thromboprophylaxis (IDPTP) with low molecular heparin (LMWH) given for 3 months has been shown in two prospective randomized trials. Objectives: To report on efficacy -reduction of all type thromboembolic events (ATTE)-, safety -incidence of Major Bleeding (MB)- and compliance in a single-centre cohort of receiving first line chemotherapy and LMWH-IDPTP. Methods: From May 2009 to October 2016, eighty two patients received IDPTP –LMWH with dalteparin. Schedule: 55kg and below: 7500 IU, between 55 and 80kg: 10,000 IU, above 80kg: 12,500 IU. MB is reported using the International Society of Thrombosis and Haemostasis (ISTH) criteria. ATTE was defined as any arterial or venous event, incidental or clinically symptomatic, including visceral VTE. Results: Mean and median time on dalteparin was 10.2 (95%CI 8.1, 12.4) and 8.0 (95%CI 6.2, 9.7) months respectively. ATTE was observed in 7 (8.5%) of patients, with a median time on IDPTP of 6.2 months (95% CI 10.0, 13.2). MB was seen in 10 (12.2%) patients with a median time on IDPTP of 4.5 months (95% CI 1.6--7.4). Six major bleeds (60%) were the direct or indirect result of aPDAC. Eighty-one patients had died at the time of data collection with a median overall survival time of 8.7 months (95%CI 6.4, 11.0). Thromboembolism and bleeding were late events. No impact of thromboembolism or bleeding on overall survival was observed. Conclusions: IDPTP-dalteparin was associated with lower ATTE occurrence rates than expected and comparable major bleeding rates. ATTE and MB were late events; the majority of MB was from direct or indirect result of locally progressing aPDAC. Since these conditions can frequently arise in aPDAC, IDPTP should be regularly reviewed beyond 3 months.

scholarly journals Increased dose primary thromboprophylaxis in ambulatory patients with advanced pancreatic ductal adenocarcinoma, a single centre cohort study

2020 ◽  
Author(s):  
Anthony Maraveyas ◽  
Farzana Haque ◽  
Iqtedar Ahmed Muazzam ◽  
Waqas MD Il ◽  
George Bozas
Keyword(s):  
Overall Survival ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Major Bleeding ◽  
Thromboembolic Event ◽  
Median Overall Survival ◽  
Ductal Adenocarcinoma ◽  
First Line ◽  
Single Centre ◽  
Ambulatory Patients ◽  
Mean Time

Abstract BackgroundAdvanced pancreatic ductal adenocarcinoma (aPDAC) patients have a lifetime all type thromboembolic event (ATTE) rate of 25- 35%. Efficacy and safety of increased dose primary thromboprophylaxis (IDPTP) with low molecular heparin (LMWH) given for 3 months has been shown in two prospective randomized trials.ObjectivesTo report on efficacy -reduction of all type thromboembolic events (ATTE)-, safety -incidence of Major Bleeding (MB)- and compliance in a single-centre cohort of receiving first line chemotherapy and LMWH-IDPTP.MethodsFrom May 2009 to October 2016, eighty two patients received IDPTP –LMWH with dalteparin. Schedule: 55kg and below: 7500 IU, between 55 and 80kg: 10,000 IU, above 80kg: 12,500 IU. MB is reported using the International Society of Thrombosis and Haemostasis (ISTH) criteria. ATTE was defined as any arterial or venous event, incidental or clinically symptomatic, including visceral VTE.ResultsMean and median time on dalteparin was 10.2 (95%CI 8.1, 12.4) and 8.0 (95%CI 6.2, 9.7) months respectively. ATTE was observed in 7 (8.5%) of patients, with a mean time on IDPTP of 6.8 months (95% CI 3.5-10.2). MB was seen in 10 (12.2%) patients with a mean time on IDPTP of 7.4 months (95% CI 3.9-10.9). Six major bleeds (60%) were the direct or indirect result of aPDAC. Eighty-one patients had died at the time of data collection with a median overall survival time of 8.7 months (95%CI 6.4, 11.0). Thromboembolism and bleeding were late events. No impact of thromboembolism or bleeding on overall survival was observed. ConclusionsIDPTP-dalteparin was associated with lower ATTE occurrence rates than expected and comparable major bleeding rates. ATTE and MB were late events, the majority of MB was from direct or indirect result of locally progressing aPDAC. Since these conditions can frequently arise in aPDAC, IDPTP should be regularly reviewed beyond 3 months.

scholarly journals Deep Convolutional Neural Network-Assisted Feature Extraction for Diagnostic Discrimination and Feature Visualization in Pancreatic Ductal Adenocarcinoma (PDAC) versus Autoimmune Pancreatitis (AIP)

2020 ◽  
Vol 9 (12) ◽  
pp. 4013
Author(s):  
Sebastian Ziegelmayer ◽  
Georgios Kaissis ◽  
Felix Harder ◽  
Friederike Jungmann ◽  
Tamara Müller ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Autoimmune Pancreatitis ◽  
Ct Scans ◽  
Ductal Adenocarcinoma ◽  
Feature Maps ◽  
Sensitivity Specificity

The differentiation of autoimmune pancreatitis (AIP) and pancreatic ductal adenocarcinoma (PDAC) poses a relevant diagnostic challenge and can lead to misdiagnosis and consequently poor patient outcome. Recent studies have shown that radiomics-based models can achieve high sensitivity and specificity in predicting both entities. However, radiomic features can only capture low level representations of the input image. In contrast, convolutional neural networks (CNNs) can learn and extract more complex representations which have been used for image classification to great success. In our retrospective observational study, we performed a deep learning-based feature extraction using CT-scans of both entities and compared the predictive value against traditional radiomic features. In total, 86 patients, 44 with AIP and 42 with PDACs, were analyzed. Whole pancreas segmentation was automatically performed on CT-scans during the portal venous phase. The segmentation masks were manually checked and corrected if necessary. In total, 1411 radiomic features were extracted using PyRadiomics and 256 features (deep features) were extracted using an intermediate layer of a convolutional neural network (CNN). After feature selection and normalization, an extremely randomized trees algorithm was trained and tested using a two-fold shuffle-split cross-validation with a test sample of 20% (n = 18) to discriminate between AIP or PDAC. Feature maps were plotted and visual difference was noted. The machine learning (ML) model achieved a sensitivity, specificity, and ROC-AUC of 0.89 ± 0.11, 0.83 ± 0.06, and 0.90 ± 0.02 for the deep features and 0.72 ± 0.11, 0.78 ± 0.06, and 0.80 ± 0.01 for the radiomic features. Visualization of feature maps indicated different activation patterns for AIP and PDAC. We successfully trained a machine learning model using deep feature extraction from CT-images to differentiate between AIP and PDAC. In comparison to traditional radiomic features, deep features achieved a higher sensitivity, specificity, and ROC-AUC. Visualization of deep features could further improve the diagnostic accuracy of non-invasive differentiation of AIP and PDAC.

Sign in / Sign up

Export Citation Format

Share Document