skip to main content

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • 3DGAUnet: 3D Generative Adversarial Networks with a 3D U-Net Based Generator to Achieve the Accurate and Effective Synthesis of Clinical Tumor Image Data for Pancreatic Cancer
Title: 3DGAUnet: 3D Generative Adversarial Networks with a 3D U-Net Based Generator to Achieve the Accurate and Effective Synthesis of Clinical Tumor Image Data for Pancreatic Cancer

Pancreatic ductal adenocarcinoma (PDAC) presents a critical global health challenge, and early detection is crucial for improving the 5-year survival rate. Recent medical imaging and computational algorithm advances offer potential solutions for early diagnosis. Deep learning, particularly in the form of convolutional neural networks (CNNs), has demonstrated success in medical image analysis tasks, including classification and segmentation. However, the limited availability of clinical data for training purposes continues to represent a significant obstacle. Data augmentation, generative adversarial networks (GANs), and cross-validation are potential techniques to address this limitation and improve model performance, but effective solutions are still rare for 3D PDAC, where the contrast is especially poor, owing to the high heterogeneity in both tumor and background tissues. In this study, we developed a new GAN-based model, named 3DGAUnet, for generating realistic 3D CT images of PDAC tumors and pancreatic tissue, which can generate the inter-slice connection data that the existing 2D CT image synthesis models lack. The transition to 3D models allowed the preservation of contextual information from adjacent slices, improving efficiency and accuracy, especially for the poor-contrast challenging case of PDAC. PDAC’s challenging characteristics, such as an iso-attenuating or hypodense appearance and lack of well-defined margins, make tumor shape and texture learning challenging. To overcome these challenges and improve the performance of 3D GAN models, our innovation was to develop a 3D U-Net architecture for the generator, to improve shape and texture learning for PDAC tumors and pancreatic tissue. Thorough examination and validation across many datasets were conducted on the developed 3D GAN model, to ascertain the efficacy and applicability of the model in clinical contexts. Our approach offers a promising path for tackling the urgent requirement for creative and synergistic methods to combat PDAC. The development of this GAN-based model has the potential to alleviate data scarcity issues, elevate the quality of synthesized data, and thereby facilitate the progression of deep learning models, to enhance the accuracy and early detection of PDAC tumors, which could profoundly impact patient outcomes. Furthermore, the model has the potential to be adapted to other types of solid tumors, hence making significant contributions to the field of medical imaging in terms of image processing models.

  more » « less
Award ID(s):
1853636
PAR ID:
10478755
Author(s) / Creator(s):
; ; ; ; ; ; ;
Publisher / Repository:
Cancers
Date Published:
Journal Name:
Cancers
Volume:
15
Issue:
23
ISSN:
2072-6694
Page Range / eLocation ID:
5496
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ( , Photochemistry and Photobiology)
    ABSTRACT

    Pancreatic ductal adenocarcinoma (PDAC) is among the most lethal of human malignancies. PDAC is characterized by dense fibrous stroma which obstructs drug delivery and plays complex tumor‐promoting roles. Photodynamic therapy (PDT) is a light‐based modality which has been demonstrated to be clinically feasible and effective for tumors of the pancreas. Here, we usein vitroheterocellular 3D co‐culture models in conjunction with imaging, bulk rheology and microrheology to investigate photodegradation of non‐cellular components of PDAC stroma (photodynamic stromal depletion, PSD). By measuring the rheology of extracellular matrix (ECM) before and after PDT we find that softening of ECM is concomitant with increased transport of nanoparticles (NPs). At the same time, as shown by us previously, photodestruction of stromal fibroblasts leads to enhanced tumor response to PDT. Here we specifically evaluate the capability of PSD to enhance RNA nanomedicine delivery, using a NP carrying an inhibitor of miR‐21‐5P, a PDAC oncomiR. We confirm improved delivery of this therapeutic NP after PSD by observation of increased expression of PDCD4, a protein target of miR‐21‐5P. Collectively, these results in 3D tumor models suggest that PSD could be developed to enhance delivery of other cancer therapeutics and improve tumor response to treatment.

     
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al ( , Cancer Research)
    Abstract The microenvironment that surrounds pancreatic ductal adenocarcinoma (PDAC) is profoundly desmoplastic and immunosuppressive. Understanding triggers of immunosuppression during the process of pancreatic tumorigenesis would aid in establishing targets for effective prevention and therapy. Here, we interrogated differential molecular mechanisms dependent on cell of origin and subtype that promote immunosuppression during PDAC initiation and in established tumors. Transcriptomic analysis of cell-of-origin–dependent epithelial gene signatures revealed that Nt5e/CD73, a cell-surface enzyme required for extracellular adenosine generation, is one of the top 10% of genes overexpressed in murine tumors arising from the ductal pancreatic epithelium as opposed to those rising from acinar cells. These findings were confirmed by IHC and high-performance liquid chromatography. Analysis in human PDAC subtypes indicated that high Nt5e in murine ductal PDAC models overlaps with high NT5E in human PDAC squamous and basal subtypes, considered to have the highest immunosuppression and worst prognosis. Multiplex immunofluorescent analysis showed that activated CD8+ T cells in the PDAC tumor microenvironment express high levels of CD73, indicating an opportunity for immunotherapeutic targeting. Delivery of CD73 small-molecule inhibitors through various delivery routes reduced tumor development and growth in genetically engineered and syngeneic mouse models. In addition, the adenosine receptor Adora2b was a determinant of adenosine-mediated immunosuppression in PDAC. These findings highlight a molecular trigger of the immunosuppressive PDAC microenvironment elevated in the ductal cell of origin, linking biology with subtype classification, critical components for PDAC immunoprevention and personalized approaches for immunotherapeutic intervention. Significance: Ductal-derived pancreatic tumors have elevated epithelial and CD8+GZM+ T-cell CD73 expression that confers sensitivity to small-molecule inhibition of CD73 or Adora2b to promote CD8+ T-cell–mediated tumor regression. See related commentary by DelGiorno, p. 977 
    more » « less
  3. ; ; ; ; ; ; ; ; ; ( , International Journal of Cancer)
     
    more » « less
  4. ; ; ; ; ; ; ; ( , Frontiers in Immunology)
    Introduction

    Immunotherapies have shown great promise, but are not effective for all tumors types and are effective in less than 3% of patients with pancreatic ductal adenocarcinomas (PDAC). To make an immune treatment that is effective for more cancer patients and those with PDAC specifically, we genetically engineered Salmonella to deliver exogenous antigens directly into the cytoplasm of tumor cells. We hypothesized that intracellular delivery of an exogenous immunization antigen would activate antigen-specific CD8 T cells and reduce tumors in immunized mice.

     Methods

    To test this hypothesis, we administered intracellular delivering (ID) Salmonella that deliver ovalbumin as a model antigen into tumor-bearing, ovalbumin-vaccinated mice. ID Salmonella delivers antigens by autonomously lysing in cells after the induction of cell invasion.

     Results

    We showed that the delivered ovalbumin disperses throughout the cytoplasm of cells in culture and in tumors. This delivery into the cytoplasm is essential for antigen cross-presentation. We showed that co-culture of ovalbumin-recipient cancer cells with ovalbumin-specific CD8 T cells triggered a cytotoxic T cell response. After the adoptive transfer of OT-I CD8 T cells, intracellular delivery of ovalbumin reduced tumor growth and eliminated tumors. This effect was dependent on the presence of the ovalbumin-specific T cells. Following vaccination with the exogenous antigen in mice, intracellular delivery of the antigen cleared 43% of established KPC pancreatic tumors, increased survival, and prevented tumor re-implantation.

     Discussion

    This response in the immunosuppressive KPC model demonstrates the potential to treat tumors that do not respond to checkpoint inhibitors, and the response to re-challenge indicates that new immunity was established against intrinsic tumor antigens. In the clinic, ID Salmonella could be used to deliver a protein antigen from a childhood immunization to refocus pre-existing T cell immunity against tumors. As an off-the-shelf immunotherapy, this bacterial system has the potential to be effective in a broad range of cancer patients.

     
    more » « less
  5. ; ; ( , Springer)
    Automatedanalysisofopticalcolonoscopy(OC)videoframes (to assist endoscopists during OC) is challenging due to variations in color, lighting, texture, and specular reflections. Previous methods ei- ther remove some of these variations via preprocessing (making pipelines cumbersome) or add diverse training data with annotations (but expen- sive and time-consuming). We present CLTS-GAN, a new deep learning model that gives fine control over color, lighting, texture, and specular reflection synthesis for OC video frames. We show that adding these colonoscopy-specific augmentations to the training data can improve state-of-the-art polyp detection/segmentation methods as well as drive next generation of OC simulators for training medical students. The code and pre-trained models for CLTS-GAN are available on Computational Endoscopy Platform GitHub (https://github.com/nadeemlab/CEP). 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email