scholarly journals Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

Cancers ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 376
Author(s):  
Natália Alves ◽  
Megan Schuurmans ◽  
Geke Litjens ◽  
Joeran S. Bosma ◽  
John Hermans ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Pancreatic Ductal Adenocarcinoma ◽  
State Of The Art ◽  
Characteristic Curve ◽  
Lesion Detection ◽  
Ductal Adenocarcinoma ◽  
Test Set ◽  
Pancreas Tumor ◽  
The Impact

Early detection improves prognosis in pancreatic ductal adenocarcinoma (PDAC), but is challenging as lesions are often small and poorly defined on contrast-enhanced computed tomography scans (CE-CT). Deep learning can facilitate PDAC diagnosis; however, current models still fail to identify small (<2 cm) lesions. In this study, state-of-the-art deep learning models were used to develop an automatic framework for PDAC detection, focusing on small lesions. Additionally, the impact of integrating the surrounding anatomy was investigated. CE-CT scans from a cohort of 119 pathology-proven PDAC patients and a cohort of 123 patients without PDAC were used to train a nnUnet for automatic lesion detection and segmentation (nnUnet_T). Two additional nnUnets were trained to investigate the impact of anatomy integration: (1) segmenting the pancreas and tumor (nnUnet_TP), and (2) segmenting the pancreas, tumor, and multiple surrounding anatomical structures (nnUnet_MS). An external, publicly available test set was used to compare the performance of the three networks. The nnUnet_MS achieved the best performance, with an area under the receiver operating characteristic curve of 0.91 for the whole test set and 0.88 for tumors <2 cm, showing that state-of-the-art deep learning can detect small PDAC and benefits from anatomy information.

scholarly journals Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography

2021 ◽  
Author(s):  
Natália Alves ◽  
Megan Schuurmans ◽  
Geke Litjens ◽  
Joeran S. Bosma ◽  
John Hermans ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Pancreatic Ductal Adenocarcinoma ◽  
State Of The Art ◽  
Characteristic Curve ◽  
Lesion Detection ◽  
Ductal Adenocarcinoma ◽  
Test Set ◽  
Pancreas Tumor ◽  
The Impact

Early detection improves prognosis in pancreatic ductal adenocarcinoma (PDAC) but is challenging as lesions are often small and poorly defined on contrast-enhanced computed tomography scans (CE-CT). Deep learning can facilitate PDAC diagnosis, however current models still fail to identify small (&amp;lt;2cm) lesions. In this study, state-of-the-art deep learning models were used to develop an automatic framework for PDAC detection, focusing on small lesions. Additionally, the impact of integrating surrounding anatomy was investigated. CE-CT scans from a cohort of 119 pathology-proven PDAC patients and a cohort of 123 patients without PDAC were used to train a nnUnet for automatic lesion detection and segmentation (nnUnet_T). Two additional nnUnets were trained to investigate the impact of anatomy integration: (1) segmenting the pancreas and tumor (nnUnet_TP), (2) segmenting the pancreas, tumor, and multiple surrounding anatomical structures (nnUnet_MS). An external, publicly available test set was used to compare the performance of the three networks. The nnUnet_MS achieved the best performance, with an area under the receiver operating characteristic curve of 0.91 for the whole test set and 0.88 for tumors &amp;lt;2cm, showing that state-of-the-art deep learning can detect small PDAC and benefits from anatomy information.

scholarly journals Dynamic perfusion CT – A promising tool to diagnose pancreatic ductal adenocarcinoma

Open Medicine ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. 284-292
Author(s):  
Inga Zaborienė ◽  
Giedrius Barauskas ◽  
Antanas Gulbinas ◽  
Povilas Ignatavičius ◽  
Saulius Lukoševičius ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Diagnostic Criteria ◽  
Ct Perfusion ◽  
Characteristic Curve ◽  
Perfusion Ct ◽  
Ductal Adenocarcinoma ◽  
Control Group ◽  
Predictive Values ◽  
Promising Tool

Abstract Background and objective This study deals with an important issue of setting the role and value of the dynamic computed tomography (CT) perfusion analysis in diagnosing pancreatic ductal adenocarcinoma (PDAC). The study aimed to assess the efficacy of perfusion CT in identifying PDAC, even isodense or hardly depicted in conventional multidetector computed tomography. Methods A total of 56 patients with PDAC and 56 control group patients were evaluated in this study. A local perfusion assessment, involving the main perfusion parameters, was evaluated for all the patients. Sensitivity, specificity, positive, and negative predictive values for each perfusion CT parameter were defined using cutoff values calculated using receiver operating characteristic curve analysis. We accomplished logistic regression to identify the probability of PDAC. Results Blood flow (BF) and blood volume (BV) values were significant independent diagnostic criteria for the presence of PDAC. If both values exceed the determined cutoff point, the estimated probability for the presence of PDAC was 97.69%. Conclusions Basic CT perfusion parameters are valuable in providing the radiological diagnosis of PDAC. The estimated BF and BV parameters may serve as independent diagnostic criteria predicting the probability of PDAC.

scholarly journals Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Malte Seemann ◽  
Lennart Bargsten ◽  
Alexander Schlaefer
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Computed Tomography Angiography ◽  
Data Augmentation ◽  
Domain Adaptation ◽  
Synthetic Image ◽  
Wide Range ◽  
The Impact

AbstractDeep learning methods produce promising results when applied to a wide range of medical imaging tasks, including segmentation of artery lumen in computed tomography angiography (CTA) data. However, to perform sufficiently, neural networks have to be trained on large amounts of high quality annotated data. In the realm of medical imaging, annotations are not only quite scarce but also often not entirely reliable. To tackle both challenges, we developed a two-step approach for generating realistic synthetic CTA data for the purpose of data augmentation. In the first step moderately realistic images are generated in a purely numerical fashion. In the second step these images are improved by applying neural domain adaptation. We evaluated the impact of synthetic data on lumen segmentation via convolutional neural networks (CNNs) by comparing resulting performances. Improvements of up to 5% in terms of Dice coefficient and 20% for Hausdorff distance represent a proof of concept that the proposed augmentation procedure can be used to enhance deep learning-based segmentation for artery lumen in CTA images.

scholarly journals Assessing the Impact of the Loss Function, Architecture and Image Type for Deep Learning-Based Wildfire Segmentation

2021 ◽  
Vol 11 (15) ◽  
pp. 7046
Author(s):  
Jorge Francisco Ciprián-Sánchez ◽  
Gilberto Ochoa-Ruiz ◽  
Lucile Rossi ◽  
Frédéric Morandini
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
State Of The Art ◽  
Fire Detection ◽  
Loss Functions ◽  
Wildfire Spread ◽  
Combine Information ◽  
The Impact ◽  
Image Type ◽  
Segmentation Models

Wildfires stand as one of the most relevant natural disasters worldwide, particularly more so due to the effect of climate change and its impact on various societal and environmental levels. In this regard, a significant amount of research has been done in order to address this issue, deploying a wide variety of technologies and following a multi-disciplinary approach. Notably, computer vision has played a fundamental role in this regard. It can be used to extract and combine information from several imaging modalities in regard to fire detection, characterization and wildfire spread forecasting. In recent years, there has been work pertaining to Deep Learning (DL)-based fire segmentation, showing very promising results. However, it is currently unclear whether the architecture of a model, its loss function, or the image type employed (visible, infrared, or fused) has the most impact on the fire segmentation results. In the present work, we evaluate different combinations of state-of-the-art (SOTA) DL architectures, loss functions, and types of images to identify the parameters most relevant to improve the segmentation results. We benchmark them to identify the top-performing ones and compare them to traditional fire segmentation techniques. Finally, we evaluate if the addition of attention modules on the best performing architecture can further improve the segmentation results. To the best of our knowledge, this is the first work that evaluates the impact of the architecture, loss function, and image type in the performance of DL-based wildfire segmentation models.

scholarly journals Investigating the Impact of the Bit Depth of Fluorescence-Stained Images on the Performance of Deep Learning-Based Nuclei Instance Segmentation

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 967
Author(s):  
Amirreza Mahbod ◽  
Gerald Schaefer ◽  
Christine Löw ◽  
Georg Dorffner ◽  
Rupert Ecker ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Computer Assisted ◽  
Important Criterion ◽  
Histological Image ◽  
Computer Mediated ◽  
Image Patches ◽  
Processing Techniques ◽  
The Impact ◽  
Instance Segmentation

Nuclei instance segmentation can be considered as a key point in the computer-mediated analysis of histological fluorescence-stained (FS) images. Many computer-assisted approaches have been proposed for this task, and among them, supervised deep learning (DL) methods deliver the best performances. An important criterion that can affect the DL-based nuclei instance segmentation performance of FS images is the utilised image bit depth, but to our knowledge, no study has been conducted so far to investigate this impact. In this work, we released a fully annotated FS histological image dataset of nuclei at different image magnifications and from five different mouse organs. Moreover, by different pre-processing techniques and using one of the state-of-the-art DL-based methods, we investigated the impact of image bit depth (i.e., eight bits vs. sixteen bits) on the nuclei instance segmentation performance. The results obtained from our dataset and another publicly available dataset showed very competitive nuclei instance segmentation performances for the models trained with 8 bit and 16 bit images. This suggested that processing 8 bit images is sufficient for nuclei instance segmentation of FS images in most cases. The dataset including the raw image patches, as well as the corresponding segmentation masks is publicly available in the published GitHub repository.

scholarly journals MicroRNA-Regulated Signaling Pathways: Potential Biomarkers for Pancreatic Ductal Adenocarcinoma

Stresses ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 30-47
Author(s):  
Maria Mortoglou ◽  
David Wallace ◽  
Aleksandra Buha Buha Djordjevic ◽  
Vladimir Djordjevic ◽  
E. Damla Arisan ◽  
...  
Keyword(s):  
Pancreatic Ductal Adenocarcinoma ◽  
Metabolic Stress ◽  
Resistance Mechanisms ◽  
Current Data ◽  
Cellular Damage ◽  
Ductal Adenocarcinoma ◽  
Aberrant Expression ◽  
Metabolic Alterations ◽  
Limited Effectiveness ◽  
The Impact

Pancreatic ductal adenocarcinoma (PDAC) is the most aggressive and invasive type of pancreatic cancer (PCa) and is expected to be the second most common cause of cancer-associated deaths. The high mortality rate is due to the asymptomatic progression of the clinical features until the advanced stages of the disease and the limited effectiveness of the current therapeutics. Aberrant expression of several microRNAs (miRs/miRNAs) has been related to PDAC progression and thus they could be potential early diagnostic, prognostic, and/or therapeutic predictors for PDAC. miRs are small (18 to 24 nucleotides long) non-coding RNAs, which regulate the expression of key genes by targeting their 3′-untranslated mRNA region. Increased evidence has also suggested that the chemoresistance of PDAC cells is associated with metabolic alterations. Metabolic stress and the dysfunctionality of systems to compensate for the altered metabolic status of PDAC cells is the foundation for cellular damage. Current data have implicated multiple systems as hallmarks of PDAC development, such as glutamine redox imbalance, oxidative stress, and mitochondrial dysfunction. Hence, both the aberrant expression of miRs and dysregulation in metabolism can have unfavorable effects in several biological processes, such as apoptosis, cell proliferation, growth, survival, stress response, angiogenesis, chemoresistance, invasion, and migration. Therefore, due to these dismal statistics, it is crucial to develop beneficial therapeutic strategies based on an improved understanding of the biology of both miRs and metabolic mediators. This review focuses on miR-mediated pathways and therapeutic resistance mechanisms in PDAC and evaluates the impact of metabolic alterations in the progression of PDAC.

scholarly journals Repression of MUC1 promotes expansion and suppressive function of myeloid-derived suppressor cells in pancreatic ductal adenocarcinoma and breast cancer murine models

2020 ◽  
Author(s):  
S. Mahnaz ◽  
L. Das Roy ◽  
M. Bose ◽  
C. De ◽  
S. Nath ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Tumor Microenvironment ◽  
Pancreatic Ductal Adenocarcinoma ◽  
Signaling Pathways ◽  
Suppressor Cells ◽  
Ductal Adenocarcinoma ◽  
Myeloid Derived Suppressor Cells ◽  
Mucin 1 ◽  
Transmembrane Glycoprotein ◽  
The Impact

ABSTRACTMyeloid-derived suppressor cells (MDSCs) are immature myeloid cells that are responsible for immunosuppression in tumor microenvironment. Here we report the impact of mucin 1 (MUC1), a transmembrane glycoprotein, on proliferation and functional activity of MDSCs. To determine the role of MUC1 in MDSC phenotype, we analyzed MDSCs derived from wild type (WT) and MUC1-knockout (MUC1KO) mice bearing pancreatic ductal adenocarcinoma KCKO and breast cancer C57MG xenografts. We observed enhanced tumor growth in MUC1KO mice compared to WT mice in both pancreatic KCKO and breast C57MG cancer models due to increased MDSC population and enrichment of Tregs in tumor microenvironment. Our current study shows that knockdown of MUC1 in MDSCs promotes proliferation and immature suppressive phenotype indicated by increased level of iNOS, ARG1 activity and TGF-β secretion under cancer conditions. Increased activity of MDSCs leads to repression of IL-2 and IFN-ɣ production by T-cells. We were able to find that MDSCs from MUC1KO mice have higher levels of c-Myc and activated pSTAT3 as compared to MUC1 WT mice, that are signaling pathways leading to increased survival, proliferation and prevention of maturation. In summary, MUC1 regulates signaling pathways that maintain immunosuppressive properties of MDSCs. Thus, immunotherapy must target only tumor associated MUC1 on epithelial cells and not MUC1 on hematopoietic cells to avoid expansion and suppressive functions of MDSC.

Sign in / Sign up

Export Citation Format

Share Document