scholarly journals CGAT: Cell Graph ATtention Network for Grading of Pancreatic Disease Histology Images

2021 ◽  
Vol 12 ◽  
Author(s):  
Mayank Baranwal ◽  
Santhoshi Krishnan ◽  
Morgan Oneka ◽  
Timothy Frankel ◽  
Arvind Rao

Early detection of Pancreatic Ductal Adenocarcinoma (PDAC), one of the most aggressive malignancies of the pancreas, is crucial to avoid metastatic spread to other body regions. Detection of pancreatic cancer is typically carried out by assessing the distribution and arrangement of tumor and immune cells in histology images. This is further complicated due to morphological similarities with chronic pancreatitis (CP), and the co-occurrence of precursor lesions in the same tissue. Most of the current automated methods for grading pancreatic cancers rely on extensive feature engineering involving accurate identification of cell features or utilising single number spatially informed indices for grading purposes. Moreover, sophisticated methods involving black-box approaches, such as neural networks, do not offer insights into the model’s ability to accurately identify the correct disease grade. In this paper, we develop a novel cell-graph based Cell-Graph Attention (CGAT) network for the precise classification of pancreatic cancer and its precursors from multiplexed immunofluorescence histology images into the six different types of pancreatic diseases. The issue of class imbalance is addressed through bootstrapping multiple CGAT-nets, while the self-attention mechanism facilitates visualization of cell-cell features that are likely responsible for the predictive capabilities of the model. It is also shown that the model significantly outperforms the decision tree classifiers built using spatially informed metric, such as the Morisita-Horn (MH) indices.

Cancers ◽  
2019 ◽  
Vol 11 (8) ◽  
pp. 1052
Author(s):  
Iranzu González-Boja ◽  
Antonio Viúdez ◽  
Saioa Goñi ◽  
Enrique Santamaria ◽  
Estefania Carrasco-García ◽  
...  

Pancreatic ductal adenocarcinoma, which represents 80% of pancreatic cancers, is mainly diagnosed when treatment with curative intent is not possible. Consequently, the overall five-year survival rate is extremely dismal—around 5% to 7%. In addition, pancreatic cancer is expected to become the second leading cause of cancer-related death by 2030. Therefore, advances in screening, prevention and treatment are urgently needed. Fortunately, a wide range of approaches could help shed light in this area. Beyond the use of cytological or histological samples focusing in diagnosis, a plethora of new approaches are currently being used for a deeper characterization of pancreatic ductal adenocarcinoma, including genetic, epigenetic, and/or proteo-transcriptomic techniques. Accordingly, the development of new analytical technologies using body fluids (blood, bile, urine, etc.) to analyze tumor derived molecules has become a priority in pancreatic ductal adenocarcinoma due to the hard accessibility to tumor samples. These types of technologies will lead us to improve the outcome of pancreatic ductal adenocarcinoma patients.


2021 ◽  
Vol 12 (11) ◽  
Author(s):  
Chao-Hui Chang ◽  
Siim Pauklin

AbstractPancreatic cancer (PC) is one of the leading causes of cancer-related death worldwide due to delayed diagnosis and limited treatments. More than 90% of all pancreatic cancers are pancreatic ductal adenocarcinoma (PDAC). Extensive communication between tumour cells and other cell types in the tumour microenvironment have been identified which regulate cancer hallmarks during pancreatic tumorigenesis via secretory factors and extracellular vesicles (EVs). The EV-capsuled factors not only facilitate tumour growth locally, but also enter circulation and reach distant organs to construct a pre-metastatic niche. In this review, we delineate the key factors in pancreatic ductal adenocarcinoma derived EVs that mediate different tumour processes. Also, we highlight the factors that are related to the crosstalk with cancer stem cells/cancer-initiating cells (CSC/CIC), the subpopulation of cancer cells that can efficiently metastasize and resist currently used chemotherapies. Lastly, we discuss the potential of EV-capsuled factors in early diagnosis and antitumour therapeutic strategies.


2018 ◽  
Author(s):  
Francois Collin ◽  
Yuhong Ning ◽  
Tierney Phillips ◽  
Erin McCarthy ◽  
Aaron Scott ◽  
...  

AbstractPancreatic cancers are typically diagnosed at late stage where disease prognosis is poor as exemplified by a 5-year survival rate of 8.2%. Earlier diagnosis would be beneficial by enabling surgical resection or earlier application of therapeutic regimens. We investigated the detection of pancreatic ductal adenocarcinoma (PDAC) in a non-invasive manner by interrogating changes in 5-hydroxymethylation cytosine status (5hmC) of circulating cell free DNA in the plasma of a PDAC cohort (n=51) in comparison with a non-cancer cohort (n=41). We found that 5hmC sites are enriched in a disease and stage specific manner in exons, 3’UTRs and transcription termination sites. Our data show that 5hmC density is reduced in promoters and histone H3K4me3-associated sites with progressive disease suggesting increased transcriptional activity. 5hmC density is differentially represented in thousands of genes, and a stringently filtered set of the most significant genes points to biology related to pancreas (GATA4, GATA6, PROX1, ONECUT1) and/or cancer development (YAP1, TEAD1, PROX1, ONECUT1, ONECUT2, IGF1 and IGF2). Regularized regression models were built using 5hmC densities in statistically filtered genes or a comprehensive set of highly variable 5hmC counts in genes and performed with an AUC = 0.94-0.96 on training data. We were able to test the ability to classify PDAC and non-cancer samples with the Elastic net and Lasso models on two external pancreatic cancer 5hmC data sets and found validation performance to be AUC = 0.74-0.97. The findings suggest that 5hmC changes enable classification of PDAC patients with high fidelity and are worthy of further investigation on larger cohorts of patient samples.


2019 ◽  
Author(s):  
Akimasa Hayashi ◽  
Jun Fan ◽  
Ruoyao Chen ◽  
Yu-jui Ho ◽  
Alvin P. Makohon-Moore ◽  
...  

SummaryRecent studies indicate that pancreatic cancer expression profiles are variable and largely reflect a classical or basal-type phenotype. We performed genetic sequencing, RNA-seq, and histologic review of multiregion sampled pancreatic cancers and found that squamous and squamoid features, indicators of poor prognosis, correlate with a “basal-like” expressional type. Cancers with squamous features were more likely to have truncal mutations in chromatin modifier genes and intercellular heterogeneity for MYC amplification that was associated with entosis. In most patients the basal phenotype coexisted with a glandular component, and phylogenetic studies indicated that it arose from a subclonal population in the tumor. These data provide a unifying paradigm for understanding the interrelationship of basal-type features, squamous histology, and somatic mutations in chromatin modifier genes in the context of the clonal evolution of pancreatic cancer.


2016 ◽  
Vol 8s1 ◽  
pp. BIC.S34414 ◽  
Author(s):  
Fataneh Karandish ◽  
Sanku Mallik

Pancreatic ductal adenocarcinoma (PDAC) constitutes 90% of pancreatic cancers. PDAC is a complex and devastating disease with only 1%–3% survival rate in five years after the second stage. Treatment of PDAC is complicated due to the tumor microenvironment, changing cell behaviors to the mesenchymal type, altered drug delivery, and drug resistance. Considering that pancreatic cancer shows early invasion and metastasis, critical research is needed to explore different aspects of the disease, such as elaboration of biomarkers, specific signaling pathways, and gene aberration. In this review, we highlight the biomarkers, the fundamental signaling pathways, and their importance in targeted drug delivery for pancreatic cancers.


Author(s):  
Elad Sharon ◽  
Jingli Zhang ◽  
Kevin Hollevoet ◽  
Seth M. Steinberg ◽  
Ira Pastan ◽  
...  

AbstractTumor mesothelin overexpression is present in different malignancies, including the majority of patients with pancreatic or biliary cancers. The objective of this study was to evaluate the use of shed serum mesothelin and megakaryocyte potentiating factor (MPF) concentrations as biomarkers for these cancers.A total of 151 individuals, divided into five groups, were retrospectively analyzed: healthy donors (n=15), patients with benign non-pancreatic conditions (n=52), benign pancreatic conditions (n=33), biliary carcinoma (n=9), and pancreatic ductal adenocarcinoma (n=42). Mesothelin and MPF concentrations were measured in serum with the Mesomark™ and Human MPF ELISA, respectively.Mesothelin and MPF concentrations did not significantly differ among the five individual participant groups (p=0.34, p=0.33, respectively), nor did any other combination and pair-wise comparison of the participant groups demonstrated a significant difference in biomarker concentrations. In patients with pancreatic cancer, mesothelin or MPF concentrations were not associated with tumor stage (p=0.87, p=0.48, respectively) or differentiation grade (p=0.73, p=0.52, respectively).Serum mesothelin and MPF concentrations, measured with standard available ELISAs, were not specific for benign or pancreatic disease. Both biomarkers were not elevated in patients with pancreatic or biliary cancers, and consequently do not appear to be useful biomarkers for these malignancies.


2021 ◽  
Author(s):  
Hae Hyun Hwang ◽  
Hee Jeong Jeong ◽  
Sangwoo Yoon ◽  
Youngro Byun ◽  
Teruo Okano ◽  
...  

Abstract Pancreatic cancers are classified based on where they occur into those derived from exocrine glands and endocrine glands, thereby showing different anti-cancer effect with medication. Therefore, it is necessary to develop anti-cancer drugs that can inhibit both of these types. To this end, we developed a heparin-taurocholate conjugate, i.e., LHT, to suppress tumor growth via its anti-angiogenic activity. Here we conducted a study to determine the anti-cancer efficacy of LHT on various types of pancreatic cancer, i.e., human pancreatic ductal adenocarcinoma (PDAC) and human pancreatic neuroendocrine tumor (PNET), at orthotopic animal model. LHT reduced not only proliferation of all three cancer cells, but also attenuated the production of VEGF through ERK dephosphorylation. Especially, these effects of LHT were much stronger to PNET (RINm cells). Also, LHT effectively reduced the migration, invasion and tube formation of endothelial cells via dephosphorylation of VEGFR, ERK1/2, and FAK protein. Eventually LHT reduced strongly ~ 50% tumor weights and tumor volumes of all three cancer cells at orthotopic model via anti-proliferation of cancer cells and anti-angiogenesis of endothelial cells. Interestingly, LHT was highly effective to PNET tumor tissue in vivo. Collectively, these findings demonstrated that LHT could be a potential anti-pancreatic cancer medication, regardless of pancreatic cancer types.


2020 ◽  
Vol 7 (1) ◽  
pp. e000408
Author(s):  
Muhammad Nadeem Yousaf ◽  
Fizah S Chaudhary ◽  
Amrat Ehsan ◽  
Alejandro L Suarez ◽  
Thiruvengadam Muniraj ◽  
...  

Pancreatic cancer is one of the leading causes of cancer-related mortality in western countries. Early diagnosis of pancreatic cancers plays a key role in the management by identification of patients who are surgical candidates. The advancement in the radiological imaging and interventional endoscopy (including endoscopic ultrasound (EUS), endoscopic retrograde cholangiopancreatography and endoscopic enteral stenting techniques) has a significant impact in the diagnostic evaluation, staging and treatment of pancreatic cancer. The multidisciplinary involvement of radiology, gastroenterology, medical oncology and surgical oncology is central to the management of patients with pancreatic cancers. This review aims to highlight the diagnostic and therapeutic role of EUS in the management of patients with pancreatic malignancy, especially pancreatic ductal adenocarcinoma.


2019 ◽  
Vol 105 (4) ◽  
pp. 353-358 ◽  
Author(s):  
Oronzo Brunetti ◽  
Claudio Luchini ◽  
Antonella Argentiero ◽  
Stefania Tommasi ◽  
Anita Mangia ◽  
...  

Introduction: Exocrine pancreatic cancers include common type pancreatic ductal adenocarcinoma and cystic neoplasms, which account for 85% and 10% of cases, respectively. The remaining 5% are rare histotypes, comprising adenosquamous carcinoma, acinar cell carcinoma, signet ring cell carcinoma, medullary carcinoma, pancreatoblastoma, hepatoid carcinoma, undifferentiated carcinoma and its variant with osteoclast-like giant cells, solid pseudopapillary carcinoma, and carcinosarcoma. Due to their low incidence, little knowledge is available on their clinical and molecular features as well as on treatment choices. The national initiative presented here aims at the molecular characterization of series of rare histotypes for which therapeutic and follow-up data are available. Methods: A nationwide Italian Rare Pancreatic Cancer (IRaPaCa) task force whose first initiative is a multicentric retrospective study involving 21 Italian cancer centers to retrieve histologic material and clinical and treatment data of at least 100 patients with rare exocrine pancreatic cancers has been created. After histologic revision by a panel of expert pathologists, DNA and RNA from paraffin tissues will be investigated by next-generation sequencing using molecular pathway–oriented and immune-oriented mutational and expression profiling panels constructed availing of the information from the International Cancer Genome Consortium. Bioinformatic analysis of data will drive validation studies by immunohistochemistry and in situ hybridization, as well as nanostring assays. Conclusions: We expect to gather novel data on rare pancreatic cancer types that will be useful to inform the design of therapeutic choices.


Author(s):  
Natalia Juiz ◽  
Abdessamad Elkaoutari ◽  
Martin Bigonnet ◽  
Odile Gayet ◽  
Julie Roques ◽  
...  

SummaryPancreatic ductal adenocarcinoma (PDAC) is composed of stromal, immune and epithelial cells. Transcriptomic analysis of the epithelial compartment allows a binary classification into mainly two phenotypic subtypes, classical and basal-like. However, little is known about the intra-tumor heterogeneity of the epithelial component. Growing evidences suggest that this two side phenotypic segregation is not so clear and that both could coexist in a single tumor. In order to elucidate this hypothesis, we performed single-cell transcriptomic analyses using combinational barcoding on epithelial cells from 6 different classical PDAC obtained by Endoscopic Ultrasound (EUS) with Fine Needle Aspiration (FNA). In order to purify the epithelial compartment, PDAC were grown as Biopsy Derived Pancreatic Cancer Organoids. Single cell transcriptomic analysis allowed the identification of 4 main cell clusters present in different proportions in all tumors. Remarkably, although these tumors were classified as Classical, one of the clusters corresponded to a basal-like. These results depict the unanticipated high heterogeneity of pancreatic cancers and demonstrated that basal-like cells with a high aggressive phenotype are more widespread than expected.


Sign in / Sign up

Export Citation Format

Share Document