scholarly journals Deep Learning in Pancreatic Tissue: Identification of Anatomical Structures, Pancreatic Intraepithelial Neoplasia, and Ductal Adenocarcinoma

2021 ◽  
Vol 22 (10) ◽  
pp. 5385
Author(s):  
Mark Kriegsmann ◽  
Katharina Kriegsmann ◽  
Georg Steinbuss ◽  
Christiane Zgorzelski ◽  
Anne Kraft ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intraepithelial Neoplasia ◽  
Tissue Microarrays ◽  
Pancreatic Tissue ◽  
Control Measures ◽  
Ductal Adenocarcinoma ◽  
Automatic Identification ◽  
Pancreatic Intraepithelial Neoplasia ◽  
Tissue Identification ◽  
Tissue Structures

Identification of pancreatic ductal adenocarcinoma (PDAC) and precursor lesions in histological tissue slides can be challenging and elaborate, especially due to tumor heterogeneity. Thus, supportive tools for the identification of anatomical and pathological tissue structures are desired. Deep learning methods recently emerged, which classify histological structures into image categories with high accuracy. However, to date, only a limited number of classes and patients have been included in histopathological studies. In this study, scanned histopathological tissue slides from tissue microarrays of PDAC patients (n = 201, image patches n = 81.165) were extracted and assigned to a training, validation, and test set. With these patches, we implemented a convolutional neuronal network, established quality control measures and a method to interpret the model, and implemented a workflow for whole tissue slides. An optimized EfficientNet algorithm achieved high accuracies that allowed automatically localizing and quantifying tissue categories including pancreatic intraepithelial neoplasia and PDAC in whole tissue slides. SmoothGrad heatmaps allowed explaining image classification results. This is the first study that utilizes deep learning for automatic identification of different anatomical tissue structures and diseases on histopathological images of pancreatic tissue specimens. The proposed approach is a valuable tool to support routine diagnostic review and pancreatic cancer research.

scholarly journals Differentiation of Pancreatic Ductal Adenocarcinoma From Chronic Pancreatitis by PAM4 Immunohistochemistry

2014 ◽  
Vol 138 (2) ◽  
pp. 220-228 ◽  
Author(s):  
Chanjuan Shi ◽  
Nipun Merchant ◽  
Guy Newsome ◽  
David M. Goldenberg ◽  
David V. Gold
Keyword(s):  
Monoclonal Antibody ◽  
Chronic Pancreatitis ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Early Stage ◽  
High Specificity ◽  
Intraepithelial Neoplasia ◽  
Tissue Microarrays ◽  
Ductal Adenocarcinoma ◽  
Precursor Lesions ◽  
Pancreatic Intraepithelial Neoplasia

Context.—PAM4 is a monoclonal antibody that shows high specificity for pancreatic ductal adenocarcinoma (PDAC) and its neoplastic precursor lesions. A PAM4-based serum immunoassay is able to detect 71% of early-stage patients and 91% with advanced disease. However, approximately 20% of patients diagnosed with chronic pancreatitis (CP) are also positive for circulating PAM4 antigen. The specificity of the PAM4 antibody is critical to the interpretation of the serum-based and immunohistochemical assays for detection of PDAC. Objective.—To determine whether PAM4 can differentiate PDAC from nonneoplastic lesions of the pancreas. Design.—Tissue microarrays of PDAC (N = 43) and surgical specimens from CP (N = 32) and benign cystic lesions (N = 19) were evaluated for expression of the PAM4 biomarker, MUC1, MUC4, CEACAM5/6, and CA19-9. Results.—PAM4 and monoclonal antibodies (MAbs) to MUC1, MUC4, CEACAM5/6, and CA19-9 were each reactive with the majority of PDAC cases; however, PAM4 was the only monoclonal antibody not to react with adjacent, nonneoplastic parenchyma. Although PAM4 labeled 19% (6 of 32) of CP specimens, reactivity was restricted to pancreatic intraepithelial neoplasia associated with CP; inflamed tissues were negative in all cases. In contrast, MUC1, MUC4, CEACAM5/6, and CA19-9 were detected in 90%, 78%, 97%, and 100% of CP, respectively, with reactivity also present in nonneoplastic inflamed tissue. Conclusions.—PAM4 was the only monoclonal antibody able to differentiate PDAC (and pancreatic intraepithelial neoplasia precursor lesions) from benign, nonneoplastic tissues of the pancreas. These results suggest the use of PAM4 for evaluation of tissue specimens, and support its role as an immunoassay for detection of PDAC.

scholarly journals Senolytic elimination of Cox2-expressing senescent cells inhibits the growth of premalignant pancreatic lesions

Gut ◽  
2021 ◽  
pp. gutjnl-2020-321112
Author(s):  
Dror Kolodkin-Gal ◽  
Lior Roitman ◽  
Yossi Ovadya ◽  
Narmen Azazmeh ◽  
Benjamin Assouline ◽  
...  
Keyword(s):  
Tumour Growth ◽  
Precancerous Lesions ◽  
Intraepithelial Neoplasia ◽  
Preventive Therapy ◽  
Ductal Adenocarcinoma ◽  
Potential Contribution ◽  
Pancreatic Intraepithelial Neoplasia ◽  
Promoting Effect ◽  
Paracrine Effects ◽  
Bcl2 Family

ObjectiveCellular senescence limits tumourigenesis by blocking the proliferation of premalignant cells. Additionally, however, senescent cells can exert paracrine effects influencing tumour growth. Senescent cells are present in premalignant pancreatic intraepithelial neoplasia (PanIN) lesions, yet their effects on the disease are poorly characterised. It is currently unknown whether senolytic drugs, aimed at eliminating senescent cells from lesions, could be beneficial in blocking tumour development.DesignTo uncover the functions of senescent cells and their potential contribution to early pancreatic tumourigenesis, we isolated and characterised senescent cells from PanINs formed in a Kras-driven mouse model, and tested the consequences of their targeted elimination through senolytic treatment.ResultsWe found that senescent PanIN cells exert a tumour-promoting effect through expression of a proinflammatory signature that includes high Cox2 levels. Senolytic treatment with the Bcl2-family inhibitor ABT-737 eliminated Cox2-expressing senescent cells, and an intermittent short-duration treatment course dramatically reduced PanIN development and progression to pancreatic ductal adenocarcinoma.ConclusionsThese findings reveal that senescent PanIN cells support tumour growth and progression, and provide a first indication that elimination of senescent cells may be effective as preventive therapy for the progression of precancerous lesions.

Abstract B115: Eflornithine (DFMO) Prevents Progression of Pancreatic Intraepithelial Neoplasia to Ductal Adenocarcinoma in LSL-KrasG12D/+ Mice

2012 ◽  
Vol 5 (11 Supplement) ◽  
pp. B115-B115
Author(s):  
Altaf Mohammed ◽  
Naveena B. Janakiram ◽  
Misty Brewer ◽  
Rebekah L. Ritchie ◽  
Anuj Marya ◽  
...  
Keyword(s):  
Intraepithelial Neoplasia ◽  
Ductal Adenocarcinoma ◽  
Pancreatic Intraepithelial Neoplasia

scholarly journals Acinar transformed ductal cells exhibit differential mucin expression in a tamoxifen-induced pancreatic ductal adenocarcinoma mouse model

Biology Open ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. bio052878
Author(s):  
Kavita Mallya ◽  
Dhanya Haridas ◽  
Parthasarathy Seshacharyulu ◽  
Ramesh Pothuraju ◽  
Wade M. Junker ◽  
...  
Keyword(s):  
Pancreatic Cancer ◽  
Mouse Model ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Intraepithelial Neoplasia ◽  
Ductal Adenocarcinoma ◽  
Chemotherapy Response ◽  
Pancreatic Intraepithelial Neoplasia ◽  
Ductal Cells ◽  
Mucin Expression ◽  
Acinar To Ductal Metaplasia

ABSTRACTPancreatic cancer (PC) is acquired postnatally; to mimic this scenario, we developed an inducible KrasG12D; Ptf1a-CreER™ (iKC) mouse model, in which Kras is activated postnatally at week 16 upon tamoxifen (TAM) administration. Upon TAM treatment, iKC mice develop pancreatic intraepithelial neoplasia (PanIN) lesions and PC with metastasis at the fourth and fortieth weeks, respectively, and exhibited acinar-to-ductal metaplasia (ADM) and transdifferentiation. Kras activation upregulated the transcription factors Ncoa3, p-cJun and FoxM1, which in turn upregulated expression of transmembrane mucins (Muc1, Muc4 and Muc16) and secretory mucin (Muc5Ac). Interestingly, knockdown of KrasG12D in multiple PC cell lines resulted in downregulation of MUC1, MUC4, MUC5AC and MUC16. In addition, iKC mice exhibited ADM and transdifferentiation. Our results show that the iKC mouse more closely mimics human PC development and can be used to investigate pancreatic ductal adenocarcinoma (PDAC) biomarkers, early onset of PDAC, and ADM. The iKC model can also be used for preclinical strategies such as targeting mucin axis alone or in combination with neo-adjuvant, immunotherapeutic approaches and to monitor chemotherapy response.

scholarly journals c-Fos/ERK promotes the progression from pancreatic intraepithelial neoplasia to pancreatic ductal adenocarcinoma

2016 ◽  
Vol 36 (6) ◽  
pp. 3413-3420 ◽  
Author(s):  
Lei You ◽  
Xiaoxia Ren ◽  
Yongxing Du ◽  
Wenjing Zhao ◽  
Ming Cui ◽  
...  
Keyword(s):  
Pancreatic Ductal Adenocarcinoma ◽  
Intraepithelial Neoplasia ◽  
Ductal Adenocarcinoma ◽  
Pancreatic Intraepithelial Neoplasia

scholarly journals Developmental Pathways Direct Pancreatic Cancer Initiation from Its Cellular Origin

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Maximilian Reichert ◽  
Karin Blume ◽  
Alexander Kleger ◽  
Daniel Hartmann ◽  
Guido von Figura
Keyword(s):  
Pancreatic Cancer ◽  
Poor Prognosis ◽  
Intraepithelial Neoplasia ◽  
Developmental Pathways ◽  
Ductal Adenocarcinoma ◽  
Pancreatic Intraepithelial Neoplasia ◽  
Cellular Origin ◽  
Mucinous Neoplasm ◽  
Cancer Initiation ◽  
Advanced Stages

Pancreatic ductal adenocarcinoma (PDA) is characterized by an extremely poor prognosis, since it is usually diagnosed at advanced stages. In order to employ tools for early detection, a better understanding of the early stages of PDA development from its main precursors, pancreatic intraepithelial neoplasia (PanIN), and intraductal papillary mucinous neoplasm (IPMN) is needed. Recent studies on murine PDA models have identified a different exocrine origin for PanINs and IPMNs. In both processes, developmental pathways direct the initiation of PDA precursors from their cellular ancestors. In this review, the current understanding of early PDA development is summarized.

Sign in / Sign up

Export Citation Format

Share Document